Performance monitoring and control of enterprise wireless networks

Abstract

An analytics system (230) is configured to manage performance of a communication network (220) deployed in an enterprise environment. The analytics system (230) comprises a data collection function (232) arranged to obtain, from one or more network nodes or functions (NNFs) of the communication network (220), a plurality of metrics representative of performance of the communication network based on current values for the one or more configuration parameters. The analytics system (230) comprises an application programming interface (API, 234) to an edge data center (212) of the enterprise environment. The data collection function (232) is further arranged to obtain, via the API, performance requirements for one or more applications (210) that utilize the communication network (220) in the enterprise environment. The analytics system (230) comprises a network configuration function (236) arranged to determine updated values for one or more configuration parameters of the communication network (220) for the communication network (220), based on the following: the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters. The network configuration function (236) is configured to configure the communication network (220) based on the updated values for the one or more configuration parameters.

Description

[0001] PERFORMANCE MONITORING AND CONTROL OF ENTERPRISE WIRELESS NETWORKS

[0002] TECHNICAL FIELD

[0003] The present disclosure relates generally to communication networks and more specifically to monitoring and control of wireless communication networks used in an enterprise environment, such as for controlling smart manufacturing and / or mobile lineless assembly.

[0004] BACKGROUND

[0005] The fifth generation (5G) of cellular systems was initially standardized 3rd Generation Partnership Project (3GPP) Rel-15 and continues to evolve in subsequent releases. 5G is developed for maximum flexibility to support a variety of different use cases including enhanced mobile broadband (eMBB), machine type communications (MTC), ultra-reliable low latency communications (URLLC), side-link device-to-device (D2D), and several other use cases. 5G technology shares many similarities with fourth-generation Long Term Evolution (LTE).

[0006] At a high level, the 5G System (5GS) consists of an Access Network (AN) and a Core Network (CN). The AN provides UEs connectivity to the CN, e.g., via base stations such as gNBs or ng-eNBs. The CN includes a variety of Network Functions (NF) that provide a range of functionality such as session and connection management, charging, authentication, etc.

[0007] One use case for 5G and future 6G wireless networks is smart manufacturing, which demands a high degree of customization with flexible and adaptive manufacturing processes. Even today many manufacturing operations are moving away from traditional rigid assembly lines towards flexible mobile lineless assembly systems, which allow mobile workpieces and machine tools to carry out runtime control of manufacturing processes via cloud.

[0008] Autonomous mobile robots (AMRs) play a key role in mobile lineless assembly systems and adaptive manufacturing. AMRs are generally capable of performing various tasks at different locations in a factory. Cloud control and dynamic runtime task distribution to AMRs facilitates flexible manufacturing with potential reuse of resources across the factory. Cloud control of AMRs requires a robust wireless network in the factory site, such as to facilitate sensor-actuator- controller closed loop communication with reliable low latency. However, this type of network traffic may have varying requirements in terms of volume and other quality-of-service (QoS) settings.

[0009] Furthermore, wireless network coverage and radio propagation conditions may vary across the factory where AMRs operate. As such, the 5G / 6G wireless network used in this application must dynamically adapt to satisfy the application’s communication requirements as AMRs move through the varying coverage and propagation conditions. SUMMARY

[0010] Embodiments of the present disclosure address these and other challenges in smart manufacturing or similar enterprise applications based on techniques for dynamically selecting 5G / 6G network configuration parameters based on data collected from the 5G / 6G network and based on data obtained from the enterprise (e.g., edge) cloud via an open API. As such, an object of embodiments of the present disclosure is to improve performance of smart manufacturing or similar enterprise applications that rely on wireless networks. The object is achieved by facilitating monitoring system performance metrics and application requirements and setting network configurations accordingly.

[0011] Some embodiments include methods (e.g., procedures) performed by an analytics system configured to manage performance of a communication network deployed in an enterprise environment.

[0012] These exemplary methods include obtaining, from one or more network nodes or functions (NNFs) of the communication network, a plurality of metrics representative of performance of the communication network based on current values for one or more configuration parameters. These exemplary methods also include obtaining performance requirements for one or more applications that utilize the communication network in the enterprise environment. These exemplary methods also include determining updated values for one or more configuration parameters of the communication network for the communication network, based on the following: the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters. These exemplary methods also include configuring the communication network based on the updated values for the one or more configuration parameters.

[0013] In some embodiments, determining updated values for the one or more configuration parameters is based on a reinforcement learning (RL) model that uses a Markov Decision Process. In some of these embodiments, these exemplary methods also include, prior to using the RL model to manage performance of the communication network, training the RL model offline based on a digital twin (DT) of the communication network. In some of these embodiments, determining updated values for the one or more configuration parameters based on the RL model includes the following operations:

[0014] • determining a current state based on the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters;

[0015] • determining a reward function based on the current state and a plurality of candidate actions, wherein each candidate action includes different values for the one or more configuration parameters; and • selecting the updated values for the one or more configuration parameters, based on the candidate action for which the reward function is largest.

[0016] In some embodiments, for each candidate action, the reward function is a function of the following: a first reward metric related to an effect of the candidate action on a first one of the plurality of metrics; and a second reward metric related to an effect of the candidate action on a second one of the plurality of metrics.

[0017] In some embodiments, for each candidate action, the reward function comprises a first function of the first and second reward metrics, when the candidate action satisfies the performance requirements, and a second function of the first and second reward metrics, when the candidate action does not satisfy the performance requirements.

[0018] In some variants of these embodiments, the reward function is a penalty function having a maximum value of zero.

[0019] In some embodiments, the communication network includes a radio access network (RAN) that provides respective communication links to one or more terminal equipment operating in the enterprise environment. In some of these embodiments, the plurality of metrics include the following for the respective communication links: a link robustness metric, and a link resource utilization metric. Also, the one or more application requirements include a quality of service (QoS) requirement. In some variants of these embodiments, the link robustness metric is measured block error rate (BLER), and the link resource utilization metric is ratio of used resource blocks (RBs) to available RBs.

[0020] In some of these embodiments, the one or more configuration parameters includes a block error rate (BLER) target for the respective communication links, and the plurality of candidate actions include a corresponding plurality different values of the BLER target. In some of these embodiments, the QoS requirement includes one or more of the following for the respective communication links to the terminal equipment: maximum latency, minimum throughput, and minimum reliability.

[0021] In some embodiments, obtaining the plurality of metrics comprises obtaining performance management (PM) data from the RAN, and determining the plurality of metrics based on the PM data.

