Method and node for performing network configuration across a plurality of cells in a communications network

Abstract

The present disclosure relates to a computer implemented method performed by a node (101, 703) for performing network configuration across a plurality of cells (103a, 103b) in a communications network (100). The plurality of cells (103a,103b) comprises at least a first cell (103a) and at least a second cell (103b). The node (101, 703) obtains input data. The input data comprises at least one PM parameter. The node (101, 703) predicts a future load contribution caused by at least one UE (105) in the first cell (103a) that is directed from the second cell (103b). The prediction is done based on the input data and performed using a machine learning algorithm. The node (101, 703) performs network configuration based on the predicted future load contribution.

Description

[0001] METHOD AND NODE FOR PERFORMING NETWORK CONFIGURATION ACROSS A PLURALITY OF CELLS IN A COMMUNICATIONS NETWORK

[0002] TECHNICAL FIELD

[0003] The present disclosure relates generally to a node, a computer implemented method performed by the node, a computer program product and a non-transitory computer-readable storage medium. More particularly, the present disclosure relates to performing network configuration across a plurality of cells in a communications network.

[0004] BACKGROUND

[0005] The rapid increase in mobile data traffic, fuelled by the widespread adoption of smartphones and tablets, presents significant challenges for network operators. These challenges include the necessity to efficiently manage finite radio resources to meet the growing demand. Mobile data usage patterns are dynamic, leading to time-varying and unbalanced network loads, where some cells, e.g. victim cells, suffer from congestion while adjacent cells remain underutilized. Traditional load balancing techniques, such as manual configurations and antenna adjustments, are typically reactive, time-consuming, and insufficient for addressing these dynamic changes.

[0006] Recently, Radio Access Network Applications (rApp), Service Management and Orchestration (SMO), and smart cloud management systems, offer a new approach for managing network traffic. SMO refers to a holistic approach that integrates service management with the orchestration of network functions, enabling seamless coordination and automation of network operations. These advanced systems offer the possibility for Machine Learning (ML) to foresee and manage cell traffic proactively. The system determines Key Performance Indicators (KPIs) for multiple cells and employs these KPIs to predict trends and identify potential network issues before they materialize. This proactive approach enables pre-emptive actions to redistribute traffic and optimize network performance.

[0007] The framework within which these technologies operate is known as Self-Organizing Networks (SON), which were introduced to automate network parameter tuning based on real-time measurements. However, existing SON algorithms and load managementtechniques are often reactive or occur in real-time, which detrimentally impacts performance due to persistent issues like network congestion and data staleness.

[0008] By integrating rApps and SMO with smart cloud management, the system not only predicts but also orchestrates a seamless and efficient distribution of network traffic across cells. These advanced technologies work in tandem to create a more robust and responsive network environment, ensuring optimal performance even in the face of fluctuating and unpredictable mobile data usage. This represents a significant evolution in network management, transforming reactive measures into proactive solutions.

[0009] There currently exist certain challenge(s):

[0010] - Questionable suitability for intricacies of Non-Standalone (NSA) architecture in Fifth Generation (5G) new radio (NR) deployment

[0011] Lack of use of external data sources for KPI prediction

[0012] Non-standalone architecture in 5G New Radio deployment

[0013] The primary approach for deploying 5G networks today is through the NSA architecture, which integrates 5G NR cells, e.g. evolved Node B (eNB), with existing Long Term Evolution (LTE) cells, e.g. g Node B (gNB), and infrastructure. This method leverages LTE nodes for control functions while utilizing 5G capabilities for enhanced data performance. However, this shared infrastructure introduces complexities in node analysis, prediction, and load balancing.

[0014] The interaction between 5G NR cells and LTE cells within the same nodes complicates performance optimization, resource allocation, and interference management. Analysts and network operators face the challenge of understanding and managing dynamics such as dual-connectivity connections, e.g., E-UTRAN - Dual Connectivity (EN-DC), New Radio-Dual Connectivity (NR-DC) etc., to ensure seamless handovers and efficient network operation. E-UTRAN is short for Evolved Universal Terrestrial Radio Access Network. Advanced techniques are required to accurately predict and mitigate potential issues arising from the coexistence of 5G NR and LTE technologies, e.g., EN-DC, within shared nodes.

[0015] In NSA 5G deployments, load balancing is used for making sure that user devices such as User Equipments (UE) are fairly distributed among the 5G NR cells connected to a Fourth Generation (4G) LTE cell. The goal is to ensure that no single NR cell isoverloaded while others are underused, which helps maintain good performance, e.g. more throughput per cell, and efficient use of the available network resources, e.g. balancing the users across 5G cells based on cell capabilities.

[0016] To achieve this, the network would need to monitor the load on each NR cell and distributes new UEs and move existing UEs as needed to keep the load balanced. This process also takes into account the differences in bandwidth among the NR cells, since some cells might have more capacity than others. By considering these bandwidth differences, the network can make smarter decisions about where to move UEs, ensuring an even and efficient distribution of the UEs.

[0017] There currently exist certain challenge(s):

[0018] - Challenges in predicting the distribution of UEs among shared resources, such as 5G NR cells, as well as their throughput or other load metric, make node balancing difficult.

[0019] Data staleness due to interface and processing delay in reporting data from gNB / eNB reaching rApp.

[0020] These challenges will now be described in more detail.

[0021] Predicting the distribution and throughput of UEs among shared resources

[0022] As the UEs are orchestrated by LTE cells, each LTE cell needs to distribute the users among the NR cells 103 it has available to perform load balancing. Fig. 1 illustrates such an example where LTE cell #x has three NR cells it can utilize. Note that one of them, NR Cell #C, is shared with LTE cell #y.

[0023] The percentages shown in fig. 1 the fraction of UEs 105 that attempted to connect to that NR cell 103_NR from the respective LTE cell 103_LTE. In fig. 1, the UEs 105 are illustrated with the users using the UE 105. For each NR cell 103_NR the number of connected UEs 105 is known, unfortunately the load e.g., throughput, delay, of those UEs 105 to the LTE cell 103_LTE is not known which makes it difficult to estimate what the effect of the redistribution of the UEs 105 will be and / or how effective it will be on the load.

[0024] Data staleness due to delay in reporting data from gNB / eNB reaching rAppCurrently, an rAPP using Performance Monitoring (PM) counters are limited to use a per Report on period (ROP) every 15 minutes. However, the data has to be processed and is not available ~20-40 minutes after it has been collected in the ROP period in the access node, e.g. gNB, eNB. The total effect of these delays is that the rAPP would base it’s load balancing calculations on data that is 45min or up to 1 hour old.

[0025] Fig. 2 is a schematic drawing illustrating an example of root cause for data staleness in rAPP. The x-axis of fig. 2 represents time. Fig. 2 shows four horizontal lines, and they represent the following, starting with the line closest to the x-axis and moving upwards: gNB / eNB, network manager, controller and rAPP.

[0026] rAPP is a software application arranged to perform network optimization and orchestration tasks in Non-Real Time RAN Intelligent Controller (Non-RT RIC). Non-real time may be longer than 1 second. The rAPP may be used for example for access network energy savings, traffic steering, policy management etc.

[0027] Therefore, there is a need to at least mitigate or solve this issue, and to improve network configuration in a communications network.

[0028] SUMMARY

[0029] An objective is to obviate at least one of the above disadvantages and to provide improved network configuration across a plurality of cells in a communications network.

[0030] According to a first aspect, the objective is achieved by a computer implemented method performed by a node for performing network configuration across a plurality of cells in a communications network. The plurality of cells comprises at least one first cell and at least one second cell. The node obtains input data. The input data comprises at least one PM parameter. The node predicts a future load contribution caused by at least one UE in a first cell that is directed from a second cell. The prediction is done based on the input data and performed using a machine learning algorithm. The node performs network configuration based on the predicted future load contribution.

[0031] According to a second aspect, the objective is achieved by a node for performing network configuration across a plurality of cells in a communications network. The plurality of cells comprises at least one first cell and at least one second cell. The node is configured toobtain input data. The input data comprises at least one PM parameter. The node is configured to predict a future load contribution caused by at least one UE in a first cell that is directed from a second cell. The prediction is done based on the input data and performed using a machine learning algorithm. The node is configured to perform network configuration based on the predicted future load contribution.

[0032] According to a third aspect, the objective is achieved by a computer program product comprising program code for performing, when executed by the processing circuitry, the method of the first aspect.

[0033] According to a fourth aspect, the objective is achieved by a non-transitory computer-readable storage medium comprising instructions, which when executed by the processing circuitry, cause the processing circuitry to perform the method of the first aspect.

[0034] Since the predicted future load contribution is done based on the input data and performed using a machine learning algorithm, network configuration may be performed in advance to handle anticipated traffic, thus minimizing the delay in data gathering from various network elements. As a result of this, real-time, optimized configurations are enabled, leading to improved overall network utilization and performance. Thus, network configuration across a plurality of cells in a communications network is improved.

