User equipment, network node and methods in a wireless communications network

Abstract

A method performed by a User Equipment (UE) is provided. The method is for initiating a procedure for transitioning the UE from a power saving mode of operation to a connected mode of operation in a wireless communications network. The UE performs (703) one or more predictions of data volume in a protocol buffer. The data volume is predicted to be transmitted between the UE and a Radio Access Network (RAN) node in an upcoming data transmission. Before data of the upcoming data transmission arrives in the protocol buffer, the UE initiates (704) the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer. The UE sends (705) a request to the RAN node. The request is for the transitioning to the connected mode of operation.

Description

[0001] USER EQUIPMENT, NETWORK NODE AND METHODS IN A WIRELESS

[0002] COMMUNICATIONS NETWORK

[0003] TECHNICAL FIELD

[0004] Embodiments herein relate to a User Equipment (UE), a Radio Access Node (RAN) node and methods therein. In some aspects, they relate to a UE initiated procedure for transitioning the UE from a power saving mode of operation to a connected mode of operation in a wireless communications network.

[0005] BACKGROUND

[0006] In a typical wireless communication network, wireless devices, also known as wireless communication devices, mobile stations, stations (STA) and / or User Equipment (UE), communicate via a Wide Area Network or a Local Area Network such as a Wi-Fi network or a cellular network comprising a Radio Access Network (RAN) part and a Core Network (CN) part. The RAN covers a geographical area which is divided into service areas or cell areas, which may also be referred to as a beam or a beam group, with each service area or cell area being served by a radio network node such as a radio access node e.g., a Wi-Fi access point or a radio base station (RBS), which in some networks may also be denoted, for example, a NodeB, eNodeB (eNB), or gNB as denoted in Fifth Generation (5G) telecommunications. A service area or cell area is a geographical area where radio coverage is provided by the radio network node. The radio network node communicates over an air interface operating on radio frequencies with the wireless device within range of the radio network node.

[0007] 3GPP is the standardization body for specify the standards for the cellular system evolution, e.g., including 3G, 4G, 5G, Sixth Generation (6G) and the future evolutions. Specifications for the Evolved Packet System (EPS), also called a Fourth Generation (4G) network, have been completed within the 3rd Generation Partnership Project (3GPP). As a continued network evolution, the new releases of 3GPP specifies a 5G network also referred to as 5G New Radio (NR).

[0008] Frequency bands for 5G NR are being separated into two different frequency ranges, Frequency Range 1 (FR1) and Frequency Range 2 (FR2). FR1 comprises sub-6 GHz frequency bands. Some of these bands are bands traditionally used by legacy standards but have been extended to cover potential new spectrum offerings from 410 MHz to 7125 MHz. FR2 comprises frequency bands from 24.25 GHz to 52.6 GHz. Bands in this millimeter wave range have shorter range but higher available bandwidth than bands in the FR1.

[0009] Multi-antenna techniques may significantly increase the data rates and reliability of a wireless communication system. For a wireless connection between a single user, such as UE, and a base station, the performance is in particular improved if both the transmitter and the receiver are equipped with multiple antennas, which results in a Multiple-Input Multiple-Output (MIMO) communication channel. This may be referred to as Single-User (SU)-MIMO. In the scenario where MIMO techniques is used for the wireless connection between multiple users and the base station, MIMO enables the users to communicate with the base station simultaneously using the same time-frequency resources by spatially separating the users, which increases further the cell capacity. This may be referred to as Multi-User (MU)-MIMO. Note that MU-MIMO may benefit when each UE only has one antenna. Such systems and / or related techniques are commonly referred to as MIMO.

[0010] Radio Resource Control (RRC) procedures for transitioning to RRC_CONNECTED in NR

[0011] Both in NR and in LTE, a UE may either be in RRCJDLE or RRCJNACTIVE, for procedures optimized for power savings, or RRC_CON NE TED, for procedures optimized for data transmission. The functionalities performed by the UE and / or a Radio Access Network (RAN) in each of these RRC states can be found in § 3GPP TS 38.300.

[0012] Figure 1 illustrates an overview of a UE RRC state machine and state transitions in NR. A UE has only one RRC state in NR at one time.

[0013] RRC Setup / establishment procedure

[0014] The purpose of this procedure is to establish an RRC connection. RRC connection establishment involves Signalling Radio Bearer 1 (SRB1) establishment. SRB1 is used for transport of RRC messages. The procedure is also used to transfer the initial Non-Acess Stratum (NAS) dedicated information and / or message from the UE to the network such as the RAN. The network applies the procedure e.g. when establishing an RRC connection and when the UE is resuming or re-establishing an RRC connection, and the network is not able to retrieve or verify the UE context. In this case, UE receives a RRC Setup message (RRCSetup) and responds with a RRC Setup Complete message (RRCSetupComplete). Figure 2 summarizes the UE triggered transition from RRCJDLE to RRC_CONNECTED, which may either be called an RRC setup or an RRC establishment procedure:

[0015] 1. The UE requests to setup a new connection from RRCJDLE. That may be triggered due to the notification of higher layers of incoming data originated from the UE.

[0016] 2 / 2a. The gNB completes the RRC setup procedure.

[0017] NOTE: The scenario where the gNB rejects the request is described below.

[0018] 3. The first NAS message from the UE, piggybacked in RRCSetupComplete, is sent to AMF.

[0019] 4 / 4a / 5 / 5a. Additional NAS messages may be exchanged between UE and AMF, see TS 23.502

[0022] ,

[0020] 6. The AMF prepares the UE context data (including PDU session context, the Security Key, UE Radio Capability and UE Security Capabilities, etc.) and sends it to the gNB.

[0021] 7 / 7a. The gNB activates the AS security with the UE.

[0022] 8 / 8a. The gNB performs the reconfiguration to setup SRB2 and Data Radio Bearers (DRB)s.

[0023] 9. The gNB informs the AMF that the setup procedure is completed.

[0024] NOTE 1: RRC messages in step 1 and 2 use SRBO, all the subsequent messages use SRB1. Messages in steps 7 / 7a are integrity protected. From step 8 on, all the messages are integrity protected and ciphered.

[0025] NOTE 2: For signalling only connection, step 8 is skipped since SRB2 and DRBs are not not setup.

[0026] In further details, the following steps are performed by the UE during the RRC establishment procedure as defined in 3GPP TS 38.331 Release 16 V16.7.0 (RRC specifications): ******************************************************************************************************

[0027] 5.3.3.2 Initiation

[0028] The UE initiates the procedure when upper layers request establishment of an RRC connection while the UE is in RRC IDLE and it has acquired essential system information.

[0029] ******************************************************************************************************

[0030] RRC Resume procedure The purpose of this procedure is to resume a suspended RRC connection, including resuming SRB(s) and DRB(s) or perform an RNA update. This can be a UE triggered transition from RRCJNACTIVE to RRC_CONNECTED e.g. when incoming data is detected. Figure 3 summarizes the UE triggered transition from RRCJNACTIVE to RRC_CONNECTED in case of UE context retrieval success:

[0031] 1. The UE resumes from RRCJNACTIVE, providing the Inactive- Radio Network Temporary Identifier (l-RNTI) , allocated by the last serving gNB.

[0032] 2. The gNB, if able to resolve the gNB identity contained in the l-RNTI, requests the last serving gNB to provide UE Context data.

[0033] 3. The last serving gNB provides UE context data.

[0034] 4 / 5. The gNB and UE completes the resumption of the RRC connection.

[0035] NOTE: User Data can also be sent in step 5 if the grant allows.

[0036] 6. If loss of DL user data buffered in the last serving gNB shall be prevented, the gNB provides forwarding addresses.

[0037] 7 / 8. The gNB performs path switch.

[0038] 9. The gNB triggers the release of the UE resources at the last serving gNB.

[0039] After step 1 above, when the gNB decides to use a single RRC message to reject the Resume Request right away and keep the UE in RRCJNACTIVE without any reconfiguration (e.g. as described in the two examples below), or when the gNB decides to setup a new RRC connection, SRBO (without security) is used. Conversely, when the gNB decides to reconfigure the UE (e.g. with a new DRX cycle or RNA) or when the gNB decides to push the UE to RRCJDLE, SRB1 (with integrity protection and ciphering as previously configured for that SRB) shall be used.

[0040] NOTE: SRB1 can only be used once the UE Context is retrieved i.e. after step 3.

[0041] In further details, the following steps are performed by the UE during the RRC resume procedure as defined in TS 38.331 (RRC specifications): ******************************************************************************************************

[0042] 5.3.13.2 Initiation

[0043] The UE initiates the procedure when upper layers or AS (when responding to RAN paging or upon triggering RNA updates while the UE is in RRC INACTIVE) requests the resume of a suspended RRC connection.

[0044] ****************************************************************************************************** Notice that in current 3GPP RRC specifications TS 38.331 Release 16 (V16.7.0) and 3GPP NAS specification TS 24.501 (v17.4.1) for 4G and 5G, it is the higher layers, e.g. Non-Access Stratum protocol layer, which trigger a transition to RRC_CONNECTED due to the presence of UL data in the UE buffer, originated in the UE, often called Mobile Originated (MO) access. In the higher layers, such as in NAS, a UE in RRCJDLE would first need to establish an RRC Connection before transmitting data, hence, from a NAS perspective, upcoming data in the UL buffer that needs to be transmitted would trigger NAS to request RRC (also called Access Stratum (AS) to initiate a connection establishment.

[0045] From a NAS / AS modeling perspective, a connection establishment would require an initial NAS message to be transmitted in the RRCSetupComplete message (at least partially) so that the model could be that the initial NAS message is considered as the trigger to initiate the establishment procedure, wherein the initial NAS message was triggered by incoming uplink data in the buffer of the UE.

[0046] This is modeled as follows in the NAS specifications, 3GPP TS 24.501 Release 17 (V17.4.1): ******************************************************************************************************

[0047] 5.3 General on elementary 5GMM procedures

[0048] [...]

[0049] 5.3.1.1 Establishment of the N1 NAS signalling connection

[0050] When the UE is in 5GMM-IDLE mode over 3GPP access and needs to transmit an initial NAS message, the UE shall request the lower layer to establish an RRC connection. Upon indication from the lower layers that the RRC connection has been established, the UE shall consider that the N1 NAS signalling connection over 3GPP access is established and enter 5GMM-CONNECTED mode over 3GPP access. ******************************************************************************************************

[0051] In the case of RRC resume, it is stated that uplink data packet when receiving an indication from the lower layers that the RRC connection has been suspended, triggers a request to the lower layers to transition to RRC_CONNECTED state. In other words, an uplink data packet can trigger the transition to RRC_CONNECTED.

[0052] This is modeled as follows in the NAS specifications, 3GPP TS 24.501 Release 17 (V17.4.1)::

[0053] ****************************************************************************************************** 5.3.1.4 5GMM-CONNECTED mode with RRC inactive indication

[0054] This subclause is only applicable for UE's 5GMM mode over 3GPP access. The 5GMM-CONNECTED mode with RRC inactive indication is not supported when the UE is in NB-N1 mode.

[0055] The UE is in 5GMM-CONNECTED mode with RRC inactive indication when the UE is in: a) 5GMM-CONNECTED mode over 3GPP access at the NAS layer; and b) RRC INACTIVE state at the AS layer (see 3GPP TS 38.300 Release 16 (V16.8.0).

[0056] [...]

[0057] The UE shall transition from 5GMM-CONNECTED mode over 3GPP access to 5GMM-CONNECTED mode with RRC inactive indication upon receiving an indication from the lower layers that the RRC connection has been suspended.

[0058] NOTE 0: Any pending procedure or uplink data packet when receiving an indication from the lower layers that the RRC connection has been suspended, triggers a request to the lower layers to transition to RRC CONNECTED state. This is also the case when the pending procedure or uplink data packet triggered a previous request to the lower layers to transition to RRC CONNECTED state. ******************************************************************************************************

[0059] Artificial Intelligence (Al) and Machine Learning (ML)

[0060] Machine learning (ML) may be used to generate a predictive function (or model) for a given dataset; the dataset is typically a mapping between a given input to an output. The predictive function, or mapping function, may be generated in a training phase, where the training phase assumes knowledge of both the input and output. There may also be a testing phase comprising predicting the output for a given input. Applications of ML are for example curve fitting, facial recognition and spam filter. Figure 4 depicts an example of classification with machine learning. Left graph a) where the features provide less class separation in comparison with using the features in right graph b). The task is to train a predictive function that separates the two classes, circle and cross. In Figure 4, feature 1 and 2 provides low separation of the output class, hence leading to a worse prediction performance in comparison with the graph b) to the right in the figure. Where using feature 3 and 4 enables a better separation and classifying performance. In general, the performance of the machine learner is proportional to the correlation between the input and the output, one key problem in machine learning is to find or create good features, another problem is to collect enough data samples.

[0061] An example of classification in a radio context is a prediction of coverage on a frequency different from the serving frequency, here called secondary frequency, based on measurements on a serving frequency. In such an example, the Reference Signal Received Power (RSRP) of a secondary frequency may be predicted based on the RSRP, TA and precoder index of cells on a serving frequency, including neighbor cells. The data may be collected through measurement reports or through specific combinations of events such as A2 or A5 and inter-frequency measurement reports. Once trained, the ML model will be able to output an estimate of coverage for different frequencies, for new input data, which can be utilized in different ways such as in mobility to filter out relevant frequency candidates.

[0062] Al / ML in 3GPP (RAN3): Release 16 and Release 17

[0063] Al and ML has been studied in 3GPP in Release 17 and some initial functionality is planned to be standardized in Release 18. The outcome of the study in Release 17 is documented in the Technical Report (TR) 37.817 entitled “Study on enhancement for Data Collection for NR and EN-Dual Connectivity (DC)”. 3GPP has considered principles for RAN intelligence enabled by Al, the functional framework (e.g. the Al functionality and the input / output of the component for Al enabled optimization) and use cases and solutions of Al enabled RAN, based on the current architecture and interfaces of Release 17.

[0064] • Data Collection is a function that provides input data to Model training and Model inference functions. AI / ML algorithm specific data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) is not carried out in the Data Collection function. Examples of input data may include measurements from UEs or different network entities, feedback from Actor, output from an AI / ML model.

[0065] - Training Data: Data needed as input for the AI / ML Model Training function.

[0066] - Inference Data: Data needed as input for the AI / ML Model Inference function.

[0067] • Model Training is a function that performs the ML model training, validation, and testing. The Model training function is also responsible for data preparation (e.g. data preprocessing and cleaning, formatting, and transformation) based on Training Data delivered by a Data Collection function, if required. - (FFS) Model Deployment / Update: Deploy or update an AI / ML model to

[0068] Model Inference function.

[0069] • Model Inference is a function that provides AI / ML model inference output (e.g. predictions or decisions). The Model inference function is also responsible for data preparation (e.g. data pre-processing and cleaning, formatting, and transformation) based on Inference Data delivered by a Data Collection function, if required.

[0070] - Output: The inference output of the AI / ML model produced by a Model

[0071] Inference function.

[0072] • Actor is a function that receives the output from the Model inference function and triggers or performs corresponding actions. The Actor may trigger actions directed to other entities or to itself.

[0073] - Feedback: Information that may be needed to derive training or inference data or performance feedback.

[0074] Al / ML in 3GPP (RAN1), in upcoming Release-18

[0075] The application of AI / ML to wireless communications has been thus far limited to implementation-based approaches, both, at the network and the UE sides. The study on enhancement for data collection for NR and Evolved Universal Terrestrial Radio Access Network (E-UTRAN) New Radio (EN)-DC in Release 17 has examined the functional framework for RAN intelligence enabled by further enhancement of data collection through use cases, examples etc. and identify the potential standardization impacts on current NG-RAN nodes and interfaces. In 3GPP Technical Specification Group Service and System Aspects (TSG SA) Working Group (WG) 2 AI / ML related study, a network functionality Network Data Analytics Function (NWDAF) was introduced in Release 15 and has been enhanced in Release 16 and Release 17.

[0076] In Release 18, 3GPP is starting a new study. The goal is to explore the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance, e.g., improved throughput, robustness, accuracy or reliability, and / or reduced complexity / overhead. Enhanced performance here depends on use cases under consideration and may be, e.g., improved throughput, robustness, accuracy or reliability, or reduced overhead, etc. Through studying a few carefully selected use cases, assessing their performance in comparison with traditional methods and the associated potential specification impacts that enable their solutions, this SI will lay the foundation for future Air-Interface use cases leveraging AI / ML techniques. The goal is that sufficient use cases will be considered to enable the identification of a common AI / ML framework, including functional requirements of AI / ML architecture, which could be used in subsequent projects. The study should also identify areas where AI / ML could improve the performance of air interface functions.

[0077] The study will serve identifying what is required for an adequate AI / ML model characterization and description establishing pertinent notation for discussions and subsequent evaluations. Various levels of collaboration between the gNB and UE are identified and considered. Evaluations to exercise the attainable gains of AI / ML based techniques for the use cases under consideration will be carried out with the corresponding identification of Key Performance Indicators (KPIs) with the goal to have a better understanding of the attainable gains and associated complexity requirements. Finally, specification impact will be assessed in order to improve the overall understanding of what would be required to enable AI / ML techniques for the air-interface.

[0078] The 3GPP framework for AI / ML for air interface corresponding to each target use case regarding aspects such as performance, complexity, and potential specification impact is to be studied.

[0079] Use cases to focus on:

[0080] - Initial set of use cases includes: o Channel State Information (CSI) feedback enhancement, e.g., overhead reduction, improved accuracy, prediction [RAN1] o Beam management, e.g., beam prediction in time, and / or spatial domain for overhead and latency reduction, beam selection accuracy improvement [RAN1] o Positioning accuracy enhancements for different scenarios including, e.g., those with heavy NLOS conditions [RAN1] o RS overhead reduction [RAN1] o RRM Mobility, e.g., prediction in time or frequency for robustness, interruption and overhead reduction [RAN2]

[0081] - Finalize representative set of use cases (reduced from the initial set and minimizing sub use cases) for characterization and baseline performance evaluations

[0082] AI / ML model and description to identify common and specific characteristics for framework investigations: - Characterize the defining stages of AI / ML related algorithms and associated complexity: o Model generation, e.g., model training (including input / output, pre- / post- process, as applicable), model validation, model testing, as applicable o Inference operation, e.g., input / output, pre- / post-process, as applicable

[0083] - Identify various levels of collaboration between UE and gNB, e.g., o No collaboration: implementation-based only AI / ML algorithms without information exchange [for comparison purposes] o Various levels of UE / gNB collaboration targeting at separate or joint ML operation.