[0022] In some embodiments, the obtained PM data includes at least two of the following: uplink (UL) and / or downlink (DL) medium access control (MAC) acknowledgements (ACKs) and negative ACKs (NACKs) for different modulation orders used by the RAN;

[0023] UL and / or DL radio link control (RLC) ACK and NACKs; signal-to-interference-and-noise ratio (SINR) for UL channels; interference-plus-noise (I+N) resource block (RB) distribution; UL and / or DL pathloss; distribution of modulation and coding schemes (MCS) used in UL and / or DL;

[0024] UL power headroom;

[0025] UL and / or DL MAC volume or throughput;

[0026] UL and / or DL MAC contention delays; and

[0027] UL and / or DL RB utilization.

[0028] In some embodiments, the configuration parameters for the RAN include one or more of the following: uplink (UL) and / or downlink (DL) block error rate (BLER) target; enable or disable packet data convergence protocol (PDCP) out of order delivery of packets; outer loop link adaptation (OLLA) step size; maximum number of hybrid ARQ (HARQ) retransmissions in UL and / or DL; least robust modulation and coding scheme (MCS) for UL and / or DL; most robust MCS for UL and / or DL; enable or disable 256 QAM in UL and / or DL; maximum number of resource blocks (RBs) used in UL and / or DL PRBs; enable or disable prescheduling; prescheduling data size; enable or disable UL robust link adaptation; time-division duplexing (TDD) pattern; location of TDD special slot; subcarrier spacing (SCS);

[0029] UL sounding reference signal (SRS) periodicity;

[0030] DL demodulation reference signal (DMRS) signal-to-interference-and-noise ratio (SINR) threshold; enable or disable terminal equipment discontinuous reception (DRX);

[0031] DRX timer value; dual-connectivity (DC) configurations used for terminal equipment; and power control for one or more UL channels.

[0032] In some embodiments, the enterprise environment is a mobile lineless assembly system and the terminal equipment are respective autonomous mobile robots (AMRs).

[0033] In some embodiments, the applications are hosted by an edge data center in the environment, and obtaining performance requirements for the one or more applications is performed via an application programming interface (API) to the edge data center. In some embodiments, the plurality of metrics are obtained and the communication network is configured via sockets of respective shell instances implemented by the one or more NNFs.

[0034] In some embodiments, the method further comprises, after configuring the communication network, obtaining an updated plurality of metrics representative of performance of the communication network based on the updated values for the one or more configuration parameters. The method also comprises determining further updated values for the one or more configuration parameters based on the following: the updated plurality of metrics, the performance requirements, and the updated values for the one or more configuration parameters.

[0035] In some embodiments, the communication network includes a 4G wireless network, a 5G wireless network, and / or a 6G wireless network. In some embodiments, the analytics system is hosted and / or implemented by one of the following:

[0036] • one or more nodes of a radio access network (RAN) in the communication network;

[0037] • a network data analytics function (NWDAF) of the communication network;

[0038] • a virtualization environment for network functions of the communication network;

[0039] • a service management and orchestration (SMO) function of the communication network;

[0040] • a network management (NM) node or function of the communication network; or

[0041] • a computing environment external to the communication network.

[0042] Other embodiments include analytics systems (or network equipment configured to implement such systems) that are configured to perform operations corresponding to any of the exemplary methods described herein.

[0043] In some embodiments, a network equipment is arranged to implement an analytics system configured to manage performance of a communication network deployed in an enterprise environment. The network equipment comprises communication interface circuitry configured to communicate with one or more nodes of the communication system and with applications utilized in the enterprise environment. The network equipment comprises processing circuitry operably coupled to the communication interface circuitry. Thereby, the processing circuitry and the communication interface circuitry are configured to perform operations corresponding to any of the methods of the aforementioned embodiments.

[0044] In some embodiments, an analytics system is configured to manage performance of a communication network deployed in an enterprise environment. The analytics system is further configured to perform operations corresponding to any of the methods of the aforementioned embodiments.

[0045] In some embodiments, an analytics system is configured to manage performance of a communication network deployed in an enterprise environment. The analytics system comprises a data collection function arranged to obtain, from one or more network nodes or functions (NNFs) of the communication network, a plurality of metrics representative of performance of the communication network based on current values for the one or more configuration parameters. The analytics system comprises an application programming interface (API) to an edge data center of the enterprise environment. The data collection function is further arranged to obtain, via the API, performance requirements for one or more applications that utilize the communication network in the enterprise environment. The analytics system comprises a network configuration function arranged to determine updated values for one or more configuration parameters of the communication network for the communication network, based on the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters. The network configuration function is arranged to configure the communication network based on the updated values for the one or more configuration parameters.

[0046] Other embodiments include non-transitory, computer-readable media storing program instructions that, when executed by processing circuitry, configure such analytics systems to perform operations corresponding to any of the exemplary methods described herein.

[0047] Other embodiments include a computer program product comprising computerexecutable instructions that, when executed by processing circuitry associated with an analytics system configured to manage performance of a communication network deployed in an enterprise environment, configure the analytics system to perform operations corresponding to any of the methods of the aforementioned embodiments.

[0048] These and other embodiments described herein can provide various benefits and / or advantages. For example, embodiments may facilitate self-optimization of networks based on monitoring network performance and configuring network parameter settings. Embodiments may also facilitate the use of network “digital twins” to predict network performance based on application requirements without disturbing operation of actual networks with parameter changes. Embodiments may also facilitate exposure of network performance metrics to external applications (e.g., in an enterprise), which may provide better network insight and / or facilitate configuration of network parameters to suit requirements of such external applications.

[0049] These and other objects, features, and advantages of embodiments of the present disclosure will become apparent upon reading the following Detailed Description in view of the Drawings briefly described below.

[0050] BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 shows a high-level view of an exemplary 5G / NR network architecture.

[0052] Figure 2 shows a high level view of a mobile lineless assembly system, according to some embodiments of the present disclosure. Figure 3 shows a flow diagram of the operation of the system shown in Figure 2, according to some embodiments of the present disclosure.

[0053] Figure 4 illustrates how an exemplary reinforcement learning (RL) agent interacts with its environment.

[0054] Figure 5 is a flow diagram of a procedure for network configuration using deep reinforcement learning (DRL) with a Markov Decision Process, according to some embodiments of the present disclosure

[0055] Figure 6 shows an exemplary arrangement for separating training and operation of a DRL agent, according to some embodiments of the present disclosure

[0056] Figure 7 shows an example network data collection arrangement, according to some embodiments of the present disclosure.