[0035] Th embodiments herein afford many advantages, of which a non-exhaustive list of examples follows:

[0036] An advantage of the present disclosure is that, by leveraging this predictive capability, network nodes can be pre-configured in advance to handle anticipated traffic, thus minimizing the delay in data gathering from various network elements.

[0037] Another advantage of the present disclosure is that it enables real-time, optimized configurations, leading to improved overall network utilization, spectral efficiency and performance.

[0038] A further advantage of the present disclosure is that it mitigates the delay in live data retrieval from nodes, as illustrated in fig. 2.Another advantage of the present disclosure is that it provides improved performance due to inclusion of informative external data sources.

[0039] Yet another advantage of the present disclosure is that the predicting to counteract staleness is a key to enable a cloud solution.

[0040] Furthermore, the present disclosure which is a transformer based artificial neural network architecture has even the following advantages:

[0041] • In context learning allows for robust inclusion / exclusion of other timeseries.

[0042] • Similarly, in context learning allows for flexibility in utilization of neighbouring nodes PM counters for improved accuracy.

[0043] The present disclosure is not limited to the features and advantages mentioned above. A person skilled in the art will recognize additional features and advantages upon reading the following detailed description.

[0044] BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0046] The present disclosure will now be described in more detail by way of example only in the following detailed description by reference to the appended drawings in which:

[0047] Fig. 1 is a schematic drawing illustrating an NSA 5G example.

[0048] Fig. 2 is a schematic drawing illustrating data staleness in rAPP.

[0049] Fig. 3 is a schematic diagram illustrating a communications network.

[0050] Fig. 4 is a schematic diagram illustrating a transformer model including inputs of historical data and output predictions for several time steps.

[0051] Fig. 5 is a schematic diagram illustrating a method.

[0052] Fig. 6 is a signalling diagram illustrating a method.

[0053] Fig. 7 is a flow chart illustrating a method.

[0054] Fig. 8 is a schematic block diagram illustrating a node.

[0055] Fig. 9 is an example of a communications network.Fig. 10 is an example of a communications network.

[0056] Fig. 11 shows a wireless device.

[0057] Fig. 12 shows a network node.

[0058] Fig. 13 is a block diagram illustrating a virtualization environment.

[0059] The drawings are not necessarily to scale and the dimensions of certain features may have been exaggerated for the sake of clarity. Emphasis is instead placed upon illustrating the principle of the embodiments herein.

[0060] DETAILED DESCRIPTION

[0061] There are numerous known node analysis and prediction methods, but their relevance is severely limited as they consider curated open-source data sets which do not take into account the true Performance Monitoring (PM) and Configuration Monitoring (CM) counters. Furthermore, many pertinent external data sources are often overlooked in current methods. Another shortcoming of the current methods is that, in real deployment scenarios, the availability and reliability of external data sources, such as those served via external Application Program Interfaces (API), are always going to be imperfect.

[0062] Therefore, any solution that incorporates such sources must be able to adapt to their occasional absence.

[0063] Some examples of such external data sources comprise:

[0064] ■ Train, airplane, and bus schedules

[0065] ■ Sporting events and concerts

[0066] ■ Weather conditions

[0067] ■ Social media activity

[0068] ■ Weekdays, Public holidays and festivals

[0069] ■ T raffic patterns

[0070] Incorporating these external data into the prediction models can radically alter the problem space, allowing for a significant improvement in performance. It is noteworthy that external data sources, such as those listed above, are not used in current methods.

[0071] Furthermore, current methods employ machine learning clustering methods that do not account for the correct dependence structure between the cells including the NSA deployment as described above. This limitation of the current methods affects theirperformance and introduces unwanted variability when deployed at a massive scale. Current methods address a specific KPI prediction on various timescales but misses the intricacies possible to exploit for the shorter time horizon prediction problem required for the load balancing applications, as in the present disclosure. Furthermore, the estimation or prediction of the number of connected UEs 105 that are related to a given LTE cell is not a KPI prediction problem. The current methods need about 20 models for 100K base stations, they cluster based on KPIs / PM counters and geographic area, they detect a victim cell from a plurality of cells, found via clustering, and they use a weighted sum of features from the neighbors’ concatenated with the features of the cell in question.

[0072] Therefore, there is a need to at least mitigate or solve this issue, and to improve network configuration in a communications network.

[0073] The present disclosure is an enhanced approach to optimize network configurations in multi-vendor Open Radio Access Network (RAN) environments. The present disclosure reduces delays in load balancing reconfigurations and proactively triggers rebalancing when changes are predicted in the loads of the cells.

[0074] The present disclosure addresses at least the following challenges which has been mentioned above:

[0075] • estimate the load contribution of UEs from each LTE cell based on prediction via machine learning methods.

[0076] • reduce the data staleness problem using machine learning based prediction.

[0077] Additionally, the present disclosure provides a transformer-based machine learning architecture, where it is possible to, in context learning, to fully take advantage of various external data sources. The transformer-based machine learning algorithm includes an attention mechanism that enables the transformer-based machine learning algorithm to dynamically assign weights to different external data

[0078] To achieve this, the present disclosure utilizes machine learning algorithms, such as supervised learning or reinforcement learning, to forecast load on different frequencies using historical data. By leveraging this predictive capability, network nodes may be preconfigured in advance to handle anticipated traffic, thus minimizing the delay in data gathering from various network elements. External data sources are used, and theproportion of UEs in an NR cell that are from a specific LTE cell is estimated or predicted. The present disclosure thereby enables real-time, optimized configurations, leading to improved overall network utilization and performance.

[0079] Fig. 3 depicts a non-limiting example of a communications network 100, which may be a wireless communications network, sometimes also referred to as a wireless communications system, cellular radio system, or cellular network, in which the present disclosure may be implemented. The communications network 100 may be a 5G system, 5G network, NR-U or Next Gen system or network. The communications network 100 may alternatively be a younger system or older system than a 5G system, such as e.g. a 2G system, a 3G system, a 4G system, a 6G system a 7G system etc. The communications network 100 may support other technologies such as, for example, Long-Term Evolution (LTE), LTE-Advanced / LTE-Advanced Pro, e.g. LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), LTE Half-Duplex Frequency Division Duplex (HD-FDD), LTE operating in an unlicensed band, NB-loT. Thus, although terminology from 5G / NR and LTE may be used in this disclosure to exemplify, this should not be seen as limiting to only the aforementioned systems.

[0080] The communications network 100 comprises one or a plurality of network nodes, whereof a first network node 101a and a second network node 101b are depicted in the nonlimiting example of fig. 1. Any of the first network node 101a, and the second network node 101b may be a radio network node, such as a radio base station, or any other network node with similar features capable of serving a user equipment, such as a wireless device or a machine type communication device, in the communications network 100. The first network node 101a may be an eNB and the second network node 101b may be a gNB. The first network node 101a may be a first eNB, and the second network node 101b may be a second eNB. The first network node 101a may be a first gNB, and the second network node 101b may be a second gNB. The first network node 101a may be a MeNB and the second network node 101b may be a gNB. Any of the first network node 101a and the second network node 101b may be co-localized, or they may be part of the same network node. The first network node 101a may be referred to as a source node or source network node, whereas the second network node 101b may be referred to as a target node or target network node. When the reference number 101 is used herein without the letters a or b, it refers to a network node in general, i.e. it refers to any of the first network node 101a or second network node 101b.The communications network 100 covers a geographical area which may be divided into cell areas, wherein each cell area may be served by a network node, although, one network node may serve one or several cells. In fig. 1 , the communications network 100 comprises a first cell 103a and a second cell 103b. Note that two cells are exemplified in fig. 3 only as an example, and that any n number of cells may be comprised in the communication network 100, where n is any positive integer. A cell is a geographical area where radio coverage is provided by the network node at a network node site. Each cell is identified by an identity within the local network node area, which is broadcast in the cell. In fig. 3, first network node 101a serves the first cell 103a, and the second network node 101b serves the second cell 103b. Any of the first network node 101a and the second network node 101b may be of different classes, such as, e.g., macro base station (BS), home BS or pico BS, based on transmission power and thereby also cell size. Any of the first network node 101a and the second network node 101b may be directly connected to one or more core networks, which are not depicted in fig. 3 for the sake of simplicity. Any of the first network node 101a and the second network node 101 n may be a distributed node, such as a virtual node in the cloud, and it may perform its functions entirely on the cloud, or partially, in collaboration with another network node. The first cell 103a may be referred to as a source cell, whereas the second cell 103b may be referred to as a target cell. When the reference number 103 is used herein without the letters a or b, it refers to a cell in general, i.e. it refers to any of the first cell 103a or second cell 103b.