[0084] - Identify lifecycle management of AI / ML model: e.g., model deployment (initiation / configuration), model monitoring, model updating, and model transfer

[0085] - Data set for training, inference, validation, and testing

[0086] - Identify common notation and terminology for AI / ML related functions, procedures and interfaces

[0087] For the use cases under consideration:

[0088] 1) Evaluate performance benefits of AI / ML based algorithms:

[0089] - Methodology based on statistical models (from TR 38.901 and TR 38.857 [positioning]), for link and system level simulations. o Extensions of 3GPP evaluation methodology for better suitability to AI / ML based techniques should be considered as needed. o Whether field data are needed to further assess the performance and robustness in real-world environments should be discussed as part of the study. o User data privacy needs to be preserved. o Need for common dataset construction for training, validation and test for the selected use cases o Consider adequate model training strategy and associated implications, e.g., offline training vs. online training of models.

[0090] - KPIs: Determine the common KPIs and corresponding requirements for the AI / ML operations. Determine the use-case specific KPIs and benchmarks of the selected usecases. o Performance and computational complexity of AI / ML based algorithms should be compared to that of a state-of-the-art (non-AI / ML and / or implementation-based AI / ML) baseline o Overhead, power consumption (including computational), memory storage, and hardware requirements (including for given processing delays) associated with enabling respective AI / ML scheme, as well as generalization capability should be considered and documented.

[0091] The need to define Typical Al model(s) for calibration shall be discussed as part of this study.

[0092] 2) Assess potential specification impact, specifically for the agreed use cases in the final representative set and for a common framework:

[0093] - PHY layer aspects including (RAN1) o Consider aspects related to, e.g., the specification of the Al Model lifecycle management, and dataset construction for training, validation and test for the selected use cases o Use case and collaboration level specific specification impact, such as new signalling, assistance information, measurement, and feedback

[0094] - Protocol aspects including (Except use case study, RAN2 only start following general assessment after there is sufficient progress on use study in RAN1) o Consider aspects related to, e.g., capability indication, configuration procedures (training / inference), validation and testing procedures, and management of data and AI / ML model o Collaboration level specific specification impact per use case including signalling design to support the collaboration identified in RAN1

[0095] - Interoperability and testability aspects (RAN4 only start the work after there is sufficient progress on use case study in RAN1 and RAN2) o UE and gNB requirements and testing frameworks to validate AI / ML based performance enhancements and ensuring that UE and gNB with AI / ML meet or exceed the existing minimum requirements o Consider the need and implications for AI / ML processing capabilities definition Note: specific AI / ML models are not expected to be specified and are left to implementation.

[0096] Al and ML in 6G

[0097] A lot has been mentioned in AI / ML for 6G, but so far, not much has been publicly disclosed for RAN2 protocols. However, the topic is expected to be brought up in the European Union 6G project Hexa-X. According to the latest information about the project, in this area the objective is to make the most out of Al technology applied to networks - to develop methodology, algorithms, and architectural requirements for an Al-native network, through Al-driven air interface and Al governance. The 6G networks should be designed to incorporate Al operation to optimize network performance, as well as operate to optimize Al performance for other services. Key targets here are to embed Al functionality into the signal processing chain and develop suitable learning methods. Governance and protocols for secure Al needs to be developed for the integration of Al into trustworthy network systems. Further, intelligent orchestration covering dynamic resource management, data-driven optimization, and intent-based operation will be developed to streamline operations of future networks. The potential of node programmability will be studied for improved development speed and flexibility.

[0098] When a UE is in RRCJDLE to RRCJNACTIVE and detects a MO call or session, e.g. due to the presence of data in the UL buffer, at the higher layers e.g. NAS, the UE triggers the initiation of an RRC resume procedure, if the UE is in RRCJNACTIVE, or an RRC establishment procedure, if the UE is in RRCJDLE.

[0099] One of the key performance indicators of 3GPP systems, including the LTE and 5G NR, is the Control Plane (CP) latency. According to the 3GPP Technical Report 38.913, the control plane latency refers to the time to move from a battery efficient state, e.g., RRCJDLE, or any other state optimized for power savings such as RRCJNACTIVE, to start of continuous data transfer, e.g., ACTIVE, RRC_CONNECTED, optimized for data transmissions / reception. The target for control plane latency should be 10ms for NR, and since LTE times the CP latency value has been proposed to be reduced more and more, from 100ms to 50ms in LTE Advanced, which means that even lower values are expected in the 5G NR evolution and 6G. This would be the delay from the moment the button of an application in the Smartphone is pressed, which would generate some UL data in buffer, until the time the UE starts continuous data transfer e.g. in the case of a resume procedure upon the transmission of an RRC Resume Complete (RRCResumeComplete) message.

[0100] Table 1 below, extracted from 3GPP R2-1707341, shows calculated latencies. The column with NR-1 shows the latency with the same Transmission Time Interval (TTI) length (1ms) and processing delay as LTE. The other columns assume different TTIs, and processing delay due to enhanced hardware capability. Considering on-going discussion and status in RAN1, 2 symbol TTI (1 / 7 ms assuming the same number of symbols as LTE in 1ms sub-frame) seems acceptable assumption for NR mini-slot. For processing delay, various options including the same delay as LTE, 50% less and 33% less processing delay can be considered for examples. Control plane latency (inactive) in the following table shows calculated latency assuming the 2nd definition, i.e. the transition time from inactive state to the time when the first uplink packet is transmitted. Control plane latency (full connection) shows conventional control plane latency for various PHY and process delay assumptions.

[0101] Table 1. Control plane latency and total latency for full connection resumption

[0102] Hence, under different assumptions, it would take from 10ms-30ms to start transmitting UL data in buffer if the UE is transitioning from RRC INACTIVE or RRC IDLE, at least theoretically. In a recent lab test, the CP latency, defined as the latency to transition from RRCJNACTIVE or RRCJDLE to RRC_CONNECTED, it has been verified that it takes about 30ms to transition from RRCJNACTIVE to RRC_CONNECTED, and 90ms to transition from RRCJDLE to RRC_CONNECTED, as shown in Figure 5. Figure 5 depicts the RRC setup time (the upper curve in Figure 5) vs. the RRC resume setup time (the lower curve in Figure 5) in ms.

[0103] These values are likely much higher in a live commercial network, due to other impairments not modeled in a lab setup such as retransmissions in different layers, e.g., random access preamble retransmissions, Radio Link Control (RLC) Packet Data Unit (PDUs), etc.

[0104] SUMMARY

[0105] As a part of developing embodiments herein a problem was identified by the inventors and will first be discussed.

[0106] As 5G Advanced and 6G are systems expected to have lower latency than 4G and 5G and, at the same time, RRC states for power savings wherein the UE spends as much time as possible when it is not transmitting / receiving data, it is important to reduce the control plane latency even further and make sure the UE only triggers the transition to RRC_CONNECTED when necessary. Traditionally, CP latency is a KPI which is proposed to be reduced in every new generation.

[0107] Concerning the usage of AI / ML in 3GPP systems: despite the fact that 3GPP RAN3 Release 17 is studying AI / ML, the use cases being considered do not assume Al / ML functions at the UE and / or predictions of data volume, and are limited to network energy savings, load balancing, mobility optimization. Also, it is noticed that most of the focus is on the RAN intelligence, i.e. , it is expected that the UE may support the RAN with data and perform actions triggered by the RAN based on AI / ML models in the RAN, but the UE itself would not perform predictions. In 5G advanced and 6G, AI / ML techniques are expected to play a larger role, possibly affecting the air interface protocols, including the UE procedures.

[0108] An object of embodiments herein is to improve the performance in a communications network.

[0109] According to an aspect of embodiments herein, the object is achieved by a method performed by a User Equipment, UE. The method is for initiating a procedure for transitioning the UE from a power saving mode of operation to a connected mode of operation in a wireless communications network. The UE performs one or more predictions of data volume in a protocol buffer. The data volume is predicted to be transmitted between the UE and a Radio Access Network, RAN, node in an upcoming data transmission. Before data of the upcoming data transmission arrives in the protocol buffer, the UE initiates the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer. The UE sends a request to the RAN node. The request is for the transitioning to the connected mode of operation.

[0110] According to an aspect of embodiments herein, the object is achieved by a method performed by a Radio Access Network, RAN, node for handling a User Equipment, UE, initiated procedure for transitioning the UE from a power saving mode of operation to a connected mode of operation in a wireless communications network.

[0111] Before data of an upcoming data transmission arrives in a protocol buffer of the UE, the RAN node receives a request from the UE. The request relates to a UE initiated procedure for transitioning to the connected mode of operation based on one or more predictions of the data volume in the protocol buffer. The data volume is predicted to be transmitted between the UE and the RAN node in the upcoming data transmission.

[0112] The RAN node decides whether or not to transitioning to connected mode of operation based on the received request. The RAN node sends a message to the UE. The message indicates the outcome of the deciding of whether or not to transitioning to connected mode of operation.

[0113] According to another aspect of embodiments herein, the object is achieved by a User Equipment, UE, configured to initiate a procedure for transitioning the UE from a power saving mode of operation to a connected mode of operation in a wireless communications network. The UE is further configured to:

[0114] - Perform one or more predictions of data volume in a protocol buffer, wherein the data volume is adapted to be predicted for being transmitted between the UE and a Radio Access Network, RAN, node in an upcoming data transmission,

[0115] - before data of the upcoming data transmission arrives in the protocol buffer, initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer, and,

[0116] - send to a RAN node , a request for the transitioning to the connected mode of operation.

[0117] According to another aspect of embodiments herein, the object is achieved by a Radio Access Network, RAN, node configured to handle a User Equipment, UE, initiated procedure for transitioning a UE from a power saving mode of operation to a connected mode of operation in a wireless communications network. The RAN node is further configured to:

[0118] - Before data of an upcoming data transmission arrives in a protocol buffer of the UE, receive a request from the UE , which request is adapted to relate to a UE initiated procedure for transitioning to the connected mode of operation based on one or more predictions of the data volume in the protocol buffer, wherein the data volume is adapted to be predicted for being transmitted between the UE and the RAN node in the upcoming data transmission,

[0119] - decide whether or not to transitioning to connected mode of operation based on the received request, and

[0120] - send to the UE , a message indicating the outcome of the deciding of whether or not to transitioning to connected mode of operation. An advantage of embodiments herein is that they enable a UE to transition to a connected mode of operation (e.g. RRC_CONNECTED) from a power saving mode of operation (e.g. RRCJDLE) with a CP latency of 0ms, at least as perceived at the UE. The reason is that the transition to RRC_CONNECTED is triggered before the UL and / or DL data arrives in the UE buffer, i.e. , the connectivity is prepared in advance. The prior art alternative to always reach the 0ms control plane latency as perceived by an end user would be to keep the UE in RRC_CONNECTED as much as possible, however, that would lead to a higher power consumption compared the case the stays longer in RRCJNACTIVE or RRC DLE.

[0121] Hence, as 5G Advanced and 6G are systems expected to have lower latency than 4G and 5G and, at the same time, RRC states for power savings wherein the UE spends as much time as possible when it is not transmitting / receiving data, embodiments herein provide reduced control plane latency and make sure the UE only triggers the transition to RRC_CONNECTED when necessary.

[0122] BRIEF DESCRIPTION OF THE DRAWINGS

[0123] Examples of embodiments herein are described in more detail with reference to attached drawings in which:

[0124] Figure 1 is a schematic block diagram illustrating prior art.

[0125] Figure 2 is a schematic sequence diagram illustrating prior art.

[0126] Figure 3 is a schematic sequence diagram illustrating prior art.

[0127] Figure 4 is a schematic diagram illustrating prior art.

[0128] Figure 5 is a schematic diagram illustrating prior art.

[0129] Figure 6 is a schematic block diagram illustrating embodiments of a communications network.

[0130] Figure 7 is a flowchart depicting an embodiment of a method in a UE.

[0131] Figure 8 is a flowchart depicting an embodiment of a method in a RAN node.

[0132] Figure 9 is a sequence diagram illustrating embodiments herein.

[0133] Figure 10 is a sequence diagram illustrating embodiments herein.

[0134] Figure 11 is a sequence diagram illustrating embodiments herein.

[0135] Figure 12 is a schematic diagram illustrating embodiments herein.

[0136] Figure 13 is a schematic diagram illustrating embodiments herein.

[0137] Figure 14 is a schematic diagram illustrating embodiments herein.

[0138] Figure 15 is a schematic block diagram illustrating embodiments herein. Figure 16 is a schematic block diagram illustrating embodiments herein.

[0139] Figure 17a-b are schematic block diagrams illustrating embodiments of a UE.

[0140] Figure 18a-b are schematic block diagrams illustrating embodiments of a RAN node,

[0141] Figure 19 schematically illustrates a telecommunication network connected via an intermediate network to a host computer.

[0142] Figure 20 is a generalized block diagram of a host computer communicating via a base station with a user equipment over a partially wireless connection,

[0143] Figures 21-24 are flowcharts illustrating methods implemented in a communication system including a host computer, a base station and a user equipment.

[0144] DETAILED DESCRIPTION

[0145] Embodiments herein e.g. relate to an early connection resume-setup based on predicted incoming data. Methods and apparatuses in a UE and a RAN node are provided.

[0146] According to example embodiments herein, the UE performs one or more predictions of incoming data volume in a protocol buffer. A protocol buffer when used herein e.g., means a protocol layer associated to the user plane data. The one or more predictions of the incoming data is to be transmitted and / or received by the UE. The UE being in a power saving mode of operation then initiates a procedure for transitioning to a connected mode of operation based on the one or more predictions of incoming data in the protocol buffer. A mode of operation may also be referred to as state. The wordings state and mode may be used interchangeably herein.

[0147] This triggers a resume or setup procedure based on the incoming data predictions. Since the resume or setup procedure is triggered based on predictions of incoming data before any data has arrived in the UE buffer, the air interface between the UE and a RAN node is already optimized for data transmission the moment the UE then is transitioned into connected mode of operation, which is before data transmission and / or reception is really needed and / or started. This will lead to a very low CP latency, e.g., a 0 millisecond CP latency, while allowing a fair amount of power savings. The UE may only initiate the request for the transition to the connected mode of operation when it knows it needs to, but before it is time.

[0148] An advantage of embodiments herein is that the UE can transition to a connected mode of operation from a power saving mode of operation with a CP latency of 0ms, at least as perceived by the end user such as the UE. The reason is that the transition to a connected mode of operation is triggered before the UL and / or DL data arrives in the UE buffer, i.e., the connectivity is prepared in advance. By using embodiments herein, there is no need to always reaching the 0ms CP latency as perceived by the end user by keeping the UEs in the connected mode. This is since the UE can predict when the UL / DL data is expected to arrive and thus the UE can be transitioned from the power saving mode to the connected mode based on such predictions. Thereby the disadvantage is overcome with keeping the UE in connected mode of operation as much as possible leading to a higher power consumption compared the case according to embodiments herein providing the UE to stay longer in a power saving mode of operation.

[0149] Hence, as 5G Advanced and 6G are systems expected to have lower latency than 4G and 5G and, at the same time, RRC states for power savings wherein the UE spends as much time as possible when it is not transmitting and / or receiving data, it is important to reduce the CP latency and make sure the UE only triggers the transition to connected mode of operation when necessary, which is provided by embodiments herein.

[0150] Figure 6 is a schematic overview depicting a wireless communications network 100 wherein embodiments herein may be implemented. The wireless communications network 100 comprises one or more RANs and one or more CNs. The wireless communications network 100 may use 5G NR, and 6G, but may further use a number of other different technologies, such as, Wi-Fi, (LTE), LTE-Advanced, Wideband Code Division Multiple Access (WCDMA), Global System for Mobile communications / enhanced Data rate for GSM Evolution (GSM / EDGE), or Ultra Mobile Broadband (UMB), just to mention a few possible implementations.

[0151] Network nodes such as a RAN node 110 operate in the wireless communications network 100, by means of antenna beams, referred to as beams herein. The RAN node 110 e.g. provides a number of cells and may use these cells for communicating with e.g. a UE 120. The RAN node 110 may be a transmission and reception point e.g. a radio access network node such as a base station, e.g. a radio base station such as a NodeB, an evolved Node B (eNB, eNodeB, eNode B), an NR Node B (gNB), a base transceiver station, a radio remote unit, an Access Point Base Station, a base station router, a transmission arrangement of a radio base station, a stand-alone access point, a Wireless Local Area Network (WLAN) access point, an Access Point Station (AP STA), an access controller, a UE acting as an access point or a peer in a Device to Device (D2D) communication, or any other network unit capable of communicating with a UE served by the RAN node 110 depending e.g. on the radio access technology and terminology used.

[0152] User Equipments operate in the wireless communications network 100, such as a UE 120. The UE 120 may respectively provide radio coverage by means of a number of antenna beams, also referred to as beams herein. The UE 120 may e.g. be an NR device, a mobile station, a wireless terminal, an NB-loT device, an eMTC device, an NR RedCap device, a CAT-M device, a Wi-Fi device, an LTE device and a non-access point (non-AP) STA, a STA, that communicates via a base station such as e.g. the RAN node 110, one or more Access Networks (AN), e.g. RAN, to one or more core networks (CN). The UE 120 may further be a Vehicle to Everything (V2X) device such as e.g. any one out of a Vehicle-to-Vehicle (V2V) device or Vehicle-to-lnfrastructure (V2I) device. It should be understood by the skilled in the art that the UE relates to a non-limiting term which means any UE, terminal, wireless communication terminal, user equipment, (D2D) terminal, or node e.g. smart phone, laptop, mobile phone, sensor, relay, mobile tablets or even a small base station communicating within a cell.