[0057] Figure 8 shows a high-level diagram of an Open RAN (O-RAN) architecture in which some embodiments of the present disclosure may be implemented.

[0058] Figure 9 shows an exemplary method (e.g., procedure) for an analytics system, according to various embodiments of the present disclosure.

[0059] Figure 10 shows a communication system according to various embodiments of the present disclosure.

[0060] Figure 11 shows a network node according to various embodiments of the present disclosure.

[0061] Figure 12 shows host computing system according to various embodiments of the present disclosure.

[0062] Figure 13 is a block diagram of a virtualization environment in which functions implemented by some embodiments of the present disclosure may be virtualized.

[0063] DETAILED DESCRIPTION

[0064] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0065] In general, all terms used herein are to be interpreted according to their ordinary meaning to a person of ordinary skill in the relevant technical field, unless a different meaning is expressly defined and / or implied from the context of use. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise or clearly implied from the context of use. The operations of any methods and / or procedures disclosed herein do not have to be performed in the exact order disclosed, unless an operation is explicitly described as following or preceding another operation and / or where it is implicit that an operation must follow or precede another operation. Any feature of any embodiment disclosed herein can apply to any other disclosed embodiment, as appropriate. Likewise, any advantage of any embodiment described herein can apply to any other disclosed embodiment, as appropriate.

[0066] The term “radio access network node” (shortened to “RAN node”) used herein may refer to any node in a radio access network (RAN) that wirelessly transmits and / or receives signals, and / or facilitates such transmission and / or reception. Some examples of a RAN node include, but are not limited to, a base station (e.g., high-power, low-power, macro, micro, femto, home, etc.), a gNB in a 5G / NR NG-RAN, an eNB in a 4G / LTE E-UTRAN, base station distributed components (e.g., CU and DU), an integrated access backhaul (IAB) node, a transmission point (TP), a transmission reception point (TRP), a remote radio unit (e.g., RRU, RRH), and a relay node.

[0067] The term “core network node” is used herein to refer to any node in a core network of a communication network. Some examples of a core network node include mobility management entity (MME), serving gateway (SGW), packet data network (PDN) gateway (P-GW), policy and charging rules function (PCRF), access and mobility management function (AMF), session management function (SMF), user plane function (UPF), charging function (CHF), policy control function (PCF), authentication server function (AUSF), location management function (LMF), and network data analytics function (NWDAF).

[0068] Note that the description given herein focuses on a 3 GPP cellular communications system and, as such, 3GPP terminology or terminology similar to 3GPP terminology is generally used. However, the concepts disclosed herein are not limited to a 3GPP system, and can be applied in any system that can benefit from the concepts, principles, and / or embodiments described herein.

[0069] Figure 1 shows a high-level view of an exemplary 5G network architecture, including a next-generation RAN (NG-RAN, 199) and a 5G core network (5GC, 198). As shown in the figure, the NG-RAN can include gNBs (e.g., 110a, b) and ng-eNBs (e.g., 120a, b) that are interconnected with each other via respective Xn interfaces. The gNBs and ng-eNBs are also connected via the NG interfaces to 5GC 198, more specifically to access and mobility management functions (AMFs, e.g., 130a, b) via respective NG-C interfaces and to user plane functions (UPFs, e.g., 140a, b) via respective NG-U interfaces. Moreover, AMFs can communicate with one or more policy control functions (PCFs, e.g., 150a,b) and network exposure functions (NEFs, e.g., 160a,b).

[0070] Each of the gNBs can support the NR radio interface including frequency division duplexing (FDD), time division duplexing (TDD), or a combination thereof. Each of ng-eNBs can support the fourth generation (4G) Long-Term Evolution (LTE) radio interface but unlike conventional LTE eNBs, ng-eNBs connect to the 5GC via the NG interface. Each of the gNBs and ng-eNBs can serve a geographic coverage area including one or more cells (e.g., 11 la-b and 121a-b shown in Figure 1). Depending on the cell in which it is located, a UE (e.g., 105 in Figure 1) can communicate with the gNB or ng-eNB serving that cell via the NR or LTE radio interface, respectively. Although Figure 1 shows gNBs and ng-eNBs separately, it is also possible that a single NG-RAN node provides both types of functionality.

[0071] Although not shown explicitly, each gNB in Figure 1 may include a Central Unit (CU or gNB-CU) and one or more Distributed Units (DUs or gNB-DUs). CUs are logical nodes that host higher-layer protocols and perform various gNB functions such as controlling operation of DUs. In contrast, DUs are decentralized logical nodes that host lower layer protocols and can include, depending on the functional split option, various subsets of the gNB functions. Each CU and DU can include various circuitry needed to perform their respective functions, including processing circuitry, communication interface circuitry (e.g., transceivers), and power supply circuitry. Each CU communicates with its associated DUs via respective Fl interfaces.

[0072] 5G / NR technology shares many similarities with LTE. For example, NR uses CP-OFDM (Cyclic Prefix Orthogonal Frequency Division Multiplexing) in the DL and both CP-OFDM and DFT-spread OFDM (DFT-S-OFDM) in the UL. As another example, in the time domain, NR DL and UL physical resources are organized into equal-sized 1-ms subframes. A subframe is further divided into multiple slots of equal duration, with each slot including multiple OFDM-based symbols. However, time-frequency resources can be configured much more flexibly for an NR cell than for an LTE cell. For example, rather than a fixed 15-kHz OFDM sub-carrier spacing (SCS) as in LTE, NR SCS can range from 15 to 240 kHz, with even greater SCS considered for future NR releases.

[0073] In addition to providing coverage via cells as in LTE, NR networks also provide coverage via “beams.” In general, a downlink (DL, i.e., network to UE) “beam” is a coverage area of a network-transmitted reference signal (RS) that may be measured or monitored by a UE. In NR, DL RS can include any of the following: synchronization signal / PBCH block (SSB), channel state information RS (CSLRS), tertiary reference signals (or any other sync signal), positioning RS (PRS), demodulation RS (DMRS), phase-tracking reference signals (PTRS), etc. In general, SSB is available to all UEs regardless of the state of their connection with the network, while other RS (e.g., CSLRS, DM-RS, PTRS) are associated with specific UEs that have a network connection.

[0074] As mentioned above, autonomous mobile robots (AMRs) play a key role in mobile lineless assembly systems and adaptive manufacturing. AMRs are generally capable of performing various tasks at different locations in a factory. Cloud control and dynamic runtime task distribution to AMRs facilitates flexible manufacturing with potential reuse of resources across the factory. Cloud control of AMRs requires a robust wireless network in the factory site, such as to facilitate sensor-actuator-controller closed loop communication with reliable low latency.