[0081] One or a plurality of UEs 105 is comprised in the communication network 100. Only one UE 105 is exemplified in fig. 3 for the sake of simplicity. A UE 105 may also be referred to simply as a device. The UE 105, e.g. an LTE UE or a 5G / NR UE, may be a wireless communication device which may also be known as e.g., a wireless device, a mobile terminal, wireless terminal and / or mobile station, a mobile telephone, cellular telephone, or laptop with wireless capability, just to mention some examples. The UE 105 may be a device by which a subscriber may access services offered by an operator’s network and services outside operator’s network to which the operator’s radio access network and core network provide access, e.g. access to the Internet. The UE 105 may be any device, mobile or stationary, enabled to communicate over a radio channel in the communications network 100, for instance but not limited to e.g. UE, mobile phone, smart phone, sensors, meters, vehicles, household appliances, medical appliances, media players, cameras, Machine to Machine (M2M) device, Internet of Things (IOT) device, terminal device,communication device or any type of consumer electronic, for instance but not limited to television, radio, lighting arrangements, tablet computer, laptop or Personal Computer (PC). The UE 105 may be portable, pocket storable, hand held, computer comprised, or vehicle mounted devices, enabled to communicate voice and / or data, via the radio access network, with another entity, such as another UE, a server, a laptop, a Personal Digital Assistant (PDA), or a tablet, Machine-to-Machine (M2M) device, device equipped with a wireless interface, such as a printer or a file storage device, modem, or any other radio network unit capable of communicating over a radio link in the communications network 100.

[0082] The UE 105 is enabled to communicate wirelessly within the communications network 100. The communication may be performed e.g. between two UEs 105, between a UE 105 and a regular telephone, between the UE 105 and a network node, between network nodes, and / or between the UE 105 and a server via the radio access network and possibly one or more core networks and possibly the internet.

[0083] The first network node 101a may be configured to communicate in the communications network 100 with the UE 105 over a first communication link 108a, e.g., a radio link. The second network node 101b may be configured to communicate in the communications network 100 with the UE 105 over a second communication link 108b, e.g., a radio link. The first network node 101a may be configured to communicate in the communications network 100 with the second network node 101b over a third communication link 108c, e.g., a radio link or a wired link, although communication over more links may be possible. When the reference number 108 is used herein without the letters a, b or c, it refers to a communication link in general, i.e. it refers to any of the first communication link 108a, the second communication link 108b and the third communication link 108c.

[0084] It should be noted that the communication links 108 in the communications network 100 may be of any suitable kind comprising either a wired or wireless link. The link may use any suitable protocol depending on type and level of layer (e.g. as indicated by the Open Systems Interconnection (OSI) model) as understood by the person skilled in the art.

[0085] For the NSA deployment described above, load balancing is accomplished via update of the EN-DC distribution profile, which comprises information indicating a distribution of EN-DC-capable UEs 105 between NR carrier frequencies that are selected based on configured parameters. This will configure the UEs 105 connected to the LTE cell 103 in a prioritized order for Measuring and setting up the NR cells 103 (EN-DC), i.e., a prioritized order of frequencies and NR cells 103 for the UEs 105 to attempt to connect to. If no prediction capability is available, the update follows the following steps:

[0086] 1. Initial EN-DC distribution profile

[0087] 2. Wait until next ROP

[0088] 3. Read ROP data, e.g. pmCounters

[0089] 4. Calculate load distribution

[0090] 5. Calculate adjustment to the EN-DC distribution profile to achieve improved load balance.

[0091] Step 5 may be performed with known business logic, or, if data collection was possible in a deployed system, even with reinforcement learning.

[0092] As described above, this would imply that a sudden change in the load distribution would not be fixed via the steps 1-5 above until ~40 minutes have passed, during which time there may be significant congestion in the communications network 100.

[0093] In general a load balancing calculation may require at least one of the following inputs:

[0094] ■ Capacity Metric:

[0095] o The capacity metric comprises information indicating cell capacity or bandwidth (BW), e.g. configuration in the communications network 100.

[0096] • Load metric

[0097] o The load metric comprises information indicating a number of UEs 105 ■ The number of UEs may be comprised in a parameter, e.g.

[0098] PmRrcConnLevelSumEnDc

[0099] o Th load metric comprises information indicating throughput in the communications network 100.

[0100] ■ The throughput may be comprised in a parameter, e.g.

[0101] pmMacVolDI

[0102] o The load metric comprises information indicating latency.

[0103] The latency may be comprised in a parameter, e.g.

[0104] pmMacLatTimeDINoDrxSyncQosIn each case, since the load distribution is performed for each LTE cell 103, a hit-Rate may be defined as the percentage of the load metric contributed by UEs 105 that come from that LTE cell 103.

[0105] Using this input, it is possible to calculate how the load caused by the UEs 105 is distributed among the NR cells 103 as well as the utilization of each frequency. This estimate may then be used to create a new EN-DC distribution profile that adjusts the distribution between frequencies to even out the load.

[0106] However, no PM parameter is available that meets the description of the Hit-Rate as described above. Instead it may be possible to use as a proxy a probability calculated based on the number of attempts made from the LTE cell 103 to connect to all NR cells 103 at the frequency in question, e.g. a parameter such as pmEndcSetupScgUeAtt. This probability may then be used as an estimate of the proportions of the connected UEs 105, e.g. a parameter such as pmRrcConnLevelSumEnDc, coming from the LTE cell 103. In general, the present disclosure may predict / estimate the hit rate as define above using at least one or a combination of PM parameters, also referred to as PM counters.

[0107] - A first counter, e.g. pmEndcSetupUeAtt:

[0108] o Purpose: This counter measures the number of attempts made to establish an EN-DC connection for a UE 105. It is a broader metric that captures all attempts to initiate dual connectivity, involving both the LTE and NR cells 103.

[0109] o Focus: It focuses on the overall initiation of the EN-DC process, encompassing all the necessary steps to set up dual connectivity for a UE 105, without specifying which part of the process is being counted.

[0110] - A second counter, e.g. pmEndcSetupScgUeAtt:

[0111] o Purpose: This counter specifically tracks the number of attempts to establish the Secondary Cell Group (SCG) for a UE 105. In EN-DC, the SCG refers to the 5G NR cells 103 that are added to the connection alongside the LTE cells 103, which form the Master Cell Group (MCG). o Focus: It is more specific than pmEndcSetupUeAtt as it focuses on the attempts to configure the 5G NR side of the dual connectivity. This involves setting up the SCG, which includes the NR cells 103 that provide additional capacity and benefits of 5G.- A third counter, e.g. pmEndcSetupUeSucc:

[0112] o Purpose: This counter measures the number of successful completions of EN-DC connection setups for UE 105. It represents instances where the entire dual connectivity process, involving both LTE and NR cells 103, has been successfully established.

[0113] o Focus: The focus of this counter is on the overall success of initiating the EN-DC process. It indicates that all necessary steps to set up dual connectivity for a UE 105 have been completed successfully, without specifying which part of the process has succeeded.

[0114] - A fourth counter, e.g. pmEndcSetupScgUeSucc:

[0115] o Purpose: This counter tracks the number of successful attempts to establish the SCG for a UE 105. In the context of EN-DC, the SCG refers specifically to the 5G NR cells 103 that are added to the connection alongside the LTE cells 103, which form the MCG.

[0116] o Focus: This counter is more specific than pmEndcSetupUeSucc, as it concentrates on the successful configuration of the 5G NR side of the dual connectivity. It indicates that the SCG, including the NR cells 103, has been successfully set up, providing the additional capacity and benefits of 5G.

[0117] The at least one PM parameter, where PM is short for performance monitoring, is a parameter indicating the monitored performance of at least a part of the communication system 100. It may be the performance of the whole communications system 100 that is monitored, or it may be a part of the communications system 100 that is monitored, for example at least one cell 103, a network node 101 etc.

[0118] Note that the above is an example of an NSA deployment, with PM parameter name “Endc”. However, similar solutions are possible for standalone “Sa” and NR-DC “NRDC”, i.e., instead of a PM parameter named pmEndcSetupScgUeSucc, it may instead be named pmsaSetupScgUeSucc and pmNRDCSetupScgUeSucc etc.

[0119] With the at least one PM parameter, it is possible to track over time the prediction / estimation of the contribution to the load from each LTE cells 103 connected to any given 5G NR cells 103.To address the issue of stale data, the PM parameters, for example a parameter indicating a number of connected UEs 105, e.g. PmRrcConnLevelSumEnDc, and a parameter indicating the number of attempts to establish the Secondary Cell Group (SCG), e.g. pmEndcSetupScgUeAtt, may be predicted and load balancing may be performed using these predicted PM parameters. To achieve this, a transformer neural network model may be trained on live network data and external data obtained from APIs. These transformer models are designed to predict the required PM counters with or without the presence of external features, ensuring robustness regardless of data availability.