[0153] The UE 120 may e.g. correspond to a UE operating in a Next-Generation (NG)- RAN, a 6G RAN or a 6G network.

[0154] Methods herein may in one aspect be performed by the UE 120, and in another aspect by the RAN node 110. As an alternative, a Distributed Node (DN) and functionality, e.g. comprised in a cloud 135 as shown in Figure 6, may be used for performing or partly performing the methods of embodiments herein.

[0155] A number of embodiments will now be described, some of which may be seen as alternatives, while some may be used in combination.

[0156] Figure 7 shows example embodiments of a method performed by the UE 120. The method is for initiating a procedure for transitioning the UE 120 from a power saving mode of operation to a connected mode of operation in the wireless communications network 100.

[0157] The method comprises the following actions, which actions may be taken in any suitable order. Optional actions are referred to as dashed boxes in Figure 7. Action 701

[0158] In some embodiments, the UE 120 obtains one or more configurations for controlling the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0159] The one or more configurations may comprise one or more parameters related to any one or more out of:

[0160] - the performing of the one or more predictions of the data volume in the protocol buffer,

[0161] - the initiating of the procedure for transitioning to the connected mode of operation.

[0162] - one or more location information where to perform the one or more predictions of data volume in the protocol buffer,

[0163] - one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,

[0164] - one or more location information where the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,

[0165] - a value for a first timer, indicating for how long time the UE 120 shall perform the one or more predictions of data volume in the protocol buffer,

[0166] - a value for a second timer, indicating for how long time the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation,

[0167] - a value for a third timer, indicating for how long time the UE 120 is not required to perform the one or more predictions of the data volume in the protocol buffer, or for how long time the UE 120 shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,

[0168] - one or more indications of one or more bearers the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0169] - one or more indications of one or more Over The Top, OTT, services the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer,

[0170] - one or more indications of one or more applications the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0171] - one or more parameters associated to the data volume to be predicted.

[0172] Action 702

[0173] In some embodiments, the UE 120 obtains a model for the one or more predictions. The model may be obtained by any one out of: - Training the model in the UE 120, or

[0174] - receiving the model from a RAN node 110.

[0175] Action 703

[0176] The UE 120 is in a power saving mode of operation. The UE 120 performs one or more predictions of data volume in a protocol buffer. The data volume is predicted to be transmitted between the UE 120 and the RAN node 110 in an upcoming data transmission. The performing of the one or more predictions may be triggered by an explicit network configuration associated to configuring the UE 120 to perform the prediction or by an implementation at the UE 120 which may initiate the initiation of the prediction on its own.

[0177] The results of the one or more predictions may indicate that there is a large data volume expected in the protocol buffer and that there is need for transitioning the UE 120 to connected mode of operation, making it possible for the UE 120 to start a data transmission and / or reception for the predicted data volume.

[0178] In some embodiments, the performing of the one or more predictions of data volume in the protocol buffer is based on the model.

[0179] Action 704

[0180] Before data of the upcoming data transmission arrives in the protocol buffer, the UE 120 initiates the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer.

[0181] It is an advantage to initiate the procedure for transitioning to the connected mode of operation before data of the upcoming data transmission arrives in the protocol buffet according to embodiments herein. This is since, when the connectivity is prepared in advance, which is possible because of the predictions, the perceived latency of transmitting the data would be 0ms as all the control plane related messages have already been exchanged between the UE 120 and the network node 110 and the data transmission and / or reception may begin when the data starts to arrive.

[0182] The UE 120 may decide whether or not to initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer. E.g., when data is expected to arrive in the protocol buffer within a time interval, the UE 120 may decide to initiate the procedure for transitioning, and when no data is expected to arrive in the protocol buffer within a time interval the UE 120 may decide to not initiate the procedure for transitioning. In some embodiments, the initiating of the procedure for transitioning to the connected mode of operation may comprise to set a cause value to be included in a request message. The cause value indicates that the UE 120 initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer.

[0183] Action 705

[0184] The UE 120 sends a request to the RAN node 110. The request is for the transitioning to the connected mode of operation. The sending of the request may be comprised in, e.g.be a part of, the initiation of the procedure for transitioning to the connected mode of operation.

[0185] The request for the transitioning to the connected mode of operation, may further indicate that the UE 120 has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer. The indication, indicate that the UE 120 has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer, may be referred to as a cause value.

[0186] Action 706

[0187] In some embodiments, the UE 120 sends a message, e.g. complete message, to the RAN node 110. The message may indicate any one or more out of:

[0188] - data based on or related to the one or more predictions of the data volume in the protocol buffer,

[0189] - data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,

[0190] - data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected, and

[0191] - data associated to any error of the one or more predictions of data volume in the protocol buffer.

[0192] Action 707

[0193] The UE 120 may then start to communicate the data related to the one or more predictions of the data volume in the protocol buffer.

[0194] Action 708 In some embodiments, at the starting the communication of data related to the one or more predictions of the data volume in the protocol buffer, the UE 120 starts an inactivity timer. When the inactivity timer expires, a transitioning of the UE 120 from a connected mode of operation to a power saving mode of operation is initiated.

[0195] Figure 8 shows example embodiments of a method performed by the RAN node 110. The method is for handling a UE initiated procedure for transitioning the UE 120 from a power saving mode of operation to a connected mode of operation in the wireless communications network 100.

[0196] The method comprises the following actions, which actions may be taken in any suitable order. Optional actions are referred to as dashed boxes in Figure 8.

[0197] Action 801

[0198] In some embodiments, the RAN node 110 sends one or more configurations to the UE 120. The one or more configurations configures the UE 120 to:

[0199] - perform one or more predictions of data volume in a protocol buffer, wherein the data volume is to be predicted to be transmitted between the UE 120 and a Radio Access Network, RAN, node 110 in an upcoming data transmission, and

[0200] - before data of the upcoming data transmission arrives in the protocol buffer, initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer.

[0201] The one or more configurations may further configure the UE 120 to:

[0202] - at starting the data communication related to the one or more predictions of the data volume in the protocol buffer, start an inactivity timer, which when expires initiates a transitioning of the UE 120 from a connected mode of operation to a power saving mode of operation.

[0203] The one or more configurations may further configure the UE 120 to perform the one or more predictions of data volume in the protocol buffer based on a model.

[0204] In some embodiments, the one or more configurations comprise one or more parameters related to any one or more out of:

[0205] - The performing of the one or more predictions of the data volume in the protocol buffer,

[0206] - the initiating of the procedure for transitioning to the connected mode of operation. - one or more location information where to perform the one or more predictions of data volume in the protocol buffer,

[0207] - one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,

[0208] - one or more location information where the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,

[0209] - a value for a first timer, indicating for how long time the UE 120 shall perform the one or more predictions of data volume in the protocol buffer,

[0210] - a value for a second timer, indicating for how long time the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation,

[0211] - a value for a third timer, indicating for how long time the UE 120 is not required to perform the one or more predictions of the data volume in the protocol buffer, or for how long time the UE 120 shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,

[0212] - one or more indications of one or more bearers the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0213] - one or more indications of one or more Over The Top, OTT, services the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer,

[0214] - one or more indications of one or more applications the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0215] - one or more parameters associated to the data volume to be predicted.

[0216] Action 802

[0217] In some embodiments, the RAN node 110 sends the model to the UE 120. The model is for the one or more predictions.

[0218] Action 803

[0219] Before data of an upcoming data transmission arrives in a protocol buffer of the UE 120, the RAN node 110 receives a request from the UE 120. The request relates to a UE initiated procedure for transitioning to the connected mode of operation based on one or more predictions of the data volume in the protocol buffer. The data volume is predicted to be transmitted between the UE 120 and the RAN node 110 in the upcoming data transmission. The request for the transitioning to the connected mode of operation, may further indicate that the UE 120 has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer. The indication may be referred to as a cause value.

[0220] Action 804

[0221] The RAN node 110 decides whether or not to transitioning to connected mode of operation based on the received request.

[0222] The deciding of whether or not to transitioning the UE 120 to connected mode of operation based on the received request, may further be based on the indication that the UE 120 has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer.

[0223] Action 805

[0224] The RAN node 110 sends a message to the UE 120. The message indicates the outcome of the deciding of whether or not to transitioning to connected mode of operation.

[0225] Action 806

[0226] The RAN node 110 may further receive a message, e.g., complete message, from the UE 120. The message e.g., indicates any one or more out of:

[0227] - Data based on or related to the one or more predictions of the data volume in the protocol buffer,

[0228] - data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,

[0229] - data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected, and

[0230] - data associated to any error of the one or more predictions of data volume in the protocol buffer.

[0231] The above embodiments will now be further explained and exemplified below. The embodiments below may be combined with any suitable embodiment above.

[0232] RRC resume procedure Figure 9 depicts an example scenario relating to the procedure for transitioning to the connected mode of operation when being represented by an RRC resume procedure as initiated by the prediction of data volume in buffer, according to some embodiments herein.

[0233] The UE 120 performs 901 prediction of data volume. The UE 120 then initiates 902 a resume procedure, triggered by the prediction of data volume. The UE 120 transmits 903 an RRC resume Request message to the RAN node 110. The RAN node 110 responds 904 in an RRC Resume message. The UE 120 transmits 905 a Resume Complete message to the RAN node 110. The UE 120 is then ready 906 for continuous data DL transmissions 907 and UL receptions 908 to and from the RAN node 110.

[0234] RRC establishment procedure

[0235] Figure 10 depicts a scenario relating to the procedure for transitioning to the connected mode of operation when being represented by an RRC establishment procedure initiated by the prediction of data volume in buffer, according to some embodiments herein.

[0236] The UE 120 performs 1001 prediction of data volume. The UE 120 then initiates 1002 an RRC establishment procedure, triggered by the prediction of data volume.

[0237] The UE 120 transmits 1003 an RRC Setup Request message to the RAN node 110. The RAN node 110 responds 1004 with an RRC Setup message.

[0238] The UE 120 transmits 1005 an RRC Setup Complete message to the RAN node 110.

[0239] The RAN node 110 transmits 1006 a Security Mode Command to the UE 120. The UE 120 responds 1007 with a Security Mode Complete.

[0240] The RAN node 110 transmits 1008 a RRC Reconfiguration message to the UE 120. The UE 120 then transmits 1009 a RRC Reconfiguration Complete message to the RAN node 110.

[0241] The UE 120 is now ready 910 for continuous DL data transmissions 911 and UL data receptions 912 to and from the RAN node 110.

[0242] Disclaimer: Some embodiments herein describe the transition to a connected mode of operation or an attempt to transition to a connected mode of operation, or connected state, which triggers the UE 120 to transmit a request message to the network such as the RAN node 110. At the network side, the RAN node 110 may respond with an RRC Reject message (RRCReject) or an RRC release message, which leads the UE 120 to not enter connected mode of operation. This is still interpreted as an attempt to enter connected mode of operation e.g., RRC_CONNECTED, herein, as the UE 120 initiated the RRC establishment or RRC resume procedure intending to enter the connected mode of operation. In any of these cases above, higher protocol layers of the UE 120, e.g. Non- Access Stratum (NAS) protocol layer, may trigger the transition to connected mode of operation such as the RRC_CONNECTED mode, due to the presence of upcoming data originated in the UE 120, often called mobile originated attempt. In the higher layers, such as in NAS, the UE 120 when in RRCJDLE mode would first need to establish an RRC Connection before transmitting data. Hence, from a NAS perspective, upcoming data in the UL that needs to be transmitted may trigger the NAS to request RRC, also called Access Stratum (AS), to initiate a connection establishment. However, from a NAS / AS modeling perspective, that may require an initial NAS message to be transmitted in the RRCSetupComplete message, at least partially, so that the model may consider the initial NAS message as the trigger to initiate the establishment procedure, wherein the initial NAS message may have been triggered by incoming UL data in the buffer of the UE 120.

[0243] The following definitions may be considered for the following:

[0244] - Data collection: Data collected from network nodes such as the RAN node 110, management entity or UE such as the UE 120, as a basis for ML model training, data analytics and inference.

[0245] - ML Model: A data driven algorithm by applying machine learning techniques that generates a set of outputs, comprising predicted information, such as e.g. the one or more predictions of data volume in a protocol buffer, based on a set of inputs.

[0246] - ML Training: An online or offline process to train an ML model by learning features and patterns that best present data and get the trained ML model for inference.

[0247] - ML Inference: A process of using a trained ML model to make a prediction or guide the decision based on collected data and ML model.

[0248] Examples of the method according to embodiments herein will now be described. They relate to and may be combined with the embodiments in the Actions described above.

[0249] Some embodiments of the method for initiating a transition from a power saving mode of operation to a connected mode of operation is illustrated in Figure 11. The method may comprise: In some embodiments, the UE 120 receives 1101 one or more configurations relating to the one or more predictions of data volume in the protocol buffer. This relates to and may be combined with Actions 701 and 801 described above

[0250] The RAN node 100 releases 1102 the UE 120 and the UE 120 is transitioned from a connected mode of operation into power saving mode of operation.

[0251] The UE 120 performs 1103 one or more predictions of a data volume in a protocol buffer according to the received one or configurations. The data volume is to be transmitted and / or received by the UE 120, to and / or from the RAN node 110. This relates to and may be combined with Action 703 described above.

[0252] The UE 120 identifies 1104 the need to perform transitioning to RRC CONNECTED based on outcome of prediction. If identified to be needed, the UE 120 initiates a procedure for transitioning to the connected mode of operation based on the one or more predictions of incoming data in the protocol buffer according to the received one or configurations. This relates to and may be combined with Action 704 described above.

[0253] The UE 120 transmits 1105 an RRC Resume / RRC Setup request to the RAN node 110. The request may comprise an indication, indicating that the UE 120 has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer. The indication may be referred to as a cause value. This relates to and may be combined with Actions 705 and 803 described above.

[0254] The RAN node 110 decides 1106 to transition the UE 120 is transitioned from power saving mode of operation to a connected mode of operation, e.g. based on the cause value in the request. This relates to and may be combined with the Action 804 described above.

[0255] The RAN node 110 transmits 1107 an RRC Resume / RRC Setup message to the UE 120. The message may indicate the outcome of the deciding of whether or not to transitioning to connected mode of operation. This relates to and may be combined with the Action 805 described above.

[0256] The UE 120 then transmits 1108 an RRC Resume / RRC Setup Complete to the RAN node 110. The RRC Resume / RRC Setup Complete message may comprise further indications of the outcome of the prediction. This relates to and may be combined with Actions 706 and 806 described above. In some embodiments the predictions of data volume are performed at an Inference Model, also referred to as model, function located at the UE 120, wherein the “Inference Model” e.g. may be defined in 3GPP Release 17 (v17.0.0) TR 37.817. This relates to and may be combined with the Actions 702 and 703 described above.

[0257] Some of the following embodiments comprise UE 120 actions, RAN node 110 actions, and actions that may be performed by both the UE 120 and the RAN node 110.

[0258] The procedure for transitioning to the connected mode of operation is performed by the UE 120 while the UE 120 is in a power saving mode of operation. The power saving mode of operation may be one or more of i) an RRCJDLE state; ii) an RRC NACTIVE state; iii) an RRC_DEACTIVATED state. Other examples of power saving mode of operation are not precluded and may include an RRC state, or a state defined in any protocol stack e.g. in the Access Stratum, wherein the procedures and / or operations of the UE 120 when it operates in that state are optimized for power savings.

[0259] In one option, that procedure may be triggered at an Actor function of the model, e.g., according to the model in 3GPP Release 17 (v17.0.0) TR 37.817 entitled “Study on enhancement for Data Collection for NR and EN-DC”.

[0260] Examples of operations and / or procedures in different modes of operation.

[0261] Examples of the operations and / or procedures performed by the UE 120 in a power saving mode of operation are for example RRCJDLE procedures such as e.g., Public Land Mobile Network (PLMN) selection by the UE 120, Broadcast of system information by the RAN node 110, and acquisition of system information by the UE 120, Cell reselection mobility by the UE 120; Paging for mobile terminated data is initiated by 5GC and monitored by the UE 120, Discontinuous Reception (DRX) for CN paging configured by NAS, the UE 120 may operate in such DRX mode; A UE 120 specific DRX may be configured by upper layers; UE 120 controlled mobility based on network configuration; Monitoring of Short Messages transmitted with Paging - Radio Network Temporary Identifier (P-RNTI) over Downlink Control Information (DCI), (see clause 6.5 in 3GPP Release 16 (v16.7.0) TS 38.331); Monitoring a Paging channel for CN paging using 5G- System architecture evolution - Temporary Mobile Subscriber Identity (S-TMSI), Performing neighbouring cell measurements and cell (re-)selection, acquisition of system information and possibly transmission of System Information requests (if configured). Examples of the operations and / or procedures performed in a power saving mode of operation are for example RRC_IN ACTIVE procedures such as: PLMN selection by the UE 120; Broadcast of system information by the network node; Cell re-selection mobility by the UE 120; Paging is initiated by NG-RAN (RAN paging) and may be monitored by the UE 120; RAN-based notification area (RNA) is managed by NG- RAN and the UE 120 may perform RNA updates due to mobility and periodically; DRX for RAN paging configured by NG-RAN; 5GC - NG-RAN connection, both Control (C) and / or User (U)-planes, may be established for the UE 120; The UE 120 AS context is stored in NG- RAN and the UE 120; NG-RAN knows the RNA which the UE 120 belongs to; A UE specific DRX may be configured by upper layers or by RRC layer; UE controlled mobility based on network configuration; The UE 120 stores the UE 120 Inactive AS context; A RAN-based notification area is configured by RRC layer; Monitoring of Short Messages transmitted with Paging (P)-RNTI over DCI (see clause 6.5); Monitoring of a Paging channel for CN paging using 5G-S-TMSI and RAN paging using full l-RNTI; Performing neighbouring cell measurements and cell (re-)selection; Performing RAN-based notification area updates periodically and when moving outside the configured RAN-based notification area; Acquisition by the UE 120 and transmission by the network node, e.g. the RAN node 110, of system information, the UE 120 may also transmit a system information request if configured.