[0075] Accordingly, embodiments of the present disclosure address these and other challenges in smart manufacturing or similar enterprise applications based on techniques for dynamically selecting network (e.g., 5G / 6G) configuration parameters based on data collected from the network and based on data obtained from the enterprise (e.g., edge) cloud via an open application programming interface (API). As such, an object of embodiments of the present disclosure is to improve performance of smart manufacturing or similar enterprise applications that rely on wireless networks. The object is achieved by facilitating monitoring system performance metrics and application requirements and setting network configurations accordingly.

[0076] Embodiments of the present disclosure may provide various benefits and / or advantages. For example, embodiments may facilitate self-optimization of networks based on monitoring network performance and configuring network parameter settings. Embodiments may also facilitate the use of network “digital twins” to predict network performance based on application requirements without disturbing operation of actual networks with parameter changes. Embodiments may also facilitate exposure of network performance metrics to external applications (e.g., in an enterprise), which may provide better network insight and / or facilitate configuration of network parameters to suit requirements of such external applications.

[0077] Although some embodiments of the present disclosure are described based on a mobile robotics or smart manufacturing use case, embodiments are equally applicable to any other enterprise application or use case that may benefit from using them.

[0078] Figure 2 shows a high level view of a mobile lineless assembly system according to some embodiments of the present disclosure. The manufacturing processes in the mobile lineless assembly are carried out by AMRs 200a-200e that operate on a factory floor and are coordinated via one or more enterprise applications 210 in an edge data center 212 (or cloud). An enterprise (factor) digital twin 214 may also reside in the edge data center 212. The AMRs 200a-200e communicate with the enterprise applications 210 in the edge data center 212 via an enterprise 5G network 220. The assembly tasks are executed by bringing the workpieces and AMRs 200a-200e to specified locations on the factory floor.

[0079] The network traffic between the AMRs 200a-200e and the edge data center 212 may have varying requirements in terms of volume, latency, and other QoS parameters. For example, the ellipse in Figure 2 represents an area on the factory floor where the assembly task(s) performed by the AMRs 200a-200e require low latency and high reliability for the communication via the 5G network 220 (referred to as “time critical”). Furthermore, 5G network coverage and radio propagation conditions may vary across the factory floor where AMRs 200a-200e operate. As such, the 5G network 220 used in this environment must dynamically adapt to satisfy communication requirements as AMRs 200a-200e move through various coverage, propagation conditions, and levels of time criticality.

[0080] To accomplish this goal, the system in Figure 2 also includes an analytics system 230 (also called “optimization framework”) with the following main components:

[0081] • Network data collection 232;

[0082] • API 234 to enterprise applications 210; and

[0083] • Network configuration 236, based on prediction and decision-making algorithms.

[0084] The data collection function 232 may collect various real- and non-real-time information from the various nodes or functions of the 5G network 220. The collected information may include performance metrics, KPIs, status information at different protocol layers, and node resource status (e.g., compute, storage, communication). The information may be collected from the RAN (e.g., individual RAN nodes), the CN, and the transport network that connects them.

[0085] The API 234 facilitates bidirectional communication between the optimization framework 230 and enterprise applications 210. For example, the enterprise applications 210 can provide QoS requirements, traffic profiles, optimization intents, application metadata, and other relevant information for the network configuration 236. This may include information about current application states as well as information about predicted future application states. As another example, the API 234 facilitates exchange of what-if analyses between the optimization framework 230 and the enterprise applications 210.

[0086] The network configuration function 236 may utilize one or more prediction or decisionmaking algorithms that predict network performance based on the collected network data and the information obtained from the enterprise applications 210 via the API 234. For example, the network configuration function 236 may dynamically select network parameters optimal for network conditions and application performance requirements and configure the network 220 with the selected network parameters in real time.

[0087] Figure 3 shows a flow diagram of these operations in the system of Figure 2, according to some embodiments of the present disclosure. Starting at the top (step 300), network data is collected from the 5G network and from the enterprise applications (e.g., application requirements). This collected information is analyzed, evaluated, and used to generate network performance predictions (step 305). Network configuration parameters are selected based on this analysis and predictions, with the 5G network being configured (or reconfigured) based on the selected parameters (step 310). Subsequently, a new cycle begins by collecting performance- related data from the network configured in the previous cycle. In some embodiments, the decision-making algorithms may be based on machine learning (ML), which is a type of artificial intelligence (Al) that imitates human learning to gradually improve accuracy. ML algorithms build models based on sample (or “training”) data, with the models being used subsequently to make predictions or decisions. In addition to communication networks, ML can be used in a wide variety of applications (e.g., medicine, email filtering, speech recognition, etc.) in which it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.

[0088] As a more specific example, the decision-making algorithms may be based on reinforcement learning (RL), where the algorithm (“agent”) is exposed to an environment in which it trains itself continually using trial and error. The agent accumulates knowledge about the dynamics of its environment (e.g., the communication network) through different interactions that may result in positive or negative outcomes. To train the system, the agent interacts with the environment by repeatedly observing its state and then - based on the knowledge available to the DRL agent at each stage - taking actions intended to maximize a long-term reward based on defined criteria. In each iteration, the agent will learn from the outcome of the suggested actions and will become increasingly “wiser”. At the beginning of the process, the agent’s exploration of the environment may be erratic but will gradually become more focused and precise as the iterations proceed and the agent gains knowledge about the environment’s dynamics.

[0089] Figure 4 illustrates how an exemplary reinforcement learning (RL) agent interacts with its environment. The arrangement shown in Figure 4 includes the environment 402 (e.g., 5G network), an RL agent 404 that includes a learning module 406, a set of environment and agent states S, a set of agent actions^, and a reward r. The probability of a transition from state .s at time t to state ' at time Z+l under action a at time t is given by:

[0090] P(.s, a, s ’) = Pr (s / + 1 = s’ | st =s, at = a) (1) and an immediate reward after a transition from .s to s' under action a is given by: r (s, a, s') . (2)

[0091] The agent 404 interacts with the environment 402 in discrete time instances. At each time instance (e.g., / ), the agent 404 receives an observation Ot, which typically includes the reward rt. The agent 404 then selects an action a from the set of available actions / I and applies the selected action to the environment 402. The environment 402 moves to a new state st+i and the reward mi associated with the transition (st, at, mi) is determined. The goal of the agent 404 is to collect as much reward as possible.