[0120] For predicting the PM parameters a transformer-based machine learning algorithm may be used due to its ability to perform in-context learning. The transformer-based machine learning algorithm implements a mechanism called attention to process information. This attention mechanism allows the transformer-based machine learning algorithm to weigh the importance of different parts of the input sequence when processing each part of the output sequence. The transformer-based machine learning algorithm may be referred to as a transformer model for the sake of simplicity. Transformer models are known to be able to detect the context of a problem, such as change in traffic patterns, to make better predictions when trained with sufficiently large amounts of data. The problem of predicting these KPIs may be determined to be an in-context learning problem, as depending on the node, day, time etc. the context of the problem varies, and the prediction algorithm needs to adapt to the change in contexts by looking at a few past examples.

[0121] Fig. 4 is a schematic drawing illustrating the transformer model including inputs of historical data and output predictions for several time steps. The transformer model is fed with KPIs such as, number of connected users, throughput, physical resource block (PRB) utilization, etc, as well as with PM counters, from the past few hours to a few days as input, and it is designed to provide predictions of PM parameters for up to 4 hours into the future. The KPIs are adjustable based on desired prediction accuracy, computational capacity, and latency constraints.

[0122] The transformer model is supplied with input in the form of examples, such as questions (Q) and answers (A). The questions are all the current time KPIs used for prediction, while the answers correspond to the desired KPI values anticipated in subsequent time steps. For example, the question may be all features of a time step, and the answer may be thatthere are no active UEs for the next 4 time steps. The input data lags may be chosen based on a correlation analysis. The transformer model illustrated in fig. 4 may be used to predict any KPI or PM counters. The transformer utilizes these examples to discern the context and generate the appropriate answer to the final question.

[0123] Once deployed, the transformer model may be continually trained on the incoming new data from the network node 101, e.g. the data listed in step 501 below. The transformer model may be continually trained on the PM counters listed above.

[0124] For example, in network configuration the transformer model may be used to predict future load contributions across multiple cells. The flexibility in utilizing sources of external data for improved accuracy stems from the algorithm's attention mechanism. The attention mechanism in a transformer model allows the model to weigh the importance of different parts of input data when processing each part of the output sequence. The attention mechanism enables the transformer model to automatically assign higher weights to external data sources that are more strongly correlated with network traffic patterns.

[0125] For example, if a sporting event is scheduled to end at a specific time, the transformer model may pay more attention to this event's schedule when predicting network traffic in the vicinity of the stadium during that time. By incorporating train, airplane, and bus schedule data, the transformer model may anticipate traffic surges at transportation hubs during peak arrival and departure times. This allows network operators to proactively adjust resource allocation to accommodate the increased demand. Further, by considering sporting events, concerts, and other public gatherings, the transformer model can predict the expected increase in network traffic in specific areas and allocate resources accordingly. This ensures that network capacity is sufficient to handle the anticipated demand.

[0126] Additionally, by incorporating weather data, the transformer model can predict changes in network traffic due to adverse weather conditions, such as heavy rain or snow. This allows network operators to proactively reroute traffic or adjust network configurations to maintain service quality. The transformer model’s ability to process sequences of varying lengths allows for the inclusion or exclusion of other time series data, such as, weather data and user activity patterns in the input sequence. The attention mechanism helps thetransformer model to be robust to variations in the availability and reliability of external data sources.

[0127] Further, the attention weights can adapt overtime as network traffic patterns and dependencies between nodes evolve. This allows the transformer model to continuously refine its understanding of which external data sources are most informative for predicting the target node's future load. If some external data sources are unavailable or unreliable, the attention mechanism can automatically down weight their contributions, preventing inaccurate predictions. Thus, the attention mechanism of the transformer model acts as a dynamic weighting mechanism, allowing the transformer model to flexibly incorporate information from external data sources based on their relevance and reliability. This leads to more accurate predictions and, consequently, more effective network configurations.

[0128] Fig. 5 is a schematic drawing illustrating a method performed in the communications network 100. The method comprises at least one of the following steps, which steps may be performed in any suitable order than described below:

[0129] Step 501

[0130] External data may be obtained. The external data may comprise at least one of the following:

[0131] • Train, airplane, and bus schedule data

[0132] • Sporting events and concert data

[0133] • Weather condition data

[0134] • Social media activity data

[0135] • Weekdays, Public holidays and festivals data

[0136] • T raffic pattern data

[0137] The external data listed above may be referred to as KPIs. The external data may be realtime data or historic data.

[0138] The external data is external to the communications network 100 in that it is obtained from data sources not part of the communications network 100, for example weather database, traffic APIs etc.

[0139] Step 502The external data is provided to the ML model. Thus, the ML model is initialized. The external data may be the input to the ML model. The ML model may be based on Al.

[0140] Step 503

[0141] Live data from a network node may be input to the ML model. The live data may comprise for example a number of connected users, throughput, physical resource block (PRB) utilization, etc, as well as the PM counters. The live data may comprise the external data listed in step 501. The live data may be real time data.

[0142] Step 504

[0143] The ML model is run. The input to the ML model may be at least one of the external data from step 501 and live data from the network node in step 503. The ML model is based on Al. The ML model in step 504 is the transformer model described above and illustrated in fig. 4.

[0144] The output of the ML model may be at least one PM parameter. The at least one PM parameter may be at least one PM counter.

[0145] The at least one PM parameter may be at least one of the following:

[0146] - A first counter, e.g. pmEndcSetupUeAtt:

[0147] - A second counter, e.g. pmEndcSetupScgUeAtt:

[0148] - A third counter, e.g. pmEndcSetupUeSucc:

[0149] - A fourth counter, e.g. pmEndcSetupScgUeSucc:

[0150] The at least one PM parameter may be input to the ML model, i.e. as past and current observations, and output from the ML model, i.e. for future predictions.

[0151] Further details about the at least one PM parameter has been provided above.

[0152] Step 505

[0153] A prediction is performed. The prediction is a prediction of the proportions of connected UEs 105. Using other words, the future load contribution caused by at least one UE 105 in a first cell that is directed from a second cell is predicted. The term “directed from” refers to that the UE 105 tries to connect to the first cell 103a. The connection is an EN-DC connection. The output of the prediction in step 505 may be an EN-DC distributionprofile or information to be used to determine the EN-DC distribution profile. The output of the prediction in step 505 may be for example an energy savings configuration, a handover configuration etc.

[0154] The load is the load experienced by a node, e.g. a CN node, an access node etc., in the first cell caused by the UEs 105 connected to the node. The load may be any type of load caused by the connected UEs 105, for example traffic load, control load, signaling load, computational load, downlink and uplink data load, energy load, interference load, just to mention some examples. The prediction of the future load contribution may be necessary in order to enable load balancing between the cells in the communications network 100. In other words, the purpose is to ensure that no single cell is overloaded while others are underused, which helps maintain good performance, e.g. more throughput per cell, and efficient use of the available network resources (balancing the users across 5G cells based on cell capabilities.

[0155] Step 506

[0156] Network configuration is performed based on the prediction from step 505. For example, a network node 101 may be configured based on the prediction from step 505. The network node 101 may be a CN node or an access network node. When the network configuration is performed, load balancing in the communications network 100 is improved. Note that the configuration of the network node 101 is only an example, and that the network configuration may be any network configuration such as energy savings configuration, handover configuration etc., just to mention some examples.

[0157] Steps 507-508

[0158] Feedback from the network node 101 may be used for training the ML model. The training may be online training. The feedback may comprise information indicating a result of the configuration that was done in step 506. The feedback from the network node 101 may be observed KPIs based on the prediction outputted from the ML model and / or it may be at least one PM parameter.

[0159] Step 509

[0160] The ML model may be updated. The update may be performed if an analysis of the feedback from the network node 101 indicates that the update needs to be done. The MLmodel may be updated using information from the online training. Consequently, the next time the ML model is run it runs using the updated version.

[0161] The present disclosure may be at least partly or entirely cloud based, and some details are given below.

[0162] O-RAN Implementation

[0163] O-RAN is short for Open-Radio Access Network, and the implementation of the Non-Real Time (Non-RT) Radio Intelligent Controller (RIC) leverages R1 interfaces to enable seamless communication between rAPP and the Non-RT RIC platform. These R1 interfaces facilitate the exchange of policy, configuration, and performance data, allowing rAPPs to interact effectively with the underlying RAN infrastructure. Through the R1 interface, rAPPs can send control directives and receive network insights to optimize functions such as traffic management, energy efficiency, and overall network performance.

[0164] Fig. 6 is a signalling diagram illustrating a method performed by a node 101, 703. The node may be a core network node or an access network node. The method comprises at least one of the following steps, which steps may be performed in any suitable order than described below:

[0165] Step 710

[0166] This step corresponds to steps 501 and 502 in fig. 5. External data may be obtained by the node 101, 703. The external data may be obtained from at least one database 701.

[0167] Examples of the at least one database 701 are: CM database, PM database 610, weather database, traffic database.