[0262] The connected mode of operation e.g. of the UE 120 and / or of the RAN node 110, may correspond to a RRC connected state. The RRC connected state may correspond to the RRC_CONNECTED state as defined in 3GPP Release 16 (v16.7.0) TS 38.331. Examples of operations and / or procedures performed in a connected mode of operation are for example RRC_CONNECTED procedures such as: 5GC - NG-RAN connection, both C / U-planes, is established for the UE 120; The UE 120 Access Stratum (AS) context may be stored in NG-RAN and the UE 120; NG-RAN knows the cell which the UE 120 belongs to; Transfer of unicast data to / from the UE 120; Network controlled mobility including measurements; The UE 120 stores the AS context; Transfer of unicast data to and / or from the UE 120; At lower layers, the UE 120 may be configured with a UE specific DRX; For UEs such as e.g. some embodiments of the UE 120, supporting Carrier Aggregation (CA) using one or more Secondary Cells (SCells) aggregated with a Primary Secondary cell group cell (PSCell) for increased bandwidth; For UEs, such as e.g. some embodiments of the UE 120, supporting DC using one Secondary Cell Group (SCG) aggregated with a Master Cell Group (MCG) for increased bandwidth; Network controlled mobility within NR and to / from E-UTRA; The UE 120 may: i) Monitor Short Messages transmitted with P-RNTI over DCI (see clause 6.5 in 3GPP Release 16 (v16.7.0) TS 38.331), if configured. ii) Monitor control channels associated with the shared data channel to determine if data is scheduled for it. iii) Provide channel quality and feedback information, iv) Perform neighbouring cell measurements, and measurement.

[0263] The initiating of the transitioning procedure

[0264] This is related to and may be combined with Action 704 described above.

[0265] In some embodiments, the UE 120 initiates the transitioning to the connected mode of operation is a procedure in the RRC protocol at the UE 120. In other embodiment the procedure is in a control plane protocol of the Access Stratum.

[0266] In some embodiments, the initiation of the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer is triggered by one or more higher layers of the protocol stack at the UE 120.

[0267] - In some embodiments, the protocol which triggers the initiation of the procedure for transitioning to the connected mode of operation, i.e. the protocol which performs the prediction of data volume, is the NAS protocol.

[0268] - In some other embodiments, the protocol which triggers the initiation, i.e. the protocol which performs the prediction of data volume, is any protocol which is above the AS protocol, e.g. RRC. The RRC protocol is responsible for initiating the transition to the connected mode of operation e.g. RRC_CONNECTED.

[0269] - In a set of embodiments, the initiation of the procedure for transitioning to the connected mode of operation, i.e. the protocol which performs the prediction of data volume, is triggered by an Over the Top (OTT) client application, such as a client in a Smartphone. In this set of embodiments, the OTT client application, such as a YouTube client, Meta client, Facebook client, Google client, Amazon client, predicts data volume in the buffer. This may e.g. be in the UL, to be transmitted within X seconds. Based on the predicts data volume in the buffer, the OTT client application triggers the UE 120 to initiate the transition to connected mode of operation. In one embodiment, the OTT client generates a first packet which is for that purpose, even though that packet is not necessarily user plane data generated by the OTT client for the sake of the application itself. For a UE 120 module, i.e., for a AS / NAS protocol stack, the prediction may be transparent in this case, as the generated packet(s) is not known to be this sort of wake-up packet generated by the OTT client. The embodiments associated to OTT client application performing the prediction of data volume potentially enable an OTT client application specific optimization of the predictor which may have a better accuracy compared to a predictor that is performing prediction across multiple applications in the AS or NAS layer.

[0270] In some embodiments the UE 120 initiates transitioning to a connected mode of operation by initiating an RRC Setup procedure. See Figure 10 described above. The RRC Setup procedure comprises the state transition at the UE 120 from RRCJDLE to RRC_CONNECTED. In one embodiment, the procedure which is initiated is the RRC connection establishment procedure as defined in § 5.3.3 of 3GPP Release 16 (v16.7.0) TS 38.331. According to further embodiments, further steps of the RRC connection establishment (or setup) after its initiation may be modified in case the procedure is triggered by the prediction of data volume. In one option, that procedure is triggered at the “Actor” function according to the model in the 3GPP Release 16 (v16.7.0) TR 37.817 entitled “Study on enhancement for Data Collection for NR and EN-DC”.

[0271] In some embodiments the UE 120 initiates transitioning to a connected mode of operation by initiating an RRC Resume procedure. See Figure 9 described above. The RRC Resume procedure may comprise a state transition at the UE 120 from RRCJNACTIVE to RRC_CONNECTED. In one embodiment, the procedure which is initiated is the RRC connection resume procedure as defined in § 5.3.13 of 3GPP Release 16 (v16.7.0) TS 38.331. According to further embodiments, the further steps of the RRC connection resume, after its initiation may be modified in case the procedure is triggered by the prediction of data volume. In one option, that procedure is triggered at the “Actor” function according to the model in 3GPP Release 17 (v17.0.0) TR 37.817 entitled “Study on enhancement for Data Collection for NR and EN-DC”.

[0272] Obtaining the one or more configurations

[0273] This is related to and may be combined with Action 701 and Action 801 described above. In some embodiments the UE 120 obtains one or more configurations from the network such, for controlling the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0274] - In one set of embodiments, the one or more configurations may be obtained by the UE 120 from the network e.g. from the gNodeB, eNodeB, another NG-RAN node 110, or a network node from a 6G RAN, a network element from a 6G RAN, or any element of a 6G network. The one or more configurations may be obtained by the UE 120 according to any one out of: o By acquiring one or more broadcasted messages from the network e.g. while the UE 120 is in RRCJDLE, RRCJNACTIVE and / or upon performing cell selection and cell re-selection. o By acquiring one or more dedicated messages from the network e.g. while the UE 120 is in RRC_CONNECTED. o By acquiring a system information message from the network, e.g. via broadcast or on demand system information. In this embodiment the configuration may be within a System Information Block (SIB) message and / or one or more fields / Information elements (IEs) / parameters within. The UE 120 may acquires the one or more configurations when it acquires that SIB, e.g., while it is in the power saving mode of operation. o By receiving a message from the network, such as the RAN node 110, while it is in the connected mode of operation, e.g. RRC_CONNECTED. The configuration may be within an RRC Reconfiguration message and / or one or more fields / Information elements (IEs) / parameters. o By receiving a message from the network such as the RAN node 110, indicating that the UE 120 is to transition to a power saving mode of operation. The configuration may be within an RRC Release message and / or one or more fields / Information elements (IEs) / parameters. The RRC Release message may include a suspend configuration, e.g. suspendConfig as defined in 3GPP Release 16 (v16.7.0) TS 38.331 , indicating the transition to RRCJNACTIVE, or the RRC Release message may omit a suspend configuration, indicating the transition to RRCJDLE. o By the UE 120 in its internal memory.

[0275] - In some embodiments, the one or more configurations comprises configuration(s) of one or more prediction models. A prediction model may correspond to a logical function which may be implemented in Software and / or Hardware. Further details about prediction models will be described below. The prediction model may implement an ML and / or Al function which receives one or more feature data input(s) and provides an output. The one or more configurations may comprise:

[0276] One or more input parameters, or one or more indications of input parameters, which the UE 120 shall use as input to the one or more prediction mode, wherein the output will be one or more predictions of data volume of incoming data in the protocol buffer.

[0277] - In some embodiments, the one or more configurations comprises configuration(s) of one or more performance related information related to the prediction function(s) and / or inference model, such as the prediction accuracy or a prediction error wherein that indicates the UE 120 only initiates the transition to connected mode of operation if the performance is better than the configured performance related information. For example, the prediction accuracy may correspond to the accuracy of the prediction as derived by the prediction model and / or inference model. It should be noted that the wordings prediction model, inference model, prediction function, inference function, prediction model function, inference model function and AI-ML model may be used interchangeably herein. An example of such a configuration would be 0.9 wherein the configuration indicates that the UE 120 initiates the transition from the power saving mode to connected mode if the AI-ML model at the UE 120 predicts the arrival of data in the buffer with a certainty equal to or above 0.9, with 90% confidence. A similar reasoning may be used in the case the performance information is a prediction error, so the UE 120 would only initiate resume based on the predictions of data volume if the prediction error is below a certain configured value.

[0278] - In some embodiments, a combination of the above-mentioned aspects is configured. For example, a configuration may be a list of tuple values wherein the tuple comprises a prediction accuracy and a data volume threshold. In such an example, the UE 120 would evaluate the outcome of the prediction model against each element of the list and if one such tuple combination satisfies the triggering condition then the UE 120 initiates the transition from the power saving mode.

[0279] -In one set of embodiments, it is described examples of which entity at the UE 120 that is configured. o In one embodiment, the configuration is for the “Model Inference” function, as defined in the 3GPP Release 17 (v17.0.0) TR 37.817. o In one embodiment, the configuration is for the “Model Training” function, as defined in the 3GPP Release 17 (v17.0.0) TR 37.817. o In one embodiment, the configuration is for the “Actor” function, as defined in the (TR) 37.817. o In one embodiment, the configuration is for the “Data Collection” function, as defined in the 3GPP Release 17 (v17.0.0) TR 37.817.

[0280] Parameters comprising location information

[0281] The one or more configurations obtained by the UE 120 may comprise one or more parameters indicating what actions the UE 120 may perform based on the one of more configurations for controlling the procedure for transitioning to the connected mode. In some embodiments, the one or more parameters comprise one or more location information. The one or more location information may indicate where the UE 120 shall performs one or more predictions of data volume in the protocol buffer. The one or more location information may further indicate where the UE 120 is allowed to trigger the initiation of the transition to a connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0282] - In one example, the location information may correspond to one or more identifiers associated to one or more configured cells e.g., cell ID, global cell ID, physical cell ID, physical cell ID + frequency information, etc. Upon transitioning to a power saving mode of operations, e.g. RRCJDLE or RRCJNACTIVE, the UE 120 may perform cell selection and perform measurements for evaluating whether it shall perform cell reselection. Upon cell selection and cell reselection, the UE 120 possibly obtains system information and verifies if the selected and / or re-selected cell is one of the configured cells. If it is, the UE 120 performs the one or more predictions of data volume in the protocol buffer and / or is allowed to initiate the to trigger the initiation of a transition to a connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0283] - In one example, the location information may correspond to one or more CN identifiers, such as CN identifiers associated to one or more Tracking Areas e.g. Tracking Areas Code (TAC), Tracking Areas Identifier(s) (TAI). Upon each cell reselection the UE 120 may verifie if it is entering a cell associated to its configured Registration Area (set of TAIs) and if it is not the UE 120 shall perform a mobility triggered Registration Area Update. In this example, upon cell selection and cell reselection, the UE 120 obtains system information and verifies if it is still in its configured Registration Area. If it is, the UE 120 performs the one or more predictions of data volume in the protocol buffer and / or is allowed to initiate the to trigger the initiation of a transition to a connected mode of operation based on one or more predictions of data volume in the protocol buffer. This may occur while the UE 120 is in RRCJNACTIVE or RRCJDLE, but while it is in other state is not precluded.

[0284] - In one example, the location information may correspond to one or more RAN identifiers, such as a RAN Notification Area Identifier e.g. RAN area ID, wherein the RAN area ID may consist of a TAC and optionally a RAN area Code (RANAC). Upon each cell reselection the UE 120 verifies if it is entering a cell associated to its configured RAN Notification Area and if it is not the UE 120 shall perform a mobility triggered RAN Area Update (RNAU). In this example, upon cell selection and cell reselection, the UE 120 obtains system information and verifies if it is still in its configured RAN Area. If it is, the UE 120 performs the one or more predictions of data volume in the protocol buffer and / or is allowed to initiate the to trigger the initiation of a transition to a connected mode of operation based on one or more predictions of data volume in the protocol buffer. This may occur while the UE 120 is in RRCJNACTIVE, but while it is in other state is not precluded.

[0285] - In one example, the location information may correspond to one or more Prediction Area identifiers, such as a PAI, which the UE 120 could obtain via system information acquisition transmitted by the network. In this example, upon cell selection and cell reselection, the UE 120 obtains system information and verifies if it is still in its configured PAI. If it is, the UE 120 performs the one or more predictions of data volume in the protocol buffer and / or is allowed to initiate the to trigger the initiation of a transition to a connected mode of operation based on one or more predictions of data volume in the protocol buffer. This may occur while the UE 120 is in RRCJNACTIVE or RRCJDLE, but while it is in other state is not precluded. - In one embodiment, the one or more parameters comprise one or more ‘location information’ where the UE 120 shall NOT perform one or more predictions of data volume in the protocol buffer; and / or the one or more parameters comprise one or more ‘location information’ where the UE 120 is allowed to trigger the initiation of a transition to a connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0286] - One example is when the UE 120 is transitioned to RRCJNACTIVE and selected and / or re-selects to one cell of the same gNodeB, or any other RAN node, e.g., the RAN node 110, of the cell which was a PCell when the was connected, i.e. the PCell from which the UE 120 has received the command, e.g. RRCRelease with suspend configuration, to transition to RRCJNACTIVE. In this example, the UE 120 AS Inactive context may be stored in that gNodeB which may be referred as the last serving node, e.g. the RAN node 110. In this way a resume operation there would be faster as it would not require context fetching towards a different gNodeB. Hence, as the resume triggered by the prediction of data volume in the protocol buffer aims to reduce the control plane latency, it may be skipped in scenarios where the control plane latency is known to be reduced by the fact that context fetching would not be required. Hence, the UE 120 may start to perform predictions of data volume and / or considering a selected or re-selected cell allowed for initiating the transition to connected based on the predictions when it leaves the configured location.

[0287] - In one example, the location area may correspond to one or more RAN Area I D(s), one or more cell identities, one or more TAIs, one or more TACs, one or more PLMNs, etc.

[0288] Parameters relating to timers

[0289] In some embodiments, the one or more parameters comprise a value for a first timer, wherein the timer indicates for how long the UE 120 performs predictions.

[0290] - The UE 120 may starts the first timer upon an event, e.g. the triggering of an event and / or the fulfillment of a condition. The event may be one or more out of: i) A reception of a message for transitioning the UE 120 to a power saving mode of operation, e.g. RRCJDLE or RRCJNACTIVE, such as an RRC Release message. ii) A cell reselection or cell selection, e.g. to one or the configured cells for performing predictions of data volume. iii) A starting of the UE 120 performing one or more predictions of data volume in the protocol buffer. iv) Upon entering the power saving mode of operation, e.g. RRCJDLE or RRCJNACTIVE. iv) A change in the system information associated to the prediction related configuration as broadcasted by the camped cell while being in power saving mode, e.g., a flag indicating when the prediction should be restarted.

[0291] - The UE 120 may perform one or more of the following actions when the first timer expires: i) Release, e.g. delete or discard, one or more of the one or more parameters; ii) Release, e.g. delete or discard, the one or more predictions of data volume in the protocol buffer, if available. iii) Stop performing the one or more predictions of data volume in the protocol buffer.

[0292] - The UE 120 may stop the first timer upon an event, wherein the event may be one or more of: i) A reception of a message for transitioning the UE 120 to a connected mode of operation from a power saving mode of operation (e.g. transition from RRCJDLE or RRCJNACTIVE to RRC_CONNECTED), such as an RRC Resume or RRC Setup message. ii) A transmission of a request message, e.g. RRC Resume Request or RRC Setup Request. iii) Stopping to perform predictions due to the occurrent of another event, e.g. cell reselection or cell selection to a cell the UE 120 is not configured to perform the predictions. iv) Detection of incoming data in a buffer, e.g. real data at time to, not prediction. v) Detection of change in the battery status at the UE 120, i.e. , upon battery level going below a threshold. vi) Upon the predicted value meeting a certain criterion, e.g., predicted volume for the next ‘X’ seconds being zero.

[0293] - One of the benefits is that such a first timer may be introduced to prevent the UE 120 to continuously perform predictions of data volume for too long, which may consume additional power and / or energy of the UE 120 and / or unnecessarily trigger the transition to connected mode, especially after a long time it has been in RRCJNACTIVE or RRCJDLE. This may be interesting if it is known that packets sensitive to control plane latency come quite soon after a previous burst, i.e. soon after the UE 120 has been transitioned to a power saving mode of operation, but not after some longer amount of time.

[0294] In some embodiments, the one or more parameters comprise a value for a second timer. The second timer indicates for how long the UE 120 is allowed to trigger the initiation of a transition to a connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0295] - The UE 120 may start the second timer upon an event, wherein the event may be one or more of: i) A reception of a message for transitioning the UE 120 to a power saving mode of operation, e.g. RRCJDLE or RRCJNACTIVE, such as an RRC Release message. ii) A cell reselection or cell selection, e.g. for one of the configured cells for performing data volume predictions. iii) The starting by the UE 120 to perform one or more predictions of data volume in the protocol buffer. iv) Entering into the power saving mode of operation, e.g. RRCJDLE or RRCJNACTIVE. v) A change in the system information associated to the prediction related configuration as broadcasted by the camped cell while being in power saving mode, e.g., a flag indicating when the prediction should be restarted.

[0296] - The UE 120 may perform one or more of the following actions when the second timer expires: i) Release, e.g. delete or discard, one or more of the one or more parameters; ii) Release e.g. delete or discard, the one or more predictions of data volume in the protocol buffer, if available. iii) Stop performing the one or more predictions of data volume in the protocol buffer.