[0092] The selection of the action by the agent may be modelled by a “policy map” given by: n : A x S -> [0,1] (3)

[0093] 7i(a, s) = Pr(at= a | st= s) (4) The policy map gives the probability of taking action a when in state 5. Given state s, action a, and policy zr, the action-value of the pair (5, a) under policy ir is defined by:

[0094] Qn(s, a) = EfE ls, a, n] (5) where the random variable R denotes the return, and is defined as the sum of future discounted rewards:

[0095] R = l'?=o Ytrt(6) where rt is the reward at instance t and 0 < y < 1 is the discount rate.

[0096] The theory of Markov Decision Processes states that if 7t* is an optimal policy, taking the optimal action is carried out by choosing the action from Q71* with the highest value at each state 5. The action-value function of such optimal policy (Q71*) is also called the optimal action-value function and is commonly denoted Q*. In summary, the optimal action-value function Q* provides suffices knowledge for how to act optimally.

[0097] Assuming full knowledge of the Markov Decision Process, two basic approaches to compute an optimal action-value function are value iteration and policy iteration. Both algorithms compute a sequence of functions Qk (k = 0, 1, 2, etc.) that converge to Q*. Computing these functions involves computing expectations over the state-space, which is impractical for all but the smallest (finite) Markov Decision Processes. In RL methods, expectations are approximated by averaging over samples and using function approximation techniques to represent value functions over large state-action spaces.

[0098] Training the agent 404 involves learning the Q(.s, a) function for all possible states and actions. The actions are typically three in this case (i.e., maintain, increase, decrease), but the state is composed of N continuous features, giving an infinite number of possible states. A tabular function for Q may not be the most appropriate approach for this agent. Although a continuous / discrete converter might be included as a first layer, a deep neural network (DNN) may be more suitable because it handles continuous features directly.

[0099] Accordingly, in some embodiments, the decision-making algorithms may be based on deep reinforcement learning (DRL) that combines DNNs with RL. This enables the RL agent to make decisions from unstructured input data without manual engineering of the state space. DRL- based algorithms are able to take in very large inputs and decide what actions to perform to optimize the given reward.

[0100] In some embodiments, the DRL’s Markov Decision Process may be defined as follows:

[0101] • State: network performance metrics / KPIs, network configuration, application information (e.g., requirements);

[0102] • Action: network parameter values to be configured

[0103] • Reward: measure of the network performance after action is taken As an illustrative example, the following Markov Decision Process may be defined for DRL in the exemplary scenario shown in Figure 2 (e.g., factory with AMRs):

[0104] • State: o Link robustness: ratio of negative acknowledgements (NACKs) to total number of transmissions (measured BLER), o Resource utilization: ratio of used to available resource blocks (RBs), o Current BLER target, and o Enterprise application QoS requirements;

[0105] • Action: BLER target selection; and

[0106] • Reward: function of measured BLER, RB ratio, and enterprise application QoS requirements.

[0107] Figure 5 is a flow diagram of a procedure for network configuration using the DRL with Markov Decision Process in the example above, according to some embodiments of the present disclosure. In block 510, data is collected from the 5G network, e.g., by a data collection function. The collected data may include the performance metrics for link robustness (i.e., NACK ratio) and resource utilization (i.e., RB ratio), as well as current BLER target being used in the 5G network (or relevant portion thereof). In block 520, data is collected from the enterprise applications (e.g., for smart manufacturing), such as current application QoS requirements. This data may be collected via the API discussed above.

[0108] In block 530, the decision-making algorithm performs a state space calculation based on the data collected in blocks 510-520 and the previous state of the DRL Markov Decision Process. In block 540, the decision-making algorithm performs a reward calculation for the DRL Markov Decision Process. The operations of blocks 530-540 can be performed in a similar manner as described above in relation to Figure 4.

[0109] In operation 550, the decision-making algorithm analyses and / or determines a next action (i.e., BLER target setting) based on the state and reward determined in blocks 530-540. In block 560, the decision-making algorithm determines whether the BLER target setting determined in block 550 is a change from the current BLER setting obtained in block 510. If so, operation first proceeds to block 570 where the decision-making algorithm configures the new target BLER setting in the 5G network. In either case, operation then returns to block 510 to begin a next cycle of the procedure. As such, the procedure illustrated in Figure 5 can be considered “closed loop”.

[0110] Conventional RL techniques may use “online” training in which the agent interacts in realtime with the environment to learn optimal actions. In most practical deployments, however, online RL training is often time-consuming and expensive, with incremental policy learning frequently producing undesirable actions in the live environment (e.g., 5G network). In some embodiments, offline RL training (or “pre-training”) may be used to decouple training and operational (or inference) phases. For example, a “digital twin” of the 5G network in the enterprise can be used as the “environment” the agent learns during offline RL training. Digital twins (DT) have been used to provide a simulated testing environment in which an ML model (e.g., RL agent) can be trained via initiating “what-if’ actions and observing reward (e.g., outcomes) due to these actions, without risk to the actual environment (e.g., 5G network). At a high level, a DT is a digital counterpart or model of an actual real-world physical product, system, or process (often referred to as “physical twin”), which is effectively indistinguishable for practical purposes such as simulation, integration, testing, monitoring, and maintenance. For example, a DT of a 5G network is a software (e.g., cloud-based) representation of the assets, information, and processes present in the physical 5G network (or portions thereof). As a more specific example, a network DT can be used to model “invisible” aspects of the communication network, such as radio signals, coverage, interference, traffic behavior, and user mobility.

[0111] In more detail, a DT may include various behavioral models, each of which is a software representation of some portion of the assets, information, and processes of a physical communication network. For example, each behavioral model may compute relevant metrics or KPIs for one or more cells in the network, based on measurements and configuration management (CM) parameters for the respective cells. These behavioral models may be hosted in a centralized computing environment, such as a private or public cloud. Alternately, the behavioral models (or portions thereof) may be distributed in nodes of the network (e.g., RAN nodes).

[0112] Implementation-wise, each behavioral model may be an ML model or a less complex set of rules / operations for calculating KPIs from the collected measurements and CM parameters. In the context of offline RL training, an agent’s action can be a change in CM parameters used by the DT’s behavioral model(s), with the RL agent maximizing a reward determined from the KPIs produced by the DT.

[0113] Figure 6 shows an exemplary arrangement for separating training and operation of a DRL agent 600 according to some embodiments of the present disclosure. As discussed above, the state (St) represents the network performs metrics / KPIs and application information, along with the current network configuration. The action (At-1) is the selection of network parameter configuration and reward (Rt) is a measure of the network performance after the action is applied.