[0168] As mentioned earlier, the external data may comprise at least one of:

[0169] • train, airplane, and bus schedule data;

[0170] • sporting events and concerts data;

[0171] • weather data;

[0172] • social media activity data;

[0173] • weekdays, public holidays and festival data;

[0174] • traffic pattern data.Step 711

[0175] This step corresponds to steps 501 and 502 in fig. 5. The node 101, 703 determines at least one PM parameter. Determining at least one PM parameter may be described as predicting the at least one PM parameter. The at least one PM parameter may be determined by being obtained from a database, e.g. a PM database, or the at least one PM parameter may be determined based on live data for example obtained from the network node 101. The at least one PM parameter may be determined using a ML model, e.g. the ML model 504 exemplified in fig. 5. The at least one PM parameter may be determined based on data analysis, e.g., correlation between PM counters and predicted load. The at least one PM parameter may be determined, e.g. obtained, collected, in the communications network 100. The at least one PM parameter may be available at a cell / node level and may be aggregated or collected by rApps or stored in a cloud based database.

[0176] The at least one PM parameter may be for at least one UE 105. The at least one PM parameter is for a period of time, for example the time duration of when the UE 105 connects to the second cell.

[0177] The at least on PM parameter may be at least one of the following:

[0178] • A first counter

[0179] • A second counter

[0180] • A third counter

[0181] • A fourth counter

[0182] Further details about the PM parameter are provided above.

[0183] Input data comprises the at least one PM parameter. The input data may comprise both the at least one PM parameter and the external data. The input data is the input to the prediction performed in step 712.

[0184] The at least one PM parameter may be determined using a machine learning method. The machine learning model may be in the form of a transformer neural network model trained on live network data and the input data, e.g. the external data from step 710. This transformer model is designed to predict the required PM parameters with or without the presence of external features, ensuring robustness regardless of data availability.The at least one PM parameter may be referred to as a KPI.

[0185] Step 710-711 may together be described as obtaining input data.

[0186] Step 712

[0187] This step corresponds to step 503 and 504 in fig. 5. The node 101, 703 predicts a future load contribution caused by at least one UE 105 in a first cell that is directed from a second cell. The term “directed from” refers to that the UE 105 is currently located or connected to the first cell 103a and attempts to connect to the second cell 103b. The connection is an EN-DC connection. Both the at least one PM parameter and the future load contribution are predicted using the ML model. They may be predicted using the same ML model or different ML models.

[0188] The prediction is done based on the input data and performed using a machine learning algorithm. It may be the load caused by at least one UE 105 that is predicted, e.g. the load caused by n UEs 105, where n is a positive integer. In other words, it may be one, two, three or more UEs 105 contributing to the load in the communications network 100.

[0189] As mentioned above, the input data comprises the at least one PM parameter. The input data may also comprise the external data. The input data may comprise historical data, for example historical load contributions.

[0190] The prediction may be performed using a transformer-based machine learning method, as illustrated in fig. 4. For example, the load contribution of UEs 105 from each LTE cell may be predicted using machine learning methods

[0191] Predicting the future load contribution may comprise determining a hit-rate which may described as a percentage of the load metric contributed by UEs 105 that is directed from the second cell.

[0192] The future load contribution may be predicted by calculating a probability based on the number of attempts made from the LTE cell to connect to all NR cells at the frequency in question, e.g. the second counter described above. This probability may be then used as an estimate of the proportions of the connected UEs 105 coming from the second cell.Using other words, the future load contribution, also referred to as hit rate, may be predicted or estimated using one PM parameter or a combination of two or more PM parameters.

[0193] It is possible to track over time the prediction / estimation of the contribution to the load from each second cell connected to any given first cell.

[0194] The load is the load experienced by a node, e.g. a CN node, an access node etc., in the first cell caused by the UEs 105 connected to the node. The load may be any type of load caused by the connected UEs 105, for example traffic load, control load, signaling load, computational load, energy load, interference load, just to mention some examples. The prediction of the future load contribution may be necessary in order to enable load balancing between the cells in the communications network 100. In other words, the purpose is to ensure that no single cell is overloaded while others are underused, which helps maintain good performance, e.g. more throughput per cell, and efficient use of the available network resources (balancing the users across 5G cells based on cell capabilities.

[0195] Step 713

[0196] This step corresponds to step 505 in fig. 5. The node 101, 703 performs network configuration based on the predicted future load contribution from step 712. With this, network nodes can be pre-configured in advance to handle anticipated traffic, thus minimizing the delay in data gathering from various network elements. Real-time, optimized configurations are enabled, leading to improved overall network utilization and performance. Delays in load balancing reconfigurations are reduced, and rebalancing is proactively triggered when changes are predicted in the loads of the cells.

[0197] The method described above will now be described seen from the perspective of the node 101, 703. Fig. 7 is a flowchart describing the present method performed by the node 701 for performing network configuration across a plurality of cells 103 in a communications network 100. The node 101, 703 may be a computer system comprising a processing circuity or the node 101, 703 may be comprised in a computer system comprising a processing circuitry. The plurality of cells 103 comprises at least one first cell 103 and at least one second cell 103. The node may be comprised in a core network or in an accessnetwork of the communications network 100, i.e. the node may be a core network node or an access network node.

[0198] The method comprises at least one of the following steps to be performed by the node 101, 703, which steps may be performed in any suitable order than described below:

[0199] Step 801

[0200] This step corresponds to steps 501 and 502 in fig. 5 and steps 710 and 711 in fig. 6. The node 101, 703 obtains input data. The input data comprises at least one PM parameter.

[0201] The at least PM parameter may comprise at least one of:

[0202] • a first counter indicating a number of attempts made by the UE 105 to initiate dual connectivity comprising the first cell 103a and the second cell 103b;

[0203] • a second counter indicating a number of attempts made by the UE 105 to establish a SCG for the UE 105;

[0204] • a third counter indicating a number of successful completions of the attempts made by the UE to initiate dual connectivity comprising the first cell 103a and the second cell 103b; and

[0205] • a fourth counter indicating a number of successful attempts made by the UE to establish the SCG for the UE 105.

[0206] Obtaining the input data may comprise determining the at least one PM parameter. The at least one PM parameter may be determined, e.g. predicted, using an ML model.

[0207] The input data may comprise external data. The external data may represent factors influencing the load in the communications network 100. The load may be at least one of: the current and past load contribution. The external data may comprise at least one of:

[0208] • train, airplane, and bus schedule data;

[0209] • sporting events and concerts data;

[0210] • weather data;

[0211] • social media activity data;

[0212] • weekdays, public holidays and festival data; and

[0213] • traffic pattern data.

[0214] Step 802This step corresponds to steps 503 and 504 in fig. 5 and step 712 in fig. 6. The node 101, 703 predicts a future load contribution caused by at least one UE 105 in a first cell that is directed from a second cell. The prediction is done based on the input data and performed using a machine learning algorithm.

[0215] The machine learning algorithm may be a transformer-based machine learning algorithm.

[0216] The machine learning may be is trained using the input data.

[0217] The machine learning algorithm may be trained using at least one of:

[0218] unsupervised learning,

[0219] - semi-supervised learning, and

[0220] reinforcement learning.

[0221] The first cell 103 may be a NR cell and the second cell 103 may be an LTE cell, or the first cell 103 may be an LTE cell and the second cell 103 may be an NR cell, or both the first cell and the second cell are NR cells, or both the first cell and the second cell are LTE cells.

[0222] Step 803

[0223] This step corresponds to step 505 in fig. 5 and step 713 in fig. 6. The node 101, 703 performs network configuration based on the predicted future load contribution.

[0224] The network configuration may comprise at least one of:

[0225] • load balancing,

[0226] • preconfiguring the node,

[0227] • turning on / off the node, and

[0228] • performing handover of the at least one UE 105 from a first node to a second node.

[0229] Fig. 9 is a schematic drawing illustrating the node 101, 703 for performing network configuration across a plurality of cells 103 in a communications network 100. The node may be comprised in a core network or in an access network of the communications network 100. The plurality of cells 103 comprises at least one first cell 103 and at least one second cell 103. The first cell 103 may be a NR cell and the second cell 103 may be an LTE cell, or the first cell 103 may be an LTE cell and the second cell 103 may be an NR cell, or both the first cell and the second cell are NR cells, or both the first cell and the second cell are LTE cells.The node 101, 703 may comprise processing circuitry 901 , e.g. one or more processors, configured to perform the methods herein.

[0230] The node 101, 703 and / or the processing circuitry 901 is configured to obtain input data. The input data comprises at least one PM parameter.

[0231] The at least PM parameter may comprise at least one of:

[0232] • a first counter indicating a number of attempts made by the UE 105 to initiate dual connectivity comprising the first cell and the second cell;

[0233] • a second counter indicating a number of attempts made by the UE 105 to establish a for the UE 105;

[0234] • a third counter indicating a number of successful completions of dual-connectivity connection setups for the UE 105; and

[0235] • a fourth counter indicating a number of successful attempts to establish the SCG for the UE 105.

[0236] The input data may comprise external data. The external data may represent factors influencing the load in the communications network 100.

[0237] The external data may comprise at least one of:

[0238] • train, airplane, and bus schedule data;

[0239] • sporting events and concerts data;

[0240] • weather data;

[0241] • social media activity data;

[0242] • weekdays, public holidays and festival data;

[0243] • traffic pattern data.