[0297] - The UE 120 may stop the second timer upon an event, wherein the event is one or more of: i) A reception of a message for transitioning the UE 120 to a connected mode of operation from a power saving mode of operation, e.g. transition from RRCJDLE or RRCJNACTIVE to RRC_CONNECTED, such as an RRC Resume or RRC Setup message. ii) A transmission of a request message, e.g. RRC Resume Request or RRC Setup Request. iii) Stop to perform predictions due to the occurrent of another event, e.g. cell reselection or cell selection to a cell the UE 120 is not configured to perform the predictions. iv) Detection of incoming data in a buffer, e.g. real data at time to, not prediction. v) Detection of a change in the battery status at the UE 120, i.e. , upon battery level going below a threshold. vi) Upon the predicted value meeting a certain criterion, e.g., predicted volume for the next ‘X’ seconds being zero.

[0298] - One of the benefits is that such a second timer may be introduced to prevent the UE 120 to trigger the initiation of the transition to connected based on the predictions after some time it has been in RRCJNACTIVE or RRCJDLE. The reasoning may be in the case it is known that most sensitive data to control plane latency are the data and / or data packets coming first in a burst, and unlikely to be the ones right after a burst i.e., not the ones after the UE 120 has been transitioned to a power saving mode of operation.

[0299] In some embodiments, the one or more parameters comprise a value for a third timer, wherein the timer indicates for how long the UE 120 is not required to perform the predictions of the data volume, or for how long the UE 120 waits until it starts performing the predictions.

[0300] - The UE 120 starts the third timer upon an event, wherein the event may be one or more of: i) A reception of a message for transitioning the UE 120 to a power saving mode of operation, e.g. RRCJDLE or RRCJNACTIVE, such as an RRC Release message. ii) A cell reselection or cell selection, e.g. to one or the configured cells for performing predictions of data volume. iii) Entering into the power saving mode of operation, e.g. RRCJDLE or RRCJNACTIVE.

[0301] - The UE 120 may perform one or more of the following actions when the third timer expires: i) Perform one or more predictions of data volume in the protocol buffer. ii) Start of the first timer. iii) Start the second timer.

[0302] - The UE 120 may stop the third timer upon an event, wherein the event is one or more of: i) A reception of a message for transitioning the UE 120 to a connected mode of operation from a power saving mode of operation, e.g. transition from RRCJDLE or RRCJNACTIVE to RRC_CONNECTED, such as an RRC Resume or RRC Setup message. ii) A transmission of a request message, e.g. RRC Resume Request or RRC Setup Request. iii) Stop to perform predictions due to the occurrent of another event, e.g. cell reselection or cell selection to a cell the UE 120 is not configured to perform the predictions. iv) A reception of a paging message e.g. RAN paging or CN paging. v) A detection of a change in the battery status at the UE 120, i.e. , upon battery level going above a threshold.

[0303] - One of the benefits is that such a third timer may be introduced to prevent the UE 120 to try to come back too to connected state too soon after it has been transitioned to the power mode of operation e.g. to RRCJDLE or to RRC NACTIVE, which may possibly lead to a lot of signaling. Then, the UE 120 is prevented to either perform predictions or trigger the initiation of the transition to connected mode while the third timer is running.

[0304] Parameters comprising indications

[0305] The one or more configurations obtained by the UE 120 may comprise one or more parameters what actions the UE 120 may perform based on the one of more configurations for controlling the procedure for transitioning to the connected mode.

[0306] - In some embodiments, the one or more parameters comprise one or more indications, e.g. DRB ld(s), of one or more bearers, e.g. Data Radio Bearers, the UE 120 considers for the one or more predictions of data volume in the protocol buffer.

[0307] If the UE 120 has been configured while in connected mode of operation with a set of bearers, e.g. DRB I D= 1 , DRB=2, DRB=3, DRB I D=4, and transitions to a power saving mode of operation, e.g. RRCJNACTIVE) the UE 120 may store the bearers and the respective identifiers. Then, the one or more one or more parameters may be one or more bearer identifiers, out of the stored configured bearers, e.g. in the UE 120 AS Inactive context, indicating the bearers for which the UE 120 performs predictions e.g. DRB ID=1 and DRB I D=2. Hence, the UE 120 may perform predictions of data volume associated to these bearers only. The network, such as the RAN node 110, may determine to configure the UE 120 for predicting data volume and possibly trigger the transition to RRC_CON NESTED only for the bearers which are more sensitive to a control plane latency e.g. bearers associated to an application and / or OTT service which requires a very fast transmission of the first packets.

[0308] In one example, the one or more bearers are only related to Downlink traffic. In another example, the one or more bearers are only related to Uplink traffic. In another example, the one or more bearers are related to both Uplink and DL traffic.

[0309] In another example, the UE 120 is aware of which bearers it performs data volume predictions for, as one or more bearer identifiers may be reserved in the specifications for that purpose, e.g. for applications more sensitive to control latency, so that if the UE 120 has been configured while in connected mode with these bearers, it performs predictions of data volume for these bearers.

[0310] - In one embodiment, the one or more parameters comprise one or more indications, e.g. service ID, client ID, application Id, OTT Id, or App Id, of one or more OTT services and / or applications the UE 120 considers for the one or more predictions of data volume in the protocol buffer.

[0311] In one example, the UE 120 is aware of which OTT services and / or Applications it performs data volume predictions for, as one or more OTT services could be considered in the specifications for that purpose, e.g. for applications more sensitive to control latency, so that if the UE 120 has been configured while in connected mode with these services, it performs predictions of data volume for these services.

[0312] - In some embodiments, the one or more parameters comprise one or more parameters associated to the data volume to be predicted, such as one or more of:

[0313] Data volume threshold

[0314] • In one example, the data volume threshold indicates an amount of predicted data volume, wherein if the predicted data volume (at a given time instance tO) is above or equal (>=) the data volume threshold the UE 120 triggers the initiation of the transition to the connected mode of operation.

[0315] • In another example, there may be different data volume thresholds for the DL and for the UL.

[0316] • In another example, there may be different data volume thresholds for different bearers, and / or services and / or OTT applications.

[0317] At least one special type of incoming packet is predicted

[0318] • In one example, the data volume is at least one special type of incoming packet which is predicted, such as a packet from a given application, OTT service and / or bearers known to be sensitive to a control plane latency so that it benefits or needs to be delivered as fast as possible. If the special packet is predicted to come, the UE 120 triggers the initiation of the transition to the connected mode of operation.

[0319] • In another example, the procedure would only be triggered if the UE 120 predicts that a number N of special type of incoming packets, e.g. within a predefined interval, is predicted, wherein N could also be configured.

[0320] A time window configuration for a moving averaging

[0321] • In one example, the UE 120 performs the data volume prediction by predicting the volume within a moving window, according to a time window configuration. The time window configuration may comprises at least i) a starting point, e.g. time instant after the UE 120 has transitioned to the power saving mode of operation, and ii) a window length.

[0322] - In some embodiments, the one or more parameters comprise one or more threshold(s) for radio conditions of the cell the UE 120 is camping while in the power saving mode of operation, so that the UE 120 only performs the predictions, and / or initiate the transition to connected based on the predictions, if it is camping on a cell in good radio conditions.

[0323] In one example, the radio conditions are RSRP, Reference Signal Received Quality (RSRQ), Singla to Interference Noise Ratio (SINR) measurement per cell as defined in 3GPP Release 16 (v16.7.0) TS 38.331. The exact measurement quantity (e.g. RSRP, RSRQ, SINR) or quantities used for this purpose may also be part of the configuration. - In one embodiment, the one or more parameters comprises at least one parameter associated to a 2-steps Random access procedure as defined in 3GPP Release 16 (v16.7.0) TS 38.321, 3GPP Release 16 (v16.8.0) 38.300 from Release-16 onwards.

[0324] The UE 120 may only perform the predictions of data volume while in power saving mode of operation if one or more of these are fulfilled: i) The UE 120 does NOT support 2-steps RA; ii) The cell the UE 120 is camping does NOT support 2- steps RA, which may be determined by acquisition of system information.

[0325] Initiating the procedure for transitioning to the connected mode of operation

[0326] This is related to and may be combined with Action 704 described above.

[0327] In some embodiments, the initiating the procedure for transitioning to the connected mode of operation comprises setting a cause value in a request message and transmitting the request message including the cause value, wherein the cause value indicates that the UE 120 initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer.

[0328] - In some of these embodiments, the request message is an RRC message. That may be an RRC Resume Request, such as the RRCResumeRequest, RRCResumeRequestl, or a RRCSetupRequest, as defined in 3GPP Release 16 (V16.7.0) TS 38.331.

[0329] - In some of these embodiments, the request message is a L2 and / or L1 message, such as a Random-Access Channel (RACH) preamble, wherein the transmission of a specific preamble, and / or a preamble from a preamble group, indicates that this is a request for transitioning to connected mode based on one or more predictions of data volume. In such an embodiment, the network such as e.g. the RAN node 110, may configure either a specific RA preamble or a indicate a RA preamble group associated to a specific cause value as part of the network configuration. Such a configuration may be either sent to the UE 120 in a dedicated message when the UE 120 was in RRC CONNECTED mode or via a broadcast message.

[0330] - In some of these embodiments, the cause value indications may be different depending on a property of the predicted data volume e.g. Uplink, Downlink or both Downlink and Uplink. - In some of these embodiments, the UE 120 transmits the request message over a bearer which is defined for requests triggered based on the predictions of data volume e.g. a bearer which is not SRBO, or SRBO.

[0331] The method wherein the UE 120 is initiating the procedure for transitioning to the connected mode of operation may comprise performing an access control procedure for the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0332] - In some of these embodiments, there may one or more Access Category(ies) and one or more Access Identities associated to an access attempt which is triggered based on one or more predictions of data volume in the protocol buffer. At the network side, e.g. at the RAN node 110, the network, such as the RAN node 110, may use an access control for the attempt triggered by, e.g. based on, one or more predictions of data volume in the protocol buffer, as a way to control that attempts based on predictions should have lower priority, depending on the load conditions at the network. In other words, attempts based on a request due to the presence of actual data in the buffer may have a higher priority, as data is actually in the buffer, while the request due to predicted incoming data may have a lower priority, as data is not yet in the buffer.

[0333] - In some of these embodiments, the configurations for the access control parameters may also be specific for the transition to connected mode which is triggered based on the one or more predictions of data volume in the protocol buffer.

[0334] The procedure for transitioning to the connected mode of operation may comprise receiving a second message in response to the request message upon which the UE 120 either transitions to the connected mode of operation or remains in the power saving mode of operation.

[0335] - In some of these embodiments, the second message is an RRC Resume message, e.g. RRCResume as defined in 3GPP Release 16 (v16.7.0) TS 38.331. Upon receiving the RRC Resume message the UE 120 transitions to RRC_CONNECTED and resumes the connection, the bearers, etc.

[0336] In one embodiment the UE 120 is in RRCJNACTIVE and initiates the resume procedure based on, e.g. triggered by, or due to, one or more predictions of data volume in the protocol buffer.

[0337] In one embodiment the UE 120 resumes the connection and starts to operate according to a first set of connected mode parameters. As the UE 120 triggers the resume procedure based on predictions of data volume, there is probably no data in the UL buffer and / or in the DL buffer to be received by the UE 120 when the connection is resume. Hence, even though the UE 120 is in RRC_CONNECTED, it may still operate according to some configurations for higher power savings, such as: i) Longer DRX cycle(s), ii) the absence of one or more configured L3 measurements, i.e. configured according to the L3 a.k.a. RRC configuration MeasConfig IE, and / or perform one or more configured L3 measurements with relaxed requirements (e.g. longer measurements periodicities, different sampling rate, lower accuracy, etc.), and / or ii) no CSI measurement reporting, no RRC measurement reporting, no carrier aggregation (or the SCells are considered as deactivated), no Dual Connectivity (or the Secondary Group Configuration cells, as defined in 3GPP Release 16 (v16.7.0) TS 38.331, are considered as deactivated), etc.

[0338] In another embodiment, when the UE 120 is operating according to a first set of connected mode parameters and determines the presence of data volume in buffer, it may perform at least one of the following actions:

[0339] - It stops operating according to the first set of connected mode parameters;

[0340] - It releases / discards the first set of connected mode parameters.

[0341] In another embodiment, the UE 120 determines the presence of data volume in buffer and performs a second set of connected mode parameters on top of the first set of parameters. In this embodiment, the first and second set of parameters are of the same type i.e. at least one parameter in the set is of the same field and / or the same Information Element defined in RRC. The second set of connected mode parameters may be considered as for normal operation in RRC_CONNECTED, when data needs to be transmitted and / or received i.e. not for aggressive power savings, such as: i) Shorter DRX cycle(s), compared to the first set of parameters, ii) start to perform the configured L3 measurements, i.e. configured according to the L3 a.k.a. RRC configuration MeasConfig IE, and / or perform one or more configured L3 measurements with normal requirements, e.g. shorter measurements periodicities, and / or iii) CSI measurement reporting, RRC measurement reporting, carrier aggregation, or the SCells are possibly considered as activated, Dual Connectivity or the Secondary Group Configuration cells, as defined in 3GPP Release 16 (v16.7.0) TS 38.331, are considered as activated, etc.

[0342] - In one example this second set of connected mode parameters is / are received when the UE 120 transitions to the lower power mode e.g. RRCJNACTIVE.

[0343] - In one example this second set of connected mode parameters is / are received when the UE 120 transitions to RRC_CONECTED from the lower power mode e.g. RRCJNACTIVE, in the RRC Resume message.

[0344] - In one example this second set of connected mode parameters is / are received while the UE 120 is in RRC_CONECTED e.g. in an RRCReconfiguration message.

[0345] - In a variant, it is the presence of incoming data volume in the network buffer(s) (e.g. in the DL, at the network side) which triggers the switching from the first set of parameters (for power savings in RRC_CONNECTED) to the second set of parameters.

[0346] - In another variant, the incoming UL data volume in the UE 120 buffer(s) triggers a message to the network (e.g. Buffer Status Report or UE assistance information) indicating incoming UL data so that the network can re-configure the UE 120 to operate according to normal mode of operation in RRC_CONNECTED, by transmitting to the UE 120 an RRC reconfiguration, possibly including the second set of parameters. In this variant, notice that the resume procedure triggered by the UE 120 based on predictions of data volume served the purpose of preparing the UE 120 with the necessary configurations, and, at the same time, enable the gNodeB the UE 120 is connected to fetch the UE 120 AS Inactive context in a possibly different gNodeB (last serving gNodeB).

[0347] -In some embodiments the second message is an RRC Release message, e.g. RRCRelease including suspend configuration or not, defined in 3GPP Release 16 (V16.7.0) TS 38.331.

[0348] One example is when the UE 120 is in RRC NACTIVE and initiates the resume procedure based on, e.g. triggered by, or due to, one or more predictions of data volume in the protocol buffer and receives the RRCRelease in response, either moving the UE 120 to RRCJDLE, if RRCRelease does not contain suspend configuration, or indicating the UE 120 remains in RRCJNACTIVE (if RRCRelease contains suspend configuration.

[0349] - In some embodiments the second message is an RRC Setup message, e.g. RRCSetup as defined in 3GPP Release 16 (v16.7.0) TS 38.331.

[0350] One example is when the UE 120 is in RRCJDLE and initiates the RRC establishment procedure based on, e.g. triggered by, or due to, one or more predictions of data volume in the protocol buffer, and the network responds with an RRCSetup e.g. for establishing SRB1.

[0351] One example is when the UE 120 is in RRC NACTIVE and initiates the resume procedure based on (e.g. triggered by, or due to) one or more predictions of data volume in the protocol buffer, and the network responds with an RRCSetup, fallback procedure e.g., if network does not obtain the UE 120 AS Inactive context.

[0352] In some embodiments, in response to receiving the second message in response to the request message, the UE 120 may determine to keeping stored or deleting releasing the one or more configurations from the network for controlling the procedure for transitioning to the connected mode of operation based on one or more predictions of data in the protocol buffer.

[0353] In some embodiments, in response to receiving the second message in response to the request message, the UE 120 may keep stored one or more configurations from the network such as the RAN node 110, for controlling the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer, and applying a new configuration on top of the one or more configurations from the network such as the RAN node 110, also referred to as delta signaling.

[0354] In some embodiments, the procedure for transitioning to the connected mode of operation comprises the UE 120 includs information based on one or more predictions of data volume in the protocol buffer in a complete message of the procedure for transitioning to the connected mode of operation and transmitting the complete message to the network.

[0355] - In one embodiment the complete message corresponds to one or more of: i) an RRC Resume complete; ii) an RRC Connection Resume complete; iii) an RRC Connection Setup complete; iv) an RRC Setup complete.

[0356] - In one embodiment the complete message includes information derived from / or the one or more predictions of data volume in the protocol buffer. This may empower the network, such as the RAN node 110, to understand, possibly in addition to the cause value, the reason for the attempted transition to connected based on predictions of data volume, and possibly configure the network accordingly. For example, if the UE 120 reports that the prediction indicates that data is expected in the UL only after X ms, the network such as the RAN node 110, may determine to configure the UE 120 with a lower power setting, e.g. longer DRTX cycles, during this period of time or slightly shorter time.

[0357] In some of these embodiments, the UE 120 transmits and / or receives data, e.g. Packet Data Convergence Protocol (PDCP), RLC or Medium Access Control (MAC) PDUs, after it has transmitted the complete message. The UE 120 may start an inactivity timer, e.g. configured by the network such as the RAN node 110, only after the UE 120 has to started to transmit and / or receive data, e.g. PDCP, RLC or MAC PDUs, in the case the transition to a connected state is triggered based on one or more predictions of data volume in the protocol buffer. The reasoning here is that in the legacy procedure the timer is started once the UE 120 enters RRC_CONNECTED because that is due to the triggering of data, but in the scenario of the embodiments herein, it may take some duration from the time the UE 120 enters connected mode based on the one or more predictions of data volume in the protocol buffer and the time real data needs to be received and transmitted. One advantage of this embodiment is that the inactivity timer would not expiry faster than expected. Similar behavior may be applicable to the inactivity timer at the network side, e.g. at the RAN node 110, i.e. the network such as the RAN node 110, only starts its timer. Upon expiry of the inactivity timer at the network such as the RAN node 110, may determine to transition the UE 120 to RRCJDLE or RRCJNACTIVE from RRC_CONNECTED. Upon expiry of the inactivity timer at the UE 120 side the UE 120 may declare a failure and transition to RRCJDLE, which is not desirable unless there is really a failure.