[0114] On the left-hand side, the DRL agent 600 undergoes pre-training based on a network simulator 602, which may be a network DT as discussed above. After the DRL agent is adequately pre-trained, it is deployed in the actual environment - an enterprise 5G / 6G network 604. The DRL agent 600 is then used to perform predictions, including selection of a new network configuration (i.e., the action) based on the collected network and application data and current network configuration as illustrated in Figure 5.

[0115] In mobile lineless assembly systems such as shown in Figure 2, AMRs dynamically move around a factory floor while performing various tasks. An AMR’s network performance requirements may vary depending on the performed task. For instance, when the AMRis moving to a docking station to charge, its network performance requirements may be relaxed. On the contrary, when the AMR is performing a joint task with another AMR on the factory floor, the AMR’s network performance requirements may be more demanding, such as for low latency and high reliability in its communications with the network.

[0116] One way to facilitate low latency and high reliability to meet such requirements is to reduce retransmissions by selection of very robust modulation coding scheme (MCS) for initial transmission. A link adaptation algorithm in the AMR’s serving RAN node is responsible for MCS selection based on observed channel quality and a target BLER. The link adaption algorithm can affect MCS selection by offsetting the observed channel quality and / or by adjusting the target BLER. For example, reducing target BLER for an observed channel quality causes selection of a more robust MCS that reduces retransmissions in a manner that meets an AMR’s requirements. However, a more robust MCS also increases the radio resources needed to carry the same amount of application data. As such, a target BLER involves a tradeoff between robustness and resource requirements.

[0117] Accordingly, some embodiments of the present disclosure select target BLER(s) for network links based on a combination of link robustness, resource utilization, and enterprise application QoS requirements. In mathematical notation, the state space S consists of three elements: link robustness (7), resource utilization (2), and current BLER target (s3). Thus, state space S at time t can be defined as St = [s* , s , sf3]. Additionally, multiple states can be “stacked” to capture network state changes over time, such as: where i indicates the ith state and n is the number of stacked states.

[0118] As previously discussed, the action includes selecting a BLER target, which can be done in various ways. As one example, incremental BLER target selection can be used, in which the current BLER target is incremented (or decremented) by a predefined amount to obtain the new BLER target. As a less restrictive example, any BLER target from a set of candidate BLER targets may be selected.

[0119] In some embodiments, the reward is a function of measured link robustness, resource utilization, and application QoS requirements. Various functions of these parameters can be used. As one example, the function may be a combination (r^.omb) of the rewards obtained from link robustness ( / 'Q and resource utilization (r™). However, the goal of the DRL algorithm is to reward actions that satisfy the application QoS requirements and penalize actions that do not satisfy the application QoS requirements.

[0120] In some variants, rewards are given in the form of penalties (i.e., negative values), such that the maximum of r^ombis zero (i.e., zero penalty). For example, r^ombcan be given by: -f(rlr, rru), application QoS requirement satisfied comb — -g(rlr, rru), application QoS requirement NOT satisfied

[0121] In these variants, the objective of reward maximization is equivalent to minimizing the absolute value of the (negative) penalty. Note that these variants may be used together with the procedure shown in Figure 5.

[0122] Figure 7 shows an example network data collection arrangement according to some embodiments of the present disclosure. This includes a software tool 700 - called MOshell Data Collection and Network Configuration (DCNC) - that may be implemented as a Python wrapper. The MOshell DCNC 700 is capable of writing and reading data via a socket of an MOshell instance 702 hosted by a baseband unit (BBU) 704 of the 5G RAN 706. For example, the MOshell DCNC 700 can read performance management (PM) data and modify RAN configuration parameters, such as system constants and managed object (MO) attributes. The MOshell DCNC 700 may be hosted in any appropriate computing environment 708, such as a public or private cloud or a general purpose server.

[0123] The following are some example PM data that may be obtained by the MOshell DCNC 700 from the RAN 706:

[0124] • Uplink (UL) and / or downlink (DL) medium access control (MAC) acknowledgements (ACKs) and negative ACKs (NACKs) for different modulation orders used by the RAN 706 (e.g., QPSK, 16QAM, 64QAM and 256QAM), including for initial transmission and / or discontinuous transmission (DTX);

[0125] • UL / DL radio link control (RLC) ACK and NACKs;

[0126] • Signal -to-interference-and-noise ratio (SINR) for UL channels such as physical UL control channel (PUCCH) and / or physical UL shared channel (PUSCH);

[0127] • Interference-plus-noise (I+N) PRB distribution;

[0128] • UL / DL pathloss;

[0129] • Distribution of modulation and coding scheme (MCS) used in UL and / or DL;

[0130] • UL power headroom;

[0131] • UL / DL MAC volume (or throughput); and • UL / DL MAC contention delays.

[0132] The collected PM data can be analyzed for different time granularities and on various aggregation levels. The following are some example RAN configuration parameters that may be modified by the MOshell DCNC 700:

[0133] • UL and / or DL BLER target;

[0134] • enable or disable packet data convergence protocol (PDCP) out of order delivery of packets;

[0135] • outer loop link adaptation (OLLA) step size;

[0136] • maximum number of hybrid ARQ (HARQ) retransmissions in UL and / or DL;

[0137] • least robust modulation and coding scheme (MCS) for UL and / or DL;

[0138] • most robust MCS for UL and / or DL;

[0139] • enable or disable 256 QAM in UL and / or DL;

[0140] • maximum number of resource blocks (RBs) used in UL and / or DL PRBs;

[0141] • enable or disable prescheduling;

[0142] • prescheduling data size;

[0143] • enable or disable UL robust link adaptation;

[0144] • time-division duplexing (TDD) pattern;

[0145] • location of TDD special slot;

[0146] • subcarrier spacing (SCS);

[0147] • UL sounding reference signal (SRS) periodicity;

[0148] • DL demodulation reference signal (DMRS) signal-to-interference-and-noise ratio (SINR) threshold;

[0149] • enable or disable terminal equipment discontinuous reception (DRX);

[0150] • DRX timer value;

[0151] • dual-connectivity (DC) configurations used for terminal equipment; and

[0152] • power control for one or more UL channels.

[0153] Although the above lists are for PM data and configuration parameters associated with the RAN 706, similar approaches can be used to collect other PM data from the CN 710 coupled to the RAN 706 and / or from UEs 712 (e.g., AMRs) that access the RAN 706. Moreover, some configuration parameters for the CN 710 may be modified based on the collected PM data.