[0244] The node 101, 703 and / or the processing circuitry 901 is configured to predict a future load contribution caused by at least one UE 105 in a first cell that is directed from a second cell. The prediction is done based on the input data and performed using a machine learning algorithm.

[0245] The machine learning algorithm may be a transformer-based machine learning algorithm.

[0246] The machine learning algorithm is trained using the input data.The machine learning algorithm may be trained using at least one of:

[0247] • unsupervised learning,

[0248] • semi-supervised learning, and

[0249] • reinforcement learning.

[0250] The node 101, 703 and / or the processing circuitry 901 is configured to perform network configuration based on the predicted future load contribution.

[0251] The network configuration may comprise at least one of:

[0252] • load balancing,

[0253] • preconfiguring the node,

[0254] • turning on / off the node, and

[0255] • performing handover of the at least one UE 105 from a first node to a second node.

[0256] The nod 703 further comprises a memory 905. The memory 905, comprises one or more units to be used to store data on, such as indications, input data, PM parameter, future load contribution information, prediction, network configuration, external data, machine learning algorithm information, training data, cell information, measurements, thresholds, data related to nodes, and applications to perform the methods disclosed herein when being executed, and similar. Furthermore, the node 793 may comprise a communication interface 906 such as comprising a transmitter, a receiver, a transceiver and / or one or more antennas.

[0257] The methods according to the embodiments described herein for are respectively implemented using e.g., a computer program product 907 or a computer program, comprising instructions, i.e., software code portions, which, when executed on at least one processor, cause the at least one processor to carry out the actions described herein, as performed by the node 101, 703. The computer program product 907, may be stored on a computer-readable storage medium 908 e.g. a disc, a universal serial bus (USB) stick or similar. The computer-readable storage medium 908 having stored thereon the computer program product, may comprise the instructions which, when executed on at least one processor, cause the at least one processor to carry out the actions described herein, as performed by the node 101, 703. In some embodiments, the computer-readable storage medium may be a transitory or a non-transitory computer-readablestorage medium. Thus, embodiments herein may disclose a node 101, 703 for performing network configuration across a plurality of cells 103 in a communications network 100 in a wireless communication network, wherein the node 101, 703 comprises processing circuitry and a memory, the memory comprising instructions executable by the processing circuitry whereby the node 101, 703 is operative to perform any of the methods herein.

[0258] Fig. 10 shows an example of a communication system 1000 in accordance with some embodiments.

[0259] In the example, the communication system 1000 includes a telecommunications network 1002 that includes an access network 1004, such as a radio access network (RAN), and a core network 1006, which includes one or more core network nodes 1008. The access network 1004 includes one or more access network nodes or base stations of various types, access network nodes 1010A and 1010B are depicted (which may be collectively referred to as network nodes 1010), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points (APs). Some embodiments of the access network 1004 may include more than one access network technology. The network nodes 1010 of access network 1004 facilitate direct or indirect connection of wireless devices, also referred to as user equipments (UEs), such as by connecting UEs 1012A, 1012B, 1012C, and 1012D (one or more of which may be generally referred to as UEs 1012) to the core network 1006 over one or more wireless connections.

[0260] Moreover, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunications network 1002 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a network node in the telecommunications network 1002 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other network nodes to implement one or more functionalities of any network node in the telecommunications network 1002, including one or more access network nodes 1010 and / or core network nodes 1008.

[0261] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). An ORAN network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1 , F1 , W1 , E1 , E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN network node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies.

[0262] The network nodes 1010 facilitate direct or indirect connection of one or more UEs 1012 to the core network 1006 over one or more wireless connections. Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1000 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1000 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0263] The UEs 1012 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1010 and other communication devices. Similarly, the network nodes 1008, 1010 are arranged, capable, configured, and / or operable to communicate directly or indirectly (e.g., via other devices of telecommunications network 1002) with the UEs 1012 and / or with other network nodes or equipment in the telecommunications network 1002 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunications network 1002. More specifically, UEs 1012 may send messages, data, and / or other signals to networknodes 1008, 1010 or other elements of the telecommunications network 1002 by transmitting such signals to the relevant device directly without the signals passing through any intervening devices or by transmitting such signals to the relevant device indirectly through an intervening device (or multiple intervening devices) that then transmit the signal to the relevant device. Similarly, network nodes 1008, 1010 may send messages, data, and other signals to UEs 10122, other network nodes 1008, 1010, and other devices in telecommunications network 1002 directly or indirectly. As one specific example, a core network node 108 may transmit a particular message to a UE 1012 by transmitting the message to an access network node 1010 that will then transmit the message to the intended UE 1012. Similarly, a core network node 108 may receive a particular message from a UE 1012 by receiving the message from an access network node 1010 that itself received the message from the UE 1012.

[0264] In the depicted example, the core network 1006 connects elements of the access network 1004 (e.g., one or more of the network nodes 1010) to one or more host computing systems, such as host 1016. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1006 includes one or more core network nodes (e.g., core network node 1008) of various types, one or more of which may be generally referred to as network nodes 1008. Network nodes 1008 are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1008. Example core network nodes provide functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0265] The host 1016 may be under the ownership or control of a service provider other than an operator or provider of the access network 1004 and / or the telecommunications network 1002. The host 1016 may be operated by the service provider or on behalf of the service provider. The host 1016 may host a variety of applications to provide one or more service.Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server. By analysing social media activity, the transformer model can identify emerging trends and events that may impact network traffic. For example, a sudden increase in tweets about a particular location may indicate an unexpected gathering, which can be factored into network configuration decisions.

[0266] As a whole, the communication system 1000 of fig. 9 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 1000 may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (Wi-Fi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (Wi-Max), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, Li-Fi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox. Moreover, the communication system 1000 may be configured to support multiple different standards, protocols, or other rule sets, with individual components supporting all of the relevant rule sets or with different components or sub-systems within the communication system 1000 supporting different standards, protocols, or rule sets.

[0267] As one example, in certain embodiments, access network 1004 may contain some access network nodes 1010 that support 3GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 1010 support (or the same access network nodes 1010 additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, telecommunications network 1002 may support multiple generations of related communication standards (e.g., 4G and 5G 3GPP communication standards) and, as a result, may include an access network 104 and / or a core network 106 that supports multiple different standard generations or may include multiple access networks 104and / or multiple core networks 106 with individual networks 104, 106 supporting different standard generations.

[0268] Telecommunications network 1002 may support network slicing to provide different logical networks to different devices that are connected to the telecommunications network 1002. For example, the telecommunications network 1002 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC)ZMassive loT services to yet further UEs.

[0269] In some examples, one or more of the UEs 1012 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1004 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1004. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0270] In the example, the hub 1014 communicates with the access network 1004 to facilitate indirect communication between one or more UEs (e.g., UE 1012C and / or 1012D) and network nodes (e.g., network node 1010B). In some examples, the hub 1014 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1014 may be a broadband router enabling access to the core network 1006 for the UEs. As another example, the hub 1014 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 1010, or by executable code, script, process, or other instructions in the hub 1014.

[0271] As another example, the hub 1014 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1014 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 1014 may retrieve VR assets, video, audio, or other media or data related to sensoryinformation via a network node, which the hub 1014 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1014 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0272] The hub 1014 may have a constant / persistent or intermittent connection to the network node 101 OB. The hub 1014 may also allow for a different communication scheme and / or schedule between the hub 1014 and UEs (e.g., UE 1012C and / or 1012D), and between the hub 1014 and the core network 1006. In other examples, the hub 1014 is connected to the core network 1006 and / or one or more UEs via a wired connection. Moreover, the hub 1014 may be configured to connect to an M2M service provider over the access network 1004 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1010 while still connected via the hub 1014 via a wired or wireless connection. In some embodiments, the hub 1014 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1010B. In other embodiments, the hub 1014 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1010B, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0273] Fig. 10 is another example of a communication system 1100 according to some embodiments. As used herein, the communication system 1100 includes multiple access points (APs) 1110 (with four exemplary APs 1110A, 1110B, 1110C, and 1110D being depicted) and multiple wireless devices, referred to in the context of communication system 1100 as stations (ST As) 1112 (referred to individually as STA 1112A, STA 1112B, STA 1112C, STA 1112D, and STA 1112E). STA 1112A is served by AP 1110A in a first basic service set (BSS) 1120A. STA 1110B and STA 1110C are served by AP 1110B in a second BSS, BSS 1120B. STA 1112D is served by AP 1110C in a third BSS, BSS 1120C. STA 1112E is served by AP 1110D in a fourth BSS, BSS 1120D. Stations 1112 may be non-AP STAs and correspond to various kinds of wireless devices, for example, user terminals, such as mobile or stationary computing devices like smartphones, laptop computers, desktop computers, tablet computers, gaming devices, head-mounted displays (HMDs) for Augmented Reality (AR) or Virtual Reality (VR), or the like. Further, stations 1112 could, for example, correspond to other kinds of equipment like smart home devices, printers, multimedia devices, data storage devices, or the like.Each of ST As 1112 may connect through a radio link to one of APs 1110. For example, depending on location or channel conditions experienced by a given STA 1112, the STA may select an appropriate AP and BSS for establishing the radio link. The radio link may be based on one or more orthogonal frequency-division multiplexing (OFDM) carriers from a frequency spectrum that is shared on the basis of a contention-based mechanism, e.g., an unlicensed or license exempt band like 2.4 GHz Industrial, Scientific, and Medical (ISM) band, the 5 GHz band, the 6 GHz band, or the 60 GHz band.