[0358] The procedure for transitioning to the connected mode of operation may comprise that the UE 120 includes information based on one or more predictions of time instance(s) or time interval(s) at which a data in the protocol buffer is expected, e.g. predicted interarrival times of data and / or data packets and / or Protocol Data Units - PDUs. In these embodiments, the information may be included in a complete message of the procedure for transitioning to the connected mode of operation and transmitting the complete message to the network such as the RAN node 110.

[0359] The complete message may include information associated to the accuracy of the predictions for the one or more predictions of data volume in the protocol buffer.

[0360] The complete message may further include information associated to the error of the predictions for the one or more predictions of data volume in the protocol buffer.

[0361] The complete message may include information associated to the accuracy of the predictions for the time interval, e.g. inter-arrival time of data, at which a data in the protocol buffer is expected.

[0362] Method in the RAN node 110

[0363] Some embodiments herein relate to a method at the RAN node 110 for transitioning a UE from a power saving mode of operation to a connected mode of operation the method performed by the RAN node 110 may comprise:

[0364] - Receiving a request from the UE 120 for a procedure for transitioning the UE 120 to the connected mode of operation. The request may be triggered based on one or more predictions of data volume in a protocol buffer of the UE 120. The data volume is to be received and / or transmitted by the RAN node 110 from and / or to the UE 120. This is related to and may be combined with Action 803 described above.

[0365] In some embodiments, the procedure for transitioning to the connected mode of operation is performed while the UE 120 is in a power saving mode of operation, wherein the power saving mode of operation is one or more of: i) an RRCJDLE state; ii) an RRCJNACTIVE state; and iii) an RRC_DEACTIVATED state.

[0366] The connected mode of operation may corresponds to an RRC connected state, e.g., RRC_CONNECTED.

[0367] The request from the UE 120 for the procedure for transitioning to a connected mode of operation may comprise the request for an RRC Setup procedure. The RRC Setup procedure may comprise a state transition from RRCJDLE to RRC_CONNECTED.

[0368] The request from the UE 120 for the procedure for transitioning to a connected mode of operation may comprise a request for an RRC Resume procedure, the RRC Resume procedure may comprise the state transition from RRCJNACTIVE to RRC_CONNECTED. The one or more predictions of data volume in the protocol buffer

[0369] Embodiments herein refer to one or more predictions of data volume in a protocol buffer, wherein the data volume is to be transmitted and / or received by the UE 120.

[0370] In some embodiments, the protocol buffer corresponds to one or more of: i) A buffer in the application layer e.g., in the client of an OTT application, ii) a buffer in the Transport Control Protocol (TCP) layer or any other transport protocol, iii) a buffer in the Interpret Protocol (IP) protocol, and iv) a buffer in a protocol of the radio interface protocol stack, placed at layer 1 (L1) and / or layer 2 (L2), such as PDCP protocol layer, RLC layer, MAC layer, Physical (PHY) / L1 layer.

[0371] In some embodiments, the one or more one or more predictions is of data volume of the protocol buffer, e.g. a first protocol buffer, while that is determined in a second protocol layer. The examples given below are examples of protocol buffers, such as one or more of: i) An application, possibly having an AI / ML functionality to predict data volume, e.g. the client of an OTT app, ii) a Non-Access Stratum (NAS) protocol, and iii) a protocol in the radio interface protocol stack, e.g. placed at L1 and / or L2, such as RRC, PDCP protocol layer, RLC layer, MAC layer, or PHY L1 layer.

[0372] The modeling may be one as follows: An AS protocol, e.g. PDCP, RRC, determining the one or more predictions of data volume in an AS protocol layer and indicating that to the NAS layer, internal at the UE 120, so that it is the NAS layer, which based on that the transition to connected may be triggered, e.g. initiation of establishment or resume, based on the predictions.

[0373] In some other embodiments, the one or more one or more predictions is of data volume of the protocol buffer, e.g. the first protocol buffer are output of an Inference Model function at the UE 120. In a set of embodiments, the one or more predictions of data volume of a protocol buffer comprises summing up the one or more predictions of the total amount of data in bytes of the results of a data volume calculation procedure across: i) All logical channels of a logical channel group where this data would have been transmitted if the UE 120 would be in a connected mode of operation and / or ii) all applications which are applicable for the procedure of triggering the transition to connected based on predictions of data volume, or iii) more than one protocol layers e.g. summing up predictions of data volume in PDCP and RLC layers.

[0374] - In one embodiment, for example, if the prediction is associated with data volume in a PDCP buffer, the UE 120 may consider for the predictions of data volume the following predictions:

[0375] The predicted PDCP Service Data Units (SDUs) for which no PDCP Data

[0376] PDUs would be constructed, according to the prediction, the predicted PDCP Data PDUs that would not be submitted to lower layers, according to the prediction, the predicted PDCP Control PDUs, and predicted PDCP SDUs and data PDUS that would be predicted to be retransmitted.

[0377] - In one embodiment, for example, if the prediction is associated with data volume in a RLC buffer, the UE 120 consider for the predictions of data volume the following predictions:

[0378] The predicted RLC SDUs and predicted RLC SDU segments, according to the prediction.

[0379] The predicted RLC data PDUs that would be pending for initial transmission, according to the prediction.

[0380] The predicted RLC data PDUs that would be pending for retransmission (RLC AM).

[0381] - In one embodiment, the one or more one or more predictions is of data volume of an Uplink protocol buffer, i.e. a buffer at the UE 120 side, for transmission of data by the UE 120. - In one embodiment, the one or more one or more predictions is of data volume of a Downlink protocol buffer, i.e. a buffer at the network side for reception of data by the UE 120, wherein the prediction is about what the network may buffer in at a certain time.

[0382] - In one embodiment, the one or more one or more predictions is of data volume which is combined volume of a Downlink protocol buffer and an Uplink protocol buffer.

[0383] In a set of embodiments, the one or more predictions of data volume of a protocol buffer may comprise one or more buffer related prediction / estimation as follows:

[0384] - Predicted data arrival times

[0385] Binary queries: The UE 120 may determine whether there will be an amount of data arriving to the UL buffer or not within a given time period. For example, if the UE 120 predicts whether any data will arrive to the buffer within a time period T, possibly part of the one or more configurations for controlling the procedure, possibly configured by the network, the UE 120 initiates the procedure to transition to connected mode, establishment, or resume. Figure 12 illustrates this in an example of predictions of data volume. The UE 120 transitions to power saving mode of operation at t0’. The UE 120 performs a prediction of data volume at time instance to for incoming data in time tO+T. At time instance to the UE 120 initiates the procedure to transitioning to connected mode of operation. At time tO+T when the actual data arrives in the buffer for transmission, the UE 120 would have already transitioned to the connected mode of operation and would experience no delay in transmission of the arrived data.

[0386] Exact time of arrivals: The UE 120 may predict the exact time at which data is predicted to arrive to the buffer.

[0387] For example, the UE 120 predicts that the next time instance when data will arrive will be at time instances t1 <t2<... tN, with N possibly being part of the one or more configurations for controlling the procedure. Such information may be used to determine whether a transition to connected mode of operation should be triggered or not. In one example, the UE 120 initiates the transition if at to the UE 120 predicts that at tO+T a first packet will be in the buffer and a number N of incoming packets, within a second interval (tn-t1) will also arrive in the buffer. Figure 13 illustrates this in an example of predictions of data volume. In Figure 13, the UE 120 transitions to power saving mode of operation at t0’. The UE 120 performs a prediction of data volume at time instance to for incoming data in time tO+T. At time instance to the UE 120 initiates the procedure to transitioning to connected mode of operation if more than at least N packets arrive within a time interval from the first predicted data. At time t1 = tO+T, t2, tN when the actual data arrives in the buffer for transmission, the UE 120 would have already transitioned to the connected mode of operation and would experience no delay in transmission of the arrived data.

[0388] - Amount of data arriving, and e.g. packet size.

[0389] How much data, e.g., in units of bytes or packets, etc., will arrive e.g. in a given time, is possibly determined by a time window of length T. For example, by the UE 120 predicting the amount of data to be arrived in a future instance, e.g. current time + T, and / or within a given time period from that future instance, current time + T + averaging interval, the UE 120 may further determine whether it should initiate the procedure to transition to a connected mode of operation of not. For example, if the UE 120 predicts at time instance to that an amount of data volume will arrive at tO+T and that is predicted to be larger than X, wherein X may be configurable, during an averaging time interval starting at tO+T. In one example the UE 120 determines the predicted data volume by summing up and / or averaging over time predicted data volume starting from tO+T until the averaging time interval, which may be modeled by a duration in a time window. Else, if the UE 120 predicts that the amount of data to be arrived is smaller than X, it does not trigger the attempt to transition to connected mode of operation.

[0390] - Continuous data vs short bursts

[0391] The UE 120 may predict at a time instance to that a burst of continuous data is coming to the buffer, and possibly predict the amount of data volume for such a burst. If the burst is larger than X the UE 120 may initiate the attempt to transition to connected mode, otherwise it does not. The advantage here is for the case where the UE 120 knows this type of traffic is the type sensitive to control plane latency.

[0392] The UE 120 may predict at a time instance to that short bursts of data are coming to the buffer, and possibly predict the amount of data volume for each of these bursts. If the UE 120 is aware that the predicted bursts are short, the UE 120 may initiate the attempt to transition to connected mode, otherwise it does not. The advantage here is for the case where the UE 120 knows this type of traffic is the type sensitive to control plane latency. In an alternative, the prediction that the bursts are short may lead the UE 120 to not initiate the procedure to transition to connected based on the predictions, but instead, wait until the data comes and determine to trigger a Small Data Transmission procedure.

[0393] Prediction model for performing predictions of data volume

[0394] This is related to and may be combined with Action 702 and 802 described above. According to embodiments herein, the UE 120 performs one or more predictions of data volume in a protocol buffer for triggering a transition to connected mode, wherein the one or more predictions of data volume in a protocol buffer are outputs of a prediction model at the UE 120. In these embodiments, the UE 120 may be equipped with a prediction model, which may be an Al and / or ML function at the UE 120.

[0395] In a set of embodiments, the prediction model is at the UE 120 i.e. the predictions of data volume are performed at the UE 120, while the UE 120 is a power saving mode of operation. However, the prediction model may be designed, generated or created at the UE 120, i.e. training phase at the UE 120, possibly created by a “Training Model” function. Alternatively, the prediction model may be designed, or generated at a network entity / node and obtained by the UE 120 via some method, such as by download, wherein that relies on the network being equipped with a Training Model function and possibly a Data Collection function, i.e. training phase at the network, such as e.g. the RAN node 110.

[0396] In one embodiment, the UE 120 receives a prediction model from the network, such as e.g. the RAN node 110. In one variant the prediction model is implemented as a software function that is provided from the network to the UE 120, for example, in a procedure where the UE 120 downloads this software function. An alternative solution relies on APIs that are exposed by the UE 120 to the network, so an entity at the network side is able to configure a prediction model at the UE 120. In that case, there may be a procedure where the UE 120 indicates to the network, such as e.g. the RAN node 110, a capability related information i.e. UE indicates to the network that it is capable to download and / or receive a prediction model from the network, for example, for mobility prediction information, according to the method. This capability may be related to software and hardware aspects at the UE 120, availability of sensors, etc. Once the UE 120 has the function available, it may be further configured by the network to use it.

[0397] In another embodiment, at least one prediction model to be implemented at the UE 120 is standardized and configured by the network, such as e.g. the RAN node 110, with a set of parameters. The set of parameters associated to the model may be part of the one or mode configurations for controlling the procedure for transitioning to connected mode of operation. A Neural Network (NN) may be used, e.g. the UE 120 already knows that it will implement a NN of “L” layers, where each layer “i” has “Ni” nodes, and each node “j” has a set of weights “Wj”, but the values of “L”, “Ni” and “Wj” are set by the network, such as e.g. the RAN node 110. Another possible model may be a Random Forest, where the network, such as e.g. the RAN node 110 will set the number of estimators, trees in the forest, the depth of each tree and the threshold of each leaf.

[0398] In another embodiment, the UE 120 has stored a prediction model, e.g., UE proprietary prediction model, to perform the prediction. In that case, there may be a procedure where the UE 120 indicates to the network, such as e.g. the RAN node 110, a capability related to that, i.e. , indicate that it is capable to perform a certain prediction according to the method, e.g., it is capable to predict whether new data is expected to arrive in the protocol buffer, e.g. a DL / UL buffer, in a given time frame, etc. A capability may be reported to the network, such as e.g. the RAN node 110, in different levels of granularity such as: i) UE has a prediction model and / or ii) which exact prediction model the UE 120 has available, e.g., out of a list defined in the specifications and / or iii) which kinds of predictions the model(s) the UE 120 has available performs and / or iv) what kinds of input the model(s) the UE 120 has available to take into account, etc.

[0399] In another embodiment, the UE 120, or any parts of the terminal, not necessarily the module for communication, may collect data statistics about a given application and / or service and / or bearer to generate or configure a prediction model, e.g. a machine learning function, artificial intelligence function, etc., that is able to perform predictions. The predictions are e.g., related to the buffer status and / or in more general terms, predictions related to incoming DL data flows and / or outcome UL data flows, like when a packet will need to be transmitted and which size in bits. In this embodiment, the UE 120 performs the training phase as the UE 120 is the entity collecting and processing the data traffic in its buffers in order to generate / configure the data model.

[0400] Figure 14 illustrates a periodic burst of data that arrives at the UE 120 buffer. The X-axis represents time, and the Y-axis represents amount of data e.g. relating to data volume. The burst has a duration of 80ms and repeats at each 110ms. A feature used in the prediction model may be represented, for example, by a vector of size “1=10”, where the “i-th” element, from the left to the right in Figure 14, corresponds to the amount of data that arrived “(l-i)*T” instants ago, where T=10ms represents a given time step. Besides, the expected output of the predictor may be a vector of size “J=6”, where the “j-th” element corresponds to the expected data that will arrive at the UE 120 buffer “j*T” instants ahead. In order to learn a model in a supervised way, the UE 120 stores, over the time, multiple snapshots of a sliding window of size “l+J= 16”, where the x-th element, from the left to the right in Figure 14, and 0<x<17, corresponds to the amount of data that arrived (16 - x)*10ms ago. During the learning process, each stored sliding window may be split into two vectors, where one vector of size 1=10 represents a given input and the other vector of size J=6 represents the expected output that a given model must learn. Recurrent Neural Networks (RNN), e.g., a Long Short-Term Memory (LSTM), may be used as a predictor, since they are known for their capability of extracting statistical information from time series. After having learnt the model, the UE 120 may use it in an online fashion, with input vectors of size “1=10” in order to predict the expected amount of data that will arrive in the next “J=6” instants of time.

[0401] A prediction model may be learnt at the network side, such as e.g., by the RAN node 110, from traffic statistics collected over time reflecting different features, e.g., amount of data and its expected time of arrival. The features may be represented, for example, by a vector of size “J”, where the “j-th” element corresponds to the amount of data that arrived “j*T” instants ago, and where T is an integer representing a given time step. Another feature may be represented by a vector of size “K”, where the “k-th” element represents the mean periodicity of packets of size “k*L”, where “L” is a given standard packet size.

[0402] Different possibilities for the training process may be envisioned, for example:

[0403] - To use previous recorded datasets assembling examples of inputs and their expected outputs. An example of a prediction model that may benefit of previous recorded dataset is a Recurrent Neural Network (RNN). Unlike standard feedforward NNs, an RNN has feedback connections that work as a memory state. This memory state allows the network, such as e.g. the RAN node 110, to preserve traffic statistics across time steps which are useful for predicting time series. For example, the network such as e.g. the RAN node 110, may feed the RNN with a feature related to the amount of data that arrived in the DL buffer over the last “T” instants of time, and the RNN will be able to output the expected amount of data that will arrive in the next instants. To train the RNN, the network, such as e.g., the RAN node 110, may use a Backpropagation Through Time (BPTT) method. A Long Short-Term Memory (LSTM) architecture is an example or RNN that may be used. It learns what to store in the long-term state, what to throw away, and what to read from it.

[0404] - To try to find hidden patterns without having any prior knowledge, e.g., training sets, of the output that they should come up with for each input. K-means is an option. It tries to find clusters only based on unlabelled input and a predefined number of clusters. For example, patterns of amount of data may be clustered according to the likelihood of new data arriving in the DL buffer over the next “T” instants of time.

[0405] The models generated by the network may be UE specific, such as UE 120 specific, e.g., a set of RNN weights specific for each connected UE, such as the UE 120, may be service specific, e.g., different set of RNN weights for Ultra-Reliable Low-Latency Communication (URLLC) and enhanced Mobile Broadband (eMBB) services, etc. In the following, one possible way of how the network, such as e.g., the RAN node 110, may use data statistics of a given application and / or service and / or bearer to generate a model that is able to perform predictions is illustrated. In this example, the prediction model will predict the probability of new data to arrive X instants of time ahead.

[0406] In a set of embodiments, some of the functions related to the predictions of the data volume in the protocol buffer may correspond to the following functions of the 3GPP Release 17 (v17.0.0) TS 37.817 Functional Framework for RAN Intelligence, as follows:

[0407] - Data Collection is a function that provides input data to Model training for predictions of data volume and Model inference functions for predictions of data volume, wherein the collected data comprises “real” data volume in protocol buffer and / or related information, such as inter-arrival time intervals. Examples of input data may include measurements from UEs, such as the UE 120, related to data volume, e.g., in UL buffer to be transmitted and / or DL buffer which has been received, such as data volume in the PDCP layer and / or RLC layers, and / or other data volume related metrics such as information related to inter-arrival time intervals. In an alternative, the input data may include measurements from a network entity, e.g. in the RAN node 110, in UL buffer which is received at the network, such as e.g. at the RAN node 110, and / or DL buffer which is to be transmitted by the network, such as e.g. the RAN node 110. Any of these input data may be used as Training data, i.e., to be provided, possibly after processing, to the AI / ML Model Training function, or as inference data, to be used as input for determining predictions of data volume in the future.