[0154] Some embodiments of the present disclosure may be implemented by a network function (NF) in a core network coupled to a RAN. For example, some embodiments of the analytics system discussed above may be implemented in a network data analytics function (NWDAF) in a 5GC. The NWDAF is a 3GPP-specified NF of the 5GC, and interacts with other NFs to collect relevant data and provide network analytics information (e.g., statistical information of past events and / or predictive information).

[0155] Some embodiments of the present disclosure can be implemented in a cloud RAN, e.g., for a 5G network. In a 5G cloud RAN, a virtualized CU (vCU) can support up to 360 virtualized DUs (vDUs), each of which can serve up to 1024 logical cells. In some implementations, the vCU and associated vDUs are physically collocated (i.e., hosted by same computing equipment), so that information shared between vDUs and vCU does not need to be sent via transmission resources.

[0156] In some embodiments, the analytics system can be hosted by and / or associated with a single vCU, such that it is responsible for collecting data and configuring parameters associated with all logical cells served by all vDUs supported by the single vCU. In other embodiments, the analytics system can be hosted by and / or associated with a single vDU, such that it is responsible for collecting data and configuring parameters associated with all logical cells served by the vDU.

[0157] In other embodiments, the functionality of the analytics system can be distributed among a vCU and one or more associated vDUs. For example, the network measurement collection functionality may be implemented in a vDU while other functionality of the analytics system may be implemented in the vCU.

[0158] In general, embodiments can be implemented using standardized measurements and interfaces between nodes and functions in a communication network (e.g., 5G). In this manner, embodiments are suitable for multi-vendor network deployments.

[0159] Open RAN (0-RAN) Alliance is a community of mobile operators and RAN vendors working towards an open, intelligent, virtualized, operationally efficient, and fully interoperable RANs. To achieve these goals, the community has defined an 0-RAN architecture with key functions and interfaces. Various specifications published by 0-RAN work groups (WGs). For example, 0-RAN WG1 is concerned with use cases and overall architecture. One general principle is that O-RAN architecture and interface specifications shall be consistent with 3GPP architecture and interface specifications, to the extent possible.

[0160] Figure 8 shows an exemplary 0-RAN architecture in which various embodiments can be implemented. The Al, 01, and 02 interfaces connect the Service Management and Orchestration function 810 (SMO) to 0-RAN network functions (NFs) and cloud infrastructure management 860 (O-Cloud). These 0-RAN NFs include Near-Real Time RAN Intelligent Controller 820 (RIC), Open Centralized Units 830(O-CUs), Open Distributed Units 850 (O- DUs), and Open Radio Units (O-RUs, 850). Additionally, there is an interface between SMO 810and external information sources. The O-RAN Architecture also includes the following three control loops with respective latencies:

[0161] • Real Time (RT) Control Loop (<10 ms), typically in O-RU 850 / O-DU 840;

[0162] • Near-RT RIC Control Loop (10-1000 ms), in Near-RT RIC 820; and

[0163] • Non-RT RIC Control Loop (>1000 ms), shown as sub-block 812 in SMO 810.

[0164] Use cases for Non-RT RIC and Near-RT RIC control loops are fully defined by O-RAN, but O- RAN only defines relevant interactions with other O-RAN nodes or functions for the RT control loop (which performs radio scheduling, HARQ, beamforming, etc.).

[0165] The Non-RT RIC 812 provides the Al interface to the Near-RT RIC 820. One task of Non- RT RIC 812 is to provide policy -based guidance, ML model management, and enrichment information to support intelligent RAN optimization by the Near-RT RIC 820 (e.g., for radio resource management, RRM). The Non-RT RIC 812 can also perform intelligent RRM in longer, non-RT intervals (e.g., greater than 1 second).

[0166] The Non-RT RIC 812 can use data analytics and ML model training / inference to determine RAN optimizations, for which it can leverage SMO services such as data collection from and provisioning to the O-RAN nodes. These actions are performed by Non-RT RIC RAN Applications (rApps, e.g., 811), which are exposed to Non-RT RIC functionality and services via the R1 interface in SMO 810.

[0167] In some embodiments, the analytics system can be implemented as an rApp (e.g., 811) in the SMO 810. In other embodiments, the analytics system can be implemented as an xApp (e.g., 821) in the Near-RT RIC 820 or within the O-CU 830 (e.g., in O-CU-CP). In other embodiments, the analytics system may be distributed across the SMO 810 and Near-RT RIC 820. For example, the network measurement collection functionality may be implemented as an rApp 811 in SMO 810 while other functionality of the analytics system may be implemented as an xApp 821 in Near-RT RIC 820.

[0168] Various features of the embodiments described above correspond to various operations illustrated in Figure 9, which shows an exemplary method (e.g., procedures) for an analytics system configured to manage communication network performance in an enterprise environment. The exemplary method can be performed by any appropriate analytics system (or network / computing equipment configured to host such a system), such as described elsewhere herein. Although Figure 9 shows specific blocks in a particular order, the operations of the exemplary method can be performed in different orders than shown and can be combined and / or divided into blocks having different functionality than shown. Optional blocks or operations are indicated by dashed lines. The exemplary method includes the operations of block 920, where the analytics system obtains, from one or more network nodes or functions (NNFs) of the communication network, a plurality of metrics representative of performance of the communication network based on current values for one or more configuration parameters. The exemplary method can also include the operations of block 930, where the analytics system obtains performance requirements for one or more applications that utilize the communication network in the enterprise environment. The exemplary method also includes the operations of block 940, where the analytics system determines updated values for one or more configuration parameters of the communication network for the communication network, based on the following: the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters. The exemplary method also includes the operations of block 950, where the analytics system configures the communication network based on the updated values for the one or more configuration parameters.

[0169] In some embodiments, determining updated values for the one or more configuration parameters in block 940 is based on a reinforcement learning (RL) model that uses a Markov Decision Process. In some of these embodiments, the exemplary method also includes the operations of block 910, where prior to using the RL model to manage performance of the communication network, the analytics system trains the RL model offline based on a digital twin (DT) of the communication network.

[0170] In some of these embodiments, determining updated values for the one or more configuration parameters based on the RL model in block 940 includes the following operations, labelled with corresponding sub-block numbers:

[0171] • (941) determining a current state based on the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters;

[0172] • (942) determining a reward function based on the current state and a plurality of candidate actions, wherein each candidate action includes different values for the one or more configuration parameters; and

[0173] • (943) selecting the updated values for the one or more configuration parameters, based on the candidate action for which the reward function is largest.