[0274] Each AP 1110 may provide data connectivity to ST As 1112 connected to a particular AP 1110. As illustrated, APs 1110 may be connected to a data network 1130. In this way, APs 1110 may also provide data connectivity between STAs 1112 and other entities, e.g., to one or more servers, service providers, data sources, data sinks, user terminals, or the like. Accordingly, the radio link established between a given STA 1112 and its serving AP 1110 may be used for providing various kinds of services to STA 1112, e.g., a voice service, a multimedia service, or other data service. Such services may be based on applications that are executed on STA 1112 and / or on a device linked to STA 1112. By way of example, Fig. 10 illustrates an application service platform 1132 provided in data network 1130. The application(s) executed on STA 1112 and / or on one or more other devices linked to STA 1112 may use the radio link for data communication with one or more other STA 1112 and / or the application service platform 1132, thereby enabling utilization of the corresponding service(s) at STA 1112.

[0275] Fig. 11 shows a wireless device 1200, which may be configured to operate in communication system 1000 of fig. 9 or in communication system 1100 of fig. 10. The wireless device 1200 may be alternatively referred to as a UE 1200, like a UE 1012 within the context of communication system 1000, or as a station (STA) 1200 or as a non-access-point station (non-AP STA) 1200, like a STA 1112 within the context of the communication system 1100, in accordance with respective embodiments. As used herein, a wireless device refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Examples of a wireless device include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet,laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, and wireless terminal. Other examples include any type of UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0276] A wireless device 1200 may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, wireless device 1200 may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, wireless device 1200 may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, wireless device 1200 may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0277] In particular embodiments, wireless device 1200 includes processing circuitry 1202 that is operatively coupled via a bus 1204 to an input / output interface 1206, a power source 1208, a memory 1210, a communication interface 1212, and / or any other component, or any combination thereof. Certain embodiments of wireless device 1200 may include all or a subset of the components shown in fig. 11. The level of integration between the components may vary from one embodiment of wireless device 1200 to another. In general, in a particular embodiment of wireless device 1200, processing circuitry 1202, input / output interface 1206, power source 1208, memory 1210, and communication interface 1212 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of wireless device 1200. Further, certain embodiments of wireless devices 1200 may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0278] The processing circuitry 1202 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructionsstored as machine-readable computer programs in the memory 1210. The processing circuitry 1202 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 1202 may include multiple central processing units (CPUs).

[0279] In the example, the input / output interface 1206 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into wireless device 1200. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0280] In some embodiments, the power source 1208 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used to supply power to circuitry or to charge an associated battery. The power source 1208 may further include power circuitry for delivering power from the power source 1208 itself, and / or an external power source, to the various parts of wireless device 1200 via input circuitry or an interface such as an electrical power cable. Power source 1208 may perform any formatting, converting, or other modification to make accessible power suitable for the respective components of the wireless device 1200 to which power is supplied.The memory 1210 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 1210 includes one or more programs 1214, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1216. The memory 1210 may store, for use by wireless device 1200, any of a variety of various operating systems or combinations of operating systems.

[0281] The memory 1210 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or I SIM , other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1210 may allow wireless device 1200 to access instructions, programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 1210, which may be or comprise a device-readable storage medium.

[0282] The processing circuitry 1202 may be configured to communicate with an access network or other network via or using the communication interface 1212. The communication interface 1212 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1222. The communication interface 1212 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another wireless device or a network node in an access network). Each transceiver may include a transmitter 1218 and / or a receiver 1220 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover,the transmitter 1218 and receiver 1220 may be coupled to one or more antennas (e.g., antenna 1222) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0283] In the illustrated embodiment, communication functions of the communication interface 1212 may include cellular communication, Wi-Fi communication (e.g., according to an IEEE 802.11 family standard), LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as IEEE 802.11 , Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0284] In particular embodiments, wireless device 1200 may provide an output of data captured via a sensor, through its communication interface 1212, via a wireless connection to a network node, and / or in any appropriate manner. Data captured by sensors of a wireless device 1200 can be communicated through a wireless connection to a network node via another wireless device 1200. In particular embodiments, such output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0285] As another example, wireless device 1200 comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, wireless device 1200 may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.Wireless device 1200, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, wearable technology, extended industrial application and healthcare. Nonlimiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. In particular embodiments, wireless device 1200 represents an loT device that comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the example embodiment of wireless device 1200 shown in fig.

[0286] 11.

[0287] As yet another specific example, in an loT scenario, wireless device 1200 may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another wireless device and / or a network node. Wireless device 1200 may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, wireless device 1200 may implement the 3GPP NB-loT standard. In other scenarios, wireless device 1200 may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0288] In practice, any number of wireless devices 1200 may be used together with respect to a single use case. For example, a first wireless device 1200 might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second wireless device 1200 that is a remote controller operating the drone. When a user makes changes from the remote controller, the first wireless device 1200 may adjust thethrottle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second wireless device 1200 can also include more than one of the functionalities described above. For example, wireless device 1200 might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0289] Fig. 12 shows a network node 1300 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunications network. In accordance with respective embodiments, network node 1300 may be configured to operate in communication system 1000 of fig. 9, like network nodes 1008 or 1010, or in communication system 1100 of fig.

[0290] 10, like an AP 1110 or a station 1112. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0291] Network nodes 1300 may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. Network node 1300 may be a relay node or a relay donor node controlling a relay. Network nodes 1300 may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0292] Other examples of network nodes 1300 include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes,positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0293] In particular embodiments, network node 1300 includes a processing circuitry 1302, a memory 1304, a communication interface 1306, and a power source 1308. In general, in a particular embodiment of network node 1300, processing circuitry 1302, memory 1304, communication interface 1306, and power source 1308 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of network node 1300.

[0294] The network node 1300 may be composed of multiple distinct network entities (e.g., a NodeB entity and a RNC entity, or a BTS entity and a BSC entity, etc.), which may each have or utilize their own respective physical components. In certain scenarios in which the network node 1300 comprises multiple such entities (e.g., BTS and BSC), one or more of the separate entities may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 1300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories 1304 or portions of memory 1304 for different RATs) and some components may be reused (e.g., a same antenna 1310 may be shared by different RATs). The network node 1300 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1300, for example GSM, WCDMA, LTE, NR, Wi-Fi (e.g., according to an IEEE 802.11 family standard), Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 1300.

[0295] The processing circuitry 1302 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other components, such as the memory 1304, to provide network node 1300 functionality.In some embodiments, the processing circuitry 1302 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1302 includes one or more of radio frequency (RF) transceiver circuitry 1312 and baseband processing circuitry 1314. In some embodiments, the RF transceiver circuitry 1312 and the baseband processing circuitry 1314 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1312 and baseband processing circuitry 1314 may be on the same chip or set of chips, boards, or units.

[0296] The memory 1304 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), readonly memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computerexecutable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1302. The memory 1304 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 1302 and utilized by the network node 1300. The memory 1304 may be used to store any calculations made by the processing circuitry 1302 and / or any data received via the communication interface 1306. In some embodiments, the processing circuitry 1302 and memory 1304 is integrated.

[0297] The communication interface 1306 is used in wired or wireless communication of signaling and / or data with UEs, other network nodes, and / or any other network equipment. In the illustrated embodiment, communication interface 1306 comprises port(s) / terminal(s) 1316 to send and receive data, for example to and from a network over a wired connection. In particular embodiments, network node 1200 may be capable of wireless communication and communication interface 1306 may also include radio frontend circuitry 1318 that may be coupled to, or in certain embodiments a part of, an antenna 1310. Particular embodiments of radio front-end circuitry 1318 include filter(s) 1320 and amplifier(s) 1322. The radio front-end circuitry 1318 may be connected to an antenna 1310 and processing circuitry 1302. The radio front-end circuitry may be configured to condition signals communicated between antenna 1310 and processing circuitry 1302.The radio front-end circuitry 1318 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 1318 may convert the digital data into a radio signal(s) having the appropriate channel and bandwidth parameters using a combination of filters 1320 and / or amplifiers 1322. The radio signal(s) may then be transmitted via the antenna 1310. Similarly, when receiving data, the antenna 1310 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1318. The digital data may be passed to the processing circuitry 1302. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0298] In certain alternative embodiments, network node 1300 may be capable of wireless communication but does not include separate radio front-end circuitry 1318, instead, the processing circuitry 1302 includes radio front-end circuitry and is connected to the antenna 1310. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1312 is part of the communication interface 1306. In still other embodiments, the communication interface 1306 includes one or more ports or terminals 1316, the radio front-end circuitry 1318, and the RF transceiver circuitry 1312, as part of a radio unit (not shown), and the communication interface 1306 communicates with the baseband processing circuitry 1314, which is part of a digital unit (not shown).