[0408] - Model Training is a function at the UE 120 that performs the ML model training, validation, and testing for the prediction of data volume. The Model training function is also responsible for data preparation, e.g., data pre-processing and cleaning, formatting, and transformation, based on Training Data delivered by a Data Collection function, if required. In one alternative the Model training function is placed at the UE 120, and receives training data from the Data collector, which also may be located at the UE 120. In another option the Model Training function is placed at a network entity, such as e.g. at the RAN node 110, and after the model is trained it is either configured at the UE 120 by the network, such as e.g. at the RAN node 110, and / or obtained by the UE 120 via other means, such as via a download and / or obtaining from a Subscriber Identity Module (SIM) card, or any other method previously described herein.

[0409] - According to embodiments herein, a “Model Inference” is a function, e.g. located at the UE 120 and is the one which may provide AI / ML model inference output, such as the predictions of data volume in the protocol buffer (which is an inference output), or the decision to initiate a resume procedure based on the predictions of data volume (which is an inference output). See Action 703 described above. According to embodiments herein, the Model inference function may also be responsible for data preparation, e.g. data preprocessing and cleaning, formatting, and transformation, based on Inference Data delivered by a Data Collection function, if required. The model inference function may also be referred to as a prediction function, a predictor or AI / ML prediction function.

[0410] - According to embodiments herein, there may be different alternatives for what the Acto” may correspond to. The actor comprises a function that receives the output from the Model inference function and triggers or performs corresponding actions. According to the method, the “Actor” provides feedback information, comprising information that may be needed to derive training or inference data or performance feedback. The Actor may comprise a triggering of actions directed to other entities or to itself and there may be alternatives:

[0411] If the output are predictions of data volume in the protocol buffer, e.g., related to Action 703 described above, the Actor at the UE 120 may verify whether the predictions shall trigger or not the initiation of a transition to a connected mode of operation, e.g. if predicted data volume threshold is above a configured value. If the Model inference function provides as output a decision to initiate the transition to connected mode of operation based on its predictions of data volume in the protocol buffer e.g., related to Action 704 described above, the Actor may comprise a function which initiates the transition.

[0412] The feedback may correspond to the verification of whether after the UE 120 transitions to connected, e.g., according to any one or more out of: a real data volume, not predicted and / or predictions of data volume, has arrived in the protocol buffer and / or how much data volume and / or if the amount of data volume is the same or close to the value of the predictions of data volume.

[0413] This feedback may be used as input by the Data Collection function and / or to compute the performance of the Model inference function.

[0414] As explained above, there may be different alternatives concerning where these functions are located e.g., at the UE 120 or in the network, such as e.g., at the RAN node 110.

[0415] In one example illustrated in Figure 15, the functions in the framework are deployed at the UE 120. At the Data Collection function, the UE 120 collects data from the applications and / or data volume information from the protocol buffers. This is possibly processed and provided as Training data to the Model Training function, which is also at the UE 120, possibly in the same protocol layer or in a different protocol layer, and / or provided as Inference data to the Model Inference function. The Model Training function deploys the model i.e. its outcome is the “Model Inference function”. For example, based on the processing of traffic patterns, like statistics of the “real” data volume in protocol buffers and / or inter-arrival timer, possibly used as training data, the Model Training gets a Model Inference function able to predict data volume, all at the UE 120, based on data volume information at the UE 120. In one alternative, the Model Inference is responsible for predicting data volume in data buffer and indicate as output to the Actor, which in this case it is a function at the UE 120 which monitors different triggers to determine to transition to connected mode of operation.

[0416] In another example illustrated in Figure 16, some of the functions in the framework are deployed at the UE 120, while others are deployed at the network, such as e.g., at the RAN node 110. For example, Data collection, at least partially, and Model Training are deployed at the network side, such as e.g. at the RAN node 110, while the Model Inference and Actor are at the UE 120, because the UE 120 needs to be the one determining to initiate resume based on the predictions of data volume, the outcome of the Model Inference function. Then, as Data Collection and Model Training functions are at the network, such as e.g., at the RAN node 110, the UE 120 ,ay need to obtain the Model Inference function and / or related configurations from the network entity, e.g. in e.g. the RAN node 110.

[0417] To perform the method actions above, the UE 120 is configured to initiate a procedure for transitioning the UE 120 from a power saving mode of operation to a connected mode of operation in a wireless communications network 100. The UE 120 may comprise an arrangement depicted in Figures 17a and 17b.

[0418] The UE 120 may comprise an input and output interface 1700 configured to communicate in the communication network 100, e.g., with the RAN node 110. The input and output interface 1700 may comprise a wireless receiver (not shown) and a wireless transmitter (not shown).

[0419] The UE 120 is further configured to, e.g. by means of a performing unit 1701 in the UE 120, perform one or more predictions of data volume in a protocol buffer. The data volume is adapted to be predicted for being transmitted between the UE 120 and the RAN node 110 in an upcoming data transmission.

[0420] The UE 120 is further configured to, e.g. by means of a initiating unit 1702 in the UE 120, before data of the upcoming data transmission arrives in the protocol buffer, initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer.

[0421] The UE 120 is further configured to, e.g. by means of a sending unit 1703 in the UE 120, send to the RAN node 110, a request for the transitioning to the connected mode of operation.

[0422] The request for the transitioning to the connected mode of operation, may further be adapted to indicate that the UE 120 has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer. The UE 120 may further be configured to, e.g. by means of an obtaining unit 1704 in the UE 120, obtain one or more configurations for controlling the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer.

[0423] The one or more configurations may be adapted to comprise one or more parameters related to any one or more out of:

[0424] - The performing of the one or more predictions of the data volume in the protocol buffer,

[0425] - the initiating of the procedure for transitioning to the connected mode of operation.

[0426] - one or more location information where to perform the one or more predictions of data volume in the protocol buffer,

[0427] - one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,

[0428] - one or more location information where the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,

[0429] - a value for a first timer, indicating for how long time the UE 120 shall perform the one or more predictions of data volume in the protocol buffer,

[0430] - a value for a second timer, indicating for how long time the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation,

[0431] - a value for a third timer, indicating for how long time the UE 120 is not required to perform the one or more predictions of the data volume in the protocol buffer, or for how long time the UE 120 shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,

[0432] - one or more indications of one or more bearers the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0433] - one or more indications of one or more Over The Top, OTT, services the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer,

[0434] - one or more indications of one or more applications the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0435] - one or more parameters associated to the data volume to be predicted. The UE 120 is further configured to, e.g. by means of the sending unit 1703 in the UE 120, send a message to the RAN node 110, which message is adapted to indicate any one or more out of:

[0436] - Data based on or related to the one or more predictions of the data volume in the protocol buffer,

[0437] - data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,

[0438] - data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected, and

[0439] - data associated to any error of the one or more predictions of data volume in the protocol buffer.

[0440] The UE 120 may further be configured to, e.g. by means of a starting unit 1705 in the UE 120, at starting to communicate the data related to the one or more predictions of the data volume in the protocol buffer, start an inactivity timer, which when expires initiates a transitioning of the UE 120 from a connected mode of operation to a power saving mode of operation.

[0441] In some embodiments, the UE 120 is further configured to, e.g. by means of the obtaining unit 1704 in the UE 120, obtain a model for the one or more predictions, and wherein the model may be obtained by any one out of:

[0442] - Training the model in the UE 120, or

[0443] - receiving the model from a RAN node 110,

[0444] In these embodiments, the UE 120 further is configured to, e.g. by means of the performing unit 1701 in the UE 120, perform the one or more predictions of data volume in the protocol buffer based on the model.

[0445] To perform the method actions above, the RAN node 110 is configured to handle a UE 120 initiated procedure for transitioning the UE 120 from a power saving mode of operation to a connected mode of operation in the wireless communications network 100. The RAN node 110 may comprise an arrangement depicted in Figures 18a and 18b.

[0446] The RAN node 110 may comprise an input and output interface 1800 configured to communicate in the communication network 100, e.g., with the UE 120. The input and output interface 1800 may comprise a wireless receiver (not shown) and a wireless transmitter (not shown).

[0447] The RAN node 110 is further configured to, e.g. by means of a receiving unit 1801 in the RAN node 110, before data of an upcoming data transmission arrives in a protocol buffer of the UE 120, receive a request from the UE 120. The request is adapted to relate to a UE initiated procedure for transitioning to the connected mode of operation based on one or more predictions of the data volume in the protocol buffer. The data volume is adapted to be predicted for being transmitted between the UE 120 and the RAN node 110 in the upcoming data transmission.

[0448] The request for the transitioning to the connected mode of operation, may further be adapted to indicate that the UE 120 has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer.

[0449] The RAN node 110 is further configured to, e.g. by means of a deciding unit 1802 in the RAN node 110, decide whether or not to transitioning to connected mode of operation based on the received request.

[0450] The RAN node 110 may further be configured to, e.g. by means of the deciding unit 1802 in the RAN node 110, decide whether or not to transitioning the UE 120 to connected mode of operation based on the received request, based on the indication.

[0451] The RAN node 110 is further configured to, e.g. by means of a sending unit 1803 in the RAN node 110, send to the UE 120, a message indicating the outcome of the deciding of whether or not to transitioning to connected mode of operation.

[0452] The RAN node 110 may further be configured to, e.g. by means of the sending unit 1803 in the RAN node 110, send to the UE 120, one or more configurations configuring the UE 120 to:

[0453] - Perform one or more predictions of data volume in a protocol buffer, wherein the data volume is to be predicted to be transmitted between the UE 120 and a Radio Access Network, RAN, node 110 in an upcoming data transmission, and

[0454] - before data of the upcoming data transmission arrives in the protocol buffer, initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer.

[0455] The one or more configurations may further be adapted to configure the UE 120 to: - at starting to communicate the data related to the one or more predictions of the data volume in the protocol buffer, start an inactivity timer, which when expires initiates a transitioning of the UE 120 from a connected mode of operation to a power saving mode of operation.

[0456] The one or more configurations may be adapted to comprise one or more parameters related to any one or more out of:

[0457] - The performing of the one or more predictions of the data volume in the protocol buffer,

[0458] - the initiating of the procedure for transitioning to the connected mode of operation.

[0459] - one or more location information where to perform the one or more predictions of data volume in the protocol buffer,

[0460] - one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,

[0461] - one or more location information where the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,

[0462] - a value for a first timer, indicating for how long time the UE 120 shall perform the one or more predictions of data volume in the protocol buffer,

[0463] - a value for a second timer, indicating for how long time the UE 120 is allowed to trigger the initiation of a transitioning to a connected mode of operation,

[0464] - a value for a third timer, indicating for how long time the UE 120 is not required to perform the one or more predictions of the data volume in the protocol buffer, or for how long time the UE 120 shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,

[0465] - one or more indications of one or more bearers the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0466] - one or more indications of one or more Over The Top, OTT, services the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer,

[0467] - one or more indications of one or more applications the UE 120 shall consider for the one or more predictions of data volume in the protocol buffer, and

[0468] - one or more parameters associated to the data volume to be predicted.

[0469] The RAN node 110 may further be configured to, e.g. by means of the receiving unit 1801 in the RAN node 110, receive a message from the UE 120, which message is adapted to indicate any one or more out of: - Data based on or related to the one or more predictions of the data volume in the protocol buffer,

[0470] - data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,

[0471] - data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected,

[0472] - data associated to any error of the one or more predictions of data volume in the protocol buffer.

[0473] The RAN node 110 may further be configured to, e.g. by means of the sending unit 1803 in the RAN node 110, send to the UE 120, a model for the one or more predictions, and wherein the one or more configurations further are adapted to configure the UE 120 to perform the one or more predictions of data volume in the protocol buffer based on the model.

[0474] The embodiments herein may be implemented through a respective processor or one or more processors, such as a processor 1706 of a processing circuitry in the UE 120 depicted in Figure 17a, and a processor 1804 of a processing circuitry in the RAN node 110 depicted in Figure 18a, together with respective computer program code for performing the functions and actions of the embodiments herein. The program code mentioned above may also be provided as a computer program product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the respective UE 120 and RAN node 110. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the respective UE 120 and RAN node 110.

[0475] The UE 120 and RAN node 110 may further comprise respective memories 1707, 1805 comprising one or more memory units. The respective memories 1707, 1805 comprise instructions executable by the processor in the respective UE 120 and RAN node 110. The respective memories 1707, 1805 are arranged to be used to store e.g. information, indications, data, configurations, communication data, and applications to perform the methods herein when being executed in the respective UE 120 and RAN node 110. In some embodiments, respective computer programs 1708, 1806 comprise instructions, which when executed by the respective at least one processor 1706, 1804, cause the at least one processor of the respective UE 120 and RAN node 110 to perform the actions above.

[0476] In some embodiments, respective carriers 1709, 1807 comprise the respective computer program 980, wherein the carrier 990 is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium.

[0477] Those skilled in the art will appreciate that the units in the respective UE 120 and RAN node 110 described above may refer to a combination of analog and digital circuits, and / or one or more processors configured with software and / or firmware, e.g. stored in the respective UE 120 and RAN node 110, that when executed by the respective one or more processors such as the processors described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application- Specific Integrated Circuitry ASIC, or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a system-on-a-chip SoC.

[0478] With reference to Figure 19, in accordance with an embodiment, a communication system includes a telecommunication network 3210, such as a 3GPP-type cellular network, e.g. communication network 100, which comprises an access network 3211, such as a radio access network, and a core network 3214. The access network 3211 comprises a plurality of base stations 3212a, 3212b, 3212c, such as AP STAs NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 3213a, 3213b, 3213c. Each base station 3212a, 3212b, 3212c, e.g. radio network nodes 141 ,142, is connectable to the core network 3214 over a wired or wireless connection 3215. A first user equipment (UE), e.g. remote end 121 or gateway device 110, such as a Non-AP STA 3291 located in coverage area 3213c is configured to wirelessly connect to, or be paged by, the corresponding base station 3212c. A second UE 3292 such as a Non-AP STA in coverage area 3213a is wirelessly connectable to the corresponding base station 3212a. While a plurality of UEs 3291 , 3292 are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding base station 3212.

[0479] The telecommunication network 3210 is itself connected to a host computer 3230, which may be embodied in the hardware and / or software of a standalone server, a cloud- implemented server, a distributed server or as processing resources in a server farm. The host computer 3230 may be under the ownership or control of a service provider, or may be operated by the service provider or on behalf of the service provider. The connections 3221, 3222 between the telecommunication network 3210 and the host computer 3230 may extend directly from the core network 3214 to the host computer 3230 or may go via an optional intermediate network 3220. The intermediate network 3220 may be one of, or a combination of more than one of, a public, private or hosted network; the intermediate network 3220, if any, may be a backbone network or the Internet; in particular, the intermediate network 3220 may comprise two or more sub-networks (not shown).

[0480] The communication system of Figure 19 as a whole enables connectivity between one of the connected UEs 3291 , 3292 and the host computer 3230. The connectivity may be described as an over-the-top (OTT) connection 3250. The host computer 3230 and the connected UEs 3291 , 3292 are configured to communicate data and / or signaling via the OTT connection 3250, using the access network 3211 , the core network 3214, any intermediate network 3220 and possible further infrastructure (not shown) as intermediaries. The OTT connection 3250 may be transparent in the sense that the participating communication devices through which the OTT connection 3250 passes are unaware of routing of uplink and downlink communications. For example, a base station 3212 may not or need not be informed about the past routing of an incoming downlink communication with data originating from a host computer 3230 to be forwarded (e.g., handed over) to a connected UE 3291. Similarly, the base station 3212 need not be aware of the future routing of an outgoing uplink communication originating from the UE 3291 towards the host computer 3230.

[0481] Example implementations, in accordance with an embodiment, of the UE, base station and host computer discussed in the preceding paragraphs will now be described with reference to Figure 20. In a communication system 3300, a host computer 3310 comprises hardware 3315 including a communication interface 3316 configured to set up and maintain a wired or wireless connection with an interface of a different communication device of the communication system 3300. The host computer 3310 further comprises processing circuitry 3318, which may have storage and / or processing capabilities. In particular, the processing circuitry 3318 may comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. The host computer 3310 further comprises software 3311 , which is stored in or accessible by the host computer 3310 and executable by the processing circuitry 3318. The software 3311 includes a host application 3312. The host application 3312 may be operable to provide a service to a remote user, such as a UE 3330 connecting via an OTT connection 3350 terminating at the UE 3330 and the host computer 3310. In providing the service to the remote user, the host application 3312 may provide user data which is transmitted using the OTT connection 3350.

[0482] The communication system 3300 further includes a base station 3320 provided in a telecommunication system and comprising hardware 3325 enabling it to communicate with the host computer 3310 and with the UE 3330. The hardware 3325 may include a communication interface 3326 for setting up and maintaining a wired or wireless connection with an interface of a different communication device of the communication system 3300, as well as a radio interface 3327 for setting up and maintaining at least a wireless connection 3370 with a UE 3330 located in a coverage area (not shown in Figure 20) served by the base station 3320. The communication interface 3326 may be configured to facilitate a connection 3360 to the host computer 3310. The connection 3360 may be direct or it may pass through a core network (not shown in Figure 20) of the telecommunication system and / or through one or more intermediate networks outside the telecommunication system. In the embodiment shown, the hardware 3325 of the base station 3320 further includes processing circuitry 3328, which may comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. The base station 3320 further has software 3321 stored internally or accessible via an external connection.