[0299] The antenna 1310 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1310 may be coupled to the radio front-end circuitry 1318 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1310 is separate from the network node 1300 and connectable to the network node 1300 through one or more interfaces or ports.

[0300] The antenna 1310, communication interface 1306, and / or the processing circuitry 1302 may be configured to perform some or all of the receiving operations and / or obtaining operations described herein as being performed by the network node 1300. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 1310, the communication interface 1306, and / or the processing circuitry 1302 may be configured to perform some or all of the transmitting or sending operations described herein as being performed by thenetwork node 1300. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0301] The power source 1308 provides power to the various components of network node 1300 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1308 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1300 with power for performing the functionality described herein. For example, the network node 1300 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 1308. As a further example, the power source 1308 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0302] Embodiments of the network node 1300 may include additional components beyond those shown in fig. 12 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 1300 may include user interface equipment to allow input of information into the network node 1300 and to allow output of information from the network node 1300. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1300.

[0303] Fig. 13 is a block diagram illustrating a virtualization environment 1400 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 1400 hosted by one or more of hardware nodes, such as a hardware computing device that operates as an access network node, UE, core network node, or host. Further, in embodiments in which a virtualnode does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 1400 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an 0-2 interface.

[0304] Applications 1402 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0305] Hardware 1404 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 1406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VM 1408A and VM 1408B (which may be collectively referred to as VMs 1408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1406 may present a virtual operating platform that appears like networking hardware to one or more of the VMs 1408.

[0306] The VMs 1408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by virtualization layer 1406. Different embodiments of the instance of a virtual appliance 1402 may be implemented on one or more of VMs 1408, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0307] In the context of NFV, each of the VMs 1408 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, nonvirtualized machine. Each of the VMs 1408, and that part of hardware 1404 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM withothers of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more of the VMs 1408 on top of the hardware 1404 and corresponds to an application 1402.

[0308] Hardware 1404 may be implemented in a standalone network node with generic or specific components. Hardware 1404 may implement some functions via virtualization. Alternatively, hardware 1404 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 1410, which, among others, oversees lifecycle management of applications 1402. In some embodiments, hardware 1404 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 1412 which may alternatively be used for communication between hardware nodes and radio units.

[0309] The embodiments herein are not limited to the above described embodiments. Various alternatives, modifications and equivalents may be used. Therefore, the above embodiments should not be taken as limiting the scope of the embodiments, which is defined by the appended claims. A feature from one embodiment may be combined with one or more features of any other embodiment.

[0310] The term “at least one of A and B” should be understood to mean “only A, only B, or both A and B.”, where A and B are any parameter, number, indication used herein etc.

[0311] It should be emphasized that the term “comprises / comprising” when used in this specification is taken to specify the presence of stated features, integers, steps or components, but does not preclude the presence or addition of one or more other features, integers, steps, components or groups thereof. It should also be noted that the words “a” or “an” preceding an element do not exclude the presence of a plurality of such elements.The term “configured to” used herein may also be referred to as “arranged to”, “adapted to”, “capable of’ or “operative to”.

[0312] It should also be emphasised that the steps of the methods defined in the appended claims may, without departing from the embodiments herein, be performed in another order than the order in which they appear in the claims.

Claims

CLAIMS1. A computer implemented method performed by a node (101, 703) for performing network configuration across a plurality of cells (103a, 103b) in a communications network (100), wherein the plurality of cells (103a ,103b) comprises at least a first cell (103a) and at least a second cell (103b), the method comprising:obtaining (501, 503, 710, 711, 801) input data, wherein the input data comprises at least one Performance Monitoring, PM, parameter;predicting (505, 712, 802) a future load contribution caused by at least one User Equipment, UE, (105) in the first cell (103a) that is directed from the second cell (103b), wherein the prediction is done based on the input data and performed using a transformer-based machine learning algorithm; andperforming (506, 713, 803) network configuration based on the predicted future load contribution.

2. The method according to any of the preceding claims, wherein the at least PM parameter comprises at least one of:• a first counter indicating a number of attempts made by the UE (105) to initiate dual connectivity comprising the first cell (103a) and the second cell (103b);• a second counter indicating a number of attempts made by the UE (105) to establish a Secondary Cell Group, SCG, for the UE (105);• a third counter indicating a number of successful completions of attempts made by the UE (105) to initiate dual connectivity comprising the first cell (103a) and the second cell (103b); and• a fourth counter indicating a number of successful attempts made by the UE (105) to establish the SCG for the UE (105).

3. The method according to any of the preceding claims, wherein the input data comprises external data (501), wherein the external data (501) represents factors influencing the load in the communications network (100), further wherein the external data (501) comprises at least one of:• train, airplane, and bus schedule data;• sporting events and concerts data;• weather data;• social media activity data;weekdays, public holidays and festival data; andtraffic pattern data.

4. The method according to any of the preceding claims, wherein performing (505, 713, 803) network configuration comprises at least one of:• load balancing,• preconfiguring the node (101, 703),• turning on / offthe node (101, 703), and• performing handover of the at least one UE (105) from a first node to a second node.

5. The method according to any of the preceding claims, wherein an attention mechanism in the transformer-based machine learning algorithm enables the transformer-based machine learning algorithm to dynamically assign weights to different external data.

6. The method according to any of the preceding claims, wherein• the first cell (103a) is a New Radio, NR, cell and the second cell (103b) is a Long Term Evolution, LTE, cell, or• the first cell (103a) is an LTE cell and the second cell (103b) is an NR cell, or• both the first cell (103a) and the second cell (103b) are NR cells, or• both the first cell (103a) and the second cell (103b) are LTE cells.

7. The method according to any of the preceding claims, wherein the node (101, 703) is a network node comprised in a core network or in an access network of the communications network (100).

8. A node (101, 703) for performing network configuration across a plurality of cells (103a, 103b) in a communications network (100),wherein the plurality of cells (103a, 103b) comprises at least a first cell (103a) and at least a second cell (103b), the node (101, 703) being configured to:obtain input data, wherein the input data comprises at least one Performance Monitoring, PM, parameter;predict a future load contribution caused by at least one User Equipment, UE, (105) in a first cell (103a) that is directed from a second cell (103b), wherein the prediction is done based on the input data and performed using a transformer-based machine learning algorithm; and toperform network configuration based on the predicted future load contribution.

9. The node (101, 703) according to claim 8, wherein the at least one PM parameter comprises at least one of:• a first counter indicating a number of attempts made by the UE (105) to initiate dual connectivity comprising the first cell (103a) and the second cell (103b);• a second counter indicating a number of attempts made by the UE (105) to establish a Secondary Cell Group, SCG, for the UE (105);• a third counter indicating a number of successful completions of attempts made by the UE (105) to initiate of dual connectivity comprising the first cell (103a) and the second cell (103b); and• a fourth counter indicating a number of successful attempts made by the UE (105) to establish the SCG for the UE (105).

10. The node (101, 703) according to any of claims 8-9, wherein the input data comprises external data (501), wherein the external data (501) represents factors influencing the load in the communications network (100), further wherein the external data (501) comprises at least one of:• train, airplane, and bus schedule data;• sporting events and concerts data;• weather data;• social media activity data;• weekdays, public holidays and festival data;• traffic pattern data.

11. The node (101, 703) according to any of claims 8-10, wherein the network configuration comprises at least one of:• load balancing,• preconfiguring the node (101, 703),• turning on / offthe node (101, 703), and• performing handover of the at least one UE (105) from a first node to a second node.

12. The node (101, 703) according to any of claims 8-11, wherein an attention mechanism in the transformer-based machine learning algorithm enables the transformer-based machine learning algorithm to dynamically assign weights to different external data.

13. The node (101, 703) according to any of claims 8-12, wherein• the first cell (103a) is a New Radio, NR, cell and the second cell (103b) is a Long Term Evolution, LTE, cell, or• the first cell (103a) is an LTE cell and the second cell (103b) is an NR cell, or both the first cell (103a) and the second cell (103b) are NR cells, or• both the first cell (103a) and the second cell (103b) are LTE cells.

14. The node (101, 703) according to any of claims 8-13, wherein the node (101, 703) is comprised in a network node in a core network or in an access network of the communications network (100).

15. A computer program product (907) comprising program code for performing, when executed by a processing circuitry (901), the method of any of claims 1-7.

16. A non-transitory computer-readable storage medium (908) comprising instructions, which when executed by a processing circuitry (901), cause the processing circuitry (901) to perform the method of any of claims 1-7.

Images