[0483] The communication system 3300 further includes the UE 3330 already referred to. Its hardware 3335 may include a radio interface 3337 configured to set up and maintain a wireless connection 3370 with a base station serving a coverage area in which the UE 3330 is currently located. The hardware 3335 of the UE 3330 further includes processing circuitry 3338, which may comprise one or more programmable processors, applicationspecific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. The UE 3330 further comprises software 3331, which is stored in or accessible by the UE 3330 and executable by the processing circuitry 3338. The software 3331 includes a client application 3332. The client application 3332 may be operable to provide a service to a human or non-human user via the UE 3330, with the support of the host computer 3310. In the host computer 3310, an executing host application 3312 may communicate with the executing client application 3332 via the OTT connection 3350 terminating at the UE 3330 and the host computer 3310. In providing the service to the user, the client application 3332 may receive request data from the host application 3312 and provide user data in response to the request data. The OTT connection 3350 may transfer both the request data and the user data. The client application 3332 may interact with the user to generate the user data that it provides. It is noted that the host computer 3310, base station 3320 and UE 3330 illustrated in Figure 20 may be identical to the host computer 3230, one of the base stations 3212a, 3212b, 3212c and one of the UEs 3291 , 3292 of Figure 19, respectively. This is to say, the inner workings of these entities may be as shown in Figure 20 and independently, the surrounding network topology may be that of Figure 19.

[0484] In Figure 20, the OTT connection 3350 has been drawn abstractly to illustrate the communication between the host computer 3310 and the use equipment 3330 via the base station 3320, without explicit reference to any intermediary devices and the precise routing of messages via these devices. Network infrastructure may determine the routing, which it may be configured to hide from the UE 3330 or from the service provider operating the host computer 3310, or both. While the OTT connection 3350 is active, the network infrastructure may further take decisions by which it dynamically changes the routing (e.g., on the basis of load balancing consideration or reconfiguration of the network).

[0485] The wireless connection 3370 between the UE 3330 and the base station 3320 is in accordance with the teachings of the embodiments described throughout this disclosure. One or more of the various embodiments improve the performance of OTT services provided to the UE 3330 using the OTT connection 3350, in which the wireless connection 3370 forms the last segment. More precisely, the teachings of these embodiments may improve the RAN effect: data rate, latency, power consumption and thereby provide benefits such as e.g. the applicable corresponding effect on the OTT service: reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime.

[0486] A measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve. There may further be an optional network functionality for reconfiguring the OTT connection 3350 between the host computer 3310 and UE 3330, in response to variations in the measurement results. The measurement procedure and / or the network functionality for reconfiguring the OTT connection 3350 may be implemented in the software 3311 of the host computer 3310 or in the software 3331 of the UE 3330, or both. In embodiments, sensors (not shown) may be deployed in or in association with communication devices through which the OTT connection 3350 passes; the sensors may participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which software 3311, 3331 may compute or estimate the monitored quantities. The reconfiguring of the OTT connection 3350 may include message format, retransmission settings, preferred routing etc.; the reconfiguring need not affect the base station 3320, and it may be unknown or imperceptible to the base station 3320. Such procedures and functionalities may be known and practiced in the art. In certain embodiments, measurements may involve proprietary UE signaling facilitating the host computer’s 3310 measurements of throughput, propagation times, latency and the like. The measurements may be implemented in that the software 3311, 3331 causes messages to be transmitted, in particular empty or ‘dummy’ messages, using the OTT connection 3350 while it monitors propagation times, errors etc.

[0487] Figure 21 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment. The communication system includes a host computer, a base station such as an AP STA, and a UE such as a Non-AP STA which may be those described with reference to Figure 19 and Figure 20. For simplicity of the present disclosure, only drawing references to Figure 21 will be included in this section. In a first step 3410 of the method, the host computer provides user data. In an optional sub step 3411 of the first step 3410, the host computer provides the user data by executing a host application. In a second step 3420, the host computer initiates a transmission carrying the user data to the UE. In an optional third step 3430, the base station transmits to the UE the user data which was carried in the transmission that the host computer initiated, in accordance with the teachings of the embodiments described throughout this disclosure. In an optional fourth step 3440, the UE executes a client application associated with the host application executed by the host computer.

[0488] Figure 22 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment. The communication system includes a host computer, a base station such as an AP STA, and a UE such as a Non-AP STA which may be those described with reference to Figure 19 and Figure 20. For simplicity of the present disclosure, only drawing references to Figure 22 will be included in this section. In a first step 3510 of the method, the host computer provides user data. In an optional sub step (not shown) the host computer provides the user data by executing a host application. In a second step 3520, the host computer initiates a transmission carrying the user data to the UE. The transmission may pass via the base station, in accordance with the teachings of the embodiments described throughout this disclosure. In an optional third step 3530, the UE receives the user data carried in the transmission.

[0489] Figure 23 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment. The communication system includes a host computer, a base station such as an AP STA, and a UE such as a Non-AP STA which may be those described with reference to Figure 19 and Figure 20. For simplicity of the present disclosure, only drawing references to Figure 23 will be included in this section. In an optional first step 3610 of the method, the UE receives input data provided by the host computer. Additionally or alternatively, in an optional second step 3620, the UE provides user data. In an optional sub step 3621 of the second step 3620, the UE provides the user data by executing a client application. In a further optional sub step 3611 of the first step 3610, the UE executes a client application which provides the user data in reaction to the received input data provided by the host computer. In providing the user data, the executed client application may further consider user input received from the user. Regardless of the specific manner in which the user data was provided, the UE initiates, in an optional third sub step 3630, transmission of the user data to the host computer. In a fourth step 3640 of the method, the host computer receives the user data transmitted from the UE, in accordance with the teachings of the embodiments described throughout this disclosure.

[0490] Figure 24 is a flowchart illustrating a method implemented in a communication system, in accordance with one embodiment. The communication system includes a host computer, a base station such as an AP STA, and a UE such as a Non-AP STA which may be those described with reference to Figure 19 and Figure 20. For simplicity of the present disclosure, only drawing references to Figure 24 will be included in this section. In an optional first step 3710 of the method, in accordance with the teachings of the embodiments described throughout this disclosure, the base station receives user data from the UE. In an optional second step 3720, the base station initiates transmission of the received user data to the host computer. In a third step 3730, the host computer receives the user data carried in the transmission initiated by the base station. When using the word "comprise" or “comprising” it shall be interpreted as nonlimiting, i.e. meaning "consist at least of".

[0491] The embodiments herein are not limited to the above described preferred embodiments. Various alternatives, modifications and equivalents may be used.

Claims

CLAIMS A method performed by a User Equipment, UE, (120) for initiating a procedure for transitioning the UE (120) from a power saving mode of operation to a connected mode of operation in a wireless communications network (100), the method comprising: performing (703) one or more predictions of data volume in a protocol buffer, wherein the data volume is predicted to be transmitted between the UE (120) and a Radio Access Network, RAN, node (110) in an upcoming data transmission, before data of the upcoming data transmission arrives in the protocol buffer, initiating (704) the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer, and, sending (705) to a RAN node (110), a request for the transitioning to the connected mode of operation. The method according to claim 1 , wherein the request for the transitioning to the connected mode of operation, further indicates that the UE (120) has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer. The method according to any of the claims 1-2, further comprising: obtaining (701) one or more configurations for controlling the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer. The method according to any of the claims 1-3, further comprising: sending (706) a message to the RAN node (110), which message indicates any one or more out of:- data based on or related to the one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected,- data associated to any error of the one or more predictions of data volume in the protocol buffer. The method according to any of the claims 1-4, further comprising: at starting communicating (707) the data related to the one or more predictions of the data volume in the protocol buffer, starting (708) an inactivity timer, which when expires initiates a transitioning of the UE (120) from a connected mode of operation to a power saving mode of operation. The method according to any of the claims 1-5, further comprising: obtaining (702) a model for the one or more predictions, and wherein the model is obtained by any one out of:- training the model in the UE (120), or- receiving the model from a RAN node (110), and wherein the performing (703) of the one or more predictions of data volume in the protocol buffer is based on the model. The method according to any of the claims 1-6, wherein the one or more configurations comprise one or more parameters related to any one or more out of:- the performing of the one or more predictions of the data volume in the protocol buffer,- the initiating of the procedure for transitioning to the connected mode of operation.- one or more location information where to perform the one or more predictions of data volume in the protocol buffer,- one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,- one or more location information where the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,- a value for a first timer, indicating for how long time the UE (120) shall perform the one or more predictions of data volume in the protocol buffer,- a value for a second timer, indicating for how long time the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation,- a value for a third timer, indicating for how long time the UE (120) is not required to perform the one or more predictions of the data volume in the protocol buffer, or for how long time the UE (120) shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more bearers the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and- one or more indications of one or more Over The Top, OTT, services the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more applications the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and- one or more parameters associated to the data volume to be predicted. A computer program comprising instructions, which when executed by a processor, causes the processor to perform actions according to any of the claims 1-7. A carrier comprising the computer program of claim 8, wherein the carrier is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium. A method performed by a Radio Access Network, RAN, node (110) for handling a User Equipment, UE, (120) initiated procedure for transitioning the UE (120) from a power saving mode of operation to a connected mode of operation in a wireless communications network (100), the method comprising:- before data of an upcoming data transmission arrives in a protocol buffer of the UE (120), receiving (803) a request from the UE (120), which request relates to a UE initiated procedure for transitioning to the connected mode of operation based on one or more predictions of the data volume in the protocol buffer, wherein the data volume is predicted to be transmitted between the UE (120) and the RAN node (110) in the upcoming data transmission, deciding (804) whether or not to transitioning to connected mode of operation based on the received request, and sending (805) to the UE (120), a message indicating the outcome of the deciding of whether or not to transitioning to connected mode of operation.

11. The method according to claims 10, further comprising: sending (801) to the UE (120), one or more configurations configuring the UE (120) to:- perform one or more predictions of data volume in a protocol buffer, wherein the data volume is to be predicted to be transmitted between the UE (120) and a Radio Access Network, RAN, node (110) in an upcoming data transmission, and- before data of the upcoming data transmission arrives in the protocol buffer, initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer.

12. The method according to any of the claims 10-11 , wherein the request for the transitioning to the connected mode of operation, further indicates that the UE (120) has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer, and wherein the deciding (804) of whether or not to transitioning the UE (120) to connected mode of operation based on the received request, is further based on the indication.

13. The method according to any of the claims 10-12, further comprising: receiving (806) a message from the UE (120), which message indicates any one or more out of:- data based on or related to the one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected,- data associated to any error of the one or more predictions of data volume in the protocol buffer.

14. The method according to any of the claims 10-13, wherein the one or more configurations further configure the UE (120) to:- at starting communicating the data related to the one or more predictions of the data volume in the protocol buffer, start an inactivity timer, which when expiresinitiates a transitioning of the UE (120) from a connected mode of operation to a power saving mode of operation. The method according to any of the claims 10-14, further comprising: sending (802) to the UE (120), a model for the one or more predictions, and wherein: the one or more configurations further configure the UE (120) to perform the one or more predictions of data volume in the protocol buffer based on the model. The method according to any of the claims 10-15, wherein the one or more configurations comprise one or more parameters related to any one or more out of:- the performing of the one or more predictions of the data volume in the protocol buffer,- the initiating of the procedure for transitioning to the connected mode of operation.- one or more location information where to perform the one or more predictions of data volume in the protocol buffer,- one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,- one or more location information where the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,- a value for a first timer, indicating for how long time the UE (120) shall perform the one or more predictions of data volume in the protocol buffer,- a value for a second timer, indicating for how long time the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation,- a value for a third timer, indicating for how long time the UE (120) is not required to perform the one or more predictions of the data volume in the protocol buffer, or for how long time the UE (120) shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more bearers the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and- one or more indications of one or more Over The Top, OTT, services the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more applications the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and- one or more parameters associated to the data volume to be predicted.

17. A computer program comprising instructions, which when executed by a processor, causes the processor to perform actions according to any of the claims 10-16.

18. A carrier comprising the computer program of claim 17, wherein the carrier is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium.

9. A User Equipment, UE, (120) configured to initiate a procedure for transitioning the UE (120) from a power saving mode of operation to a connected mode of operation in a wireless communications network (100), the UE (120) further being configured to:- perform one or more predictions of data volume in a protocol buffer, wherein the data volume is adapted to be predicted for being transmitted between the UE (120) and a Radio Access Network, RAN, node (110) in an upcoming data transmission,- before data of the upcoming data transmission arrives in the protocol buffer, initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer, and,- send to a RAN node (110), a request for the transitioning to the connected mode of operation.

20. The UE (120) according to claim 19, wherein the request for the transitioning to the connected mode of operation, further is adapted to indicate that the UE (120) has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer.

21. The UE (120) according to any of the claims 19-20, further being configured to: obtain one or more configurations for controlling the procedure for transitioning to the connected mode of operation based on one or more predictions of data volume in the protocol buffer.

22. The UE (120) according to any of the claims 19-21, further being configured to: send a message to the RAN node (110), which message is adapted to indicate any one or more out of:- data based on or related to the one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected,- data associated to any error of the one or more predictions of data volume in the protocol buffer.

23. The UE (120) according to any of the claims 19-22, further being configured to: at starting to communicate the data related to the one or more predictions of the data volume in the protocol buffer, start an inactivity timer, which when expires initiates a transitioning of the UE (120) from a connected mode of operation to a power saving mode of operation.

24. The UE (120) according to any of the claims 19-23 further being configured to: obtain a model for the one or more predictions, and wherein the model is obtained by any one out of:- training the model in the UE (120), or- receiving the model from a RAN node (110), and wherein the UE (120) further is configured to perform the one or more predictions of data volume in the protocol buffer based on the model.

25. The UE (120) according to any of the claims 19-24 wherein the one or more configurations are adapted to comprise one or more parameters related to any one or more out of:- the performing of the one or more predictions of the data volume in the protocol buffer,- the initiating of the procedure for transitioning to the connected mode of operation.- one or more location information where to perform the one or more predictions of data volume in the protocol buffer,- one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,- one or more location information where the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,- a value for a first timer, indicating for how long time the UE (120) shall perform the one or more predictions of data volume in the protocol buffer,- a value for a second timer, indicating for how long time the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation,- a value for a third timer, indicating for how long time the UE (120) is not required to perform the one or more predictions of the data volume in the protocol buffer, or for how long time the UE (120) shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more bearers the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and- one or more indications of one or more Over The Top, OTT, services the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more applications the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and- one or more parameters associated to the data volume to be predicted. A Radio Access Network, RAN, node (110) configured to handle a User Equipment, UE, (120) initiated procedure for transitioning the UE (120) from a power saving mode of operation to a connected mode of operation in a wireless communications network (100), the RAN node (110) further being configured to:- before data of an upcoming data transmission arrives in a protocol buffer of the UE (120), receive a request from the UE (120), which request is adapted to relate to a UE initiated procedure for transitioning to the connected mode of operation based on one or more predictions of the data volume in the protocol buffer, wherein the data volume is adapted to be predicted for being transmitted between the UE (120) and the RAN node (110) in the upcoming data transmission,- decide whether or not to transitioning to connected mode of operation based on the received request, and- send to the UE (120), a message indicating the outcome of the deciding of whether or not to transitioning to connected mode of operation.

27. The RAN node (110) according to claims 26, further being configured to: send to the UE (120), one or more configurations configuring the UE (120) to:- perform one or more predictions of data volume in a protocol buffer, wherein the data volume is to be predicted to be transmitted between the UE (120) and a Radio Access Network, RAN, node (110) in an upcoming data transmission, and- before data of the upcoming data transmission arrives in the protocol buffer, initiate the procedure for transitioning to the connected mode of operation based on the one or more predictions of the data volume in the protocol buffer.

28. The RAN node (110) according to any of the claims 26-27, wherein the request for the transitioning to the connected mode of operation, further is adapted to indicate that the UE (120) has initiated the procedure for transitioning to the connected mode based on one or more predictions of data volume in the protocol buffer, and wherein the RAN node (110) further being configured to decide whether or not to transitioning the UE (120) to connected mode of operation based on the received request, based on the indication.

29. The RAN node (110) according to any of the claims 26-28, further being configured to: receive a message from the UE (120), which message is adapted to indicate any one or more out of:- data based on or related to the one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of the respective one or more predictions of the data volume in the protocol buffer,- data related to the accuracy of one or more predictions for a time interval at which data related to the data volume in the protocol buffer is expected,- data associated to any error of the one or more predictions of data volume in the protocol buffer.

30. The RAN node (110) according to any of the claims 26-29, wherein the one or more configurations further are adapted to configure the UE (120) to:- at starting communicating the data related to the one or more predictions of the data volume in the protocol buffer, start an inactivity timer, which when expires initiates a transitioning of the UE (120) from a connected mode of operation to a power saving mode of operation.

31. The RAN node (110) according to any of the claims 26-30, further being configured to: send to the UE (120), a model for the one or more predictions, and wherein: the one or more configurations further are adapted to configure the UE (120) to perform the one or more predictions of data volume in the protocol buffer based on the model.

32. The RAN node (110) according to any of the claims 26-31, wherein the one or more configurations are adapted to comprise one or more parameters related to any one or more out of:- the performing of the one or more predictions of the data volume in the protocol buffer,- the initiating of the procedure for transitioning to the connected mode of operation.- one or more location information where to perform the one or more predictions of data volume in the protocol buffer,- one or more location information where to NOT perform the one or more predictions of data volume in the protocol buffer,- one or more location information where the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation based on one or more predictions of data volume in the protocol buffer,- a value for a first timer, indicating for how long time the UE (120) shall perform the one or more predictions of data volume in the protocol buffer,- a value for a second timer, indicating for how long time the UE (120) is allowed to trigger the initiation of a transitioning to a connected mode of operation,- a value for a third timer, indicating for how long time the UE (120) is not required to perform the one or more predictions of the data volume in the protocolbuffer, or for how long time the UE (120) shall wait until it starts performing the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more bearers the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and - one or more indications of one or more Over The Top, OTT, services the UE(120) shall consider for the one or more predictions of data volume in the protocol buffer,- one or more indications of one or more applications the UE (120) shall consider for the one or more predictions of data volume in the protocol buffer, and - one or more parameters associated to the data volume to be predicted.

Images