[0174] In some variants of these embodiments, the reward function is a penalty function having a maximum value of zero. In some variants of these embodiments, for each candidate action, the reward function is a function of the following:

[0175] • a first reward metric related to an effect of the candidate action on a first one of the plurality of metrics; and • a second reward metric related to an effect of the candidate action on a second one of the plurality of metrics.

[0176] In some further variants, for each candidate action, the reward function comprises:

[0177] • a first function of the first and second reward metrics, when the candidate action satisfies the performance requirements; and

[0178] • a second function of the first and second reward metrics, when the candidate action does not satisfy the performance requirements.

[0179] In some embodiments, the communication network includes a radio access network (RAN) that provides respective communication links to one or more terminal equipment operating in the enterprise environment. In some of these embodiments, the plurality of metrics include the following for the respective communication links: a link robustness metric, and a link resource utilization metric. Also, the one or more application requirements include a quality of service (QoS) requirement. In some variants of these embodiments, the link robustness metric is measured BLER, and the link resource utilization metric is ratio of used resource blocks (RBs) to available RBs.

[0180] In some of these embodiments, the one or more configuration parameters includes a block error rate (BLER) target for the respective communication links, and the plurality of candidate actions include a corresponding plurality different value of the BLER target. In some of these embodiments, the QoS requirement includes one or more of the following for the respective communication links to the terminal equipment: maximum latency, minimum throughput, and minimum reliability.

[0181] In other of these embodiments, obtaining the plurality of metrics in block 920 includes the operations of sub-blocks 921-922, where the analytics system obtains performance management (PM) data from the RAN and determines the plurality of metrics based on the PM data. In some variants of these embodiments, the obtained PM data includes at least two of the following:

[0182] • uplink (UL) and / or downlink (DL) medium access control (MAC) acknowledgements

[0183] (ACKs) and negative ACKs (NACKs) for different modulation orders used by the RAN;

[0184] • UL and / or DL radio link control (RLC) ACK and NACKs;

[0185] • signal-to-interference-and-noise ratio (SINR) for UL channels;

[0186] • interference-plus-noise (I+N) resource block (RB) distribution;

[0187] • UL and / or DL pathloss;

[0188] • distribution of modulation and coding schemes (MCS) used in UL and / or DL;

[0189] • UL power headroom;

[0190] • UL and / or DL MAC volume or throughput; • UL and / or DL MAC contention delays; and

[0191] • UL and / or DL RB utilization.

[0192] In some of these embodiments, the configuration parameters for the RAN include one or more of the following:

[0193] • UL and / or DL BLER target;

[0194] • enable or disable packet data convergence protocol (PDCP) out of order delivery of packets;

[0195] • outer loop link adaptation (OLLA) step size;

[0196] • maximum number of hybrid ARQ (HARQ) retransmissions in UL and / or DL;

[0197] • least robust MCS for UL and / or DL;

[0198] • most robust MCS for UL and / or DL;

[0199] • enable or disable 256 QAM in UL and / or DL;

[0200] • maximum number of RBs used in UL and / or DL PRBs;

[0201] • enable or disable prescheduling;

[0202] • prescheduling data size;

[0203] • enable or disable UL robust link adaptation;

[0204] • time-division duplexing (TDD) pattern;

[0205] • location of TDD special slot;

[0206] • subcarrier spacing (SCS);

[0207] • UL sounding reference signal (SRS) periodicity;

[0208] • DL demodulation reference signal (DMRS) signal-to-interference-and-noise ratio (SINR) threshold;

[0209] • enable or disable terminal equipment discontinuous reception (DRX);

[0210] • DRX timer value;

[0211] • dual-connectivity (DC) configurations used for terminal equipment; and

[0212] • power control for one or more UL channels.

[0213] In some of these embodiments, the enterprise environment is a mobile lineless assembly system and the terminal equipment are respective autonomous mobile robots (AMRs).

[0214] In some embodiments, the applications are hosted by an edge data center in the environment, and obtaining performance requirements for the one or more applications is performed via an application programming interface (API) to the edge data center. In some embodiments, the plurality of metrics are obtained (e.g., in block 910) and the communication network is configured (e.g., in block 970) via sockets of respective shell instances implemented by the one or more NNFs, such as the MOshell instances implemented by BBUs discussed above. In some embodiments, the communication network includes a 4G wireless network, a 5G wireless network, and / or a 6G wireless network. In some embodiments, the analytics system is hosted by one of the following:

[0215] • one or more nodes of a radio access network (RAN) in the communication network;

[0216] • a network data analytics function (NWDAF) of the communication network;

[0217] • a virtualization environment for network functions of the communication network;

[0218] • a service management and orchestration (SMO) function of the communication network;

[0219] • a network management (NM) node or function of the communication network; or

[0220] • a computing environment external to the communication network.

[0221] In some embodiments, the exemplary method also includes the following operations, labelled with corresponding block numbers:

[0222] • (960) after configuring the communication network (e.g., in block 950), obtaining an updated plurality of metrics representative of performance of the communication network based on the updated values for the one or more configuration parameters; and

[0223] • (970) determining further updated values for the one or more configuration parameters based on the following: the updated plurality of metrics, the performance requirements, and the updated values for the one or more configuration parameters.

[0224] Skilled persons will recognize that the analytics system may configure the communication network with the further updated values, in a similar manner as in block 950. In this manner, the analytics system performs closed-loop monitoring and control of the communication network.

[0225] Although various embodiments are described herein above in terms of methods, apparatus, devices, computer-readable medium and receivers, the person of ordinary skill will readily comprehend that such methods can be embodied by various combinations of hardware and software in various systems, communication devices, computing devices, control devices, apparatuses, non-transitory computer-readable media, etc.

[0226] Figure 10 shows an example of a communication system 1000 in accordance with some embodiments. In this example, communication system 1000 includes a telecommunication network 1002 that includes an access network 1004 (e.g., RAN) and a core network 1006, which includes one or more core network nodes 1008. Access network 1004 includes one or more access network nodes, such as network nodes lOlOa-b (one or more of which may be generally referred to as network nodes 1010), or any other similar 3 GPP access nodes or non-3GPP access points. Moreover, as will be appreciated by those of skill in the art, 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, telecommunication network 1002 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in telecommunication 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 nodes to implement one or more functionalities of any node in telecommunication network 1002, including one or more network nodes 1010 and / or core network nodes 1008.

[0227] 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). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access 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 O-2 interface defined by the O-RAN Alliance or comparable technologies. Network nodes 1010 facilitate direct or indirect connection of UEs, such as by connecting UEs 1012a-d (one or more of which may be generally referred to as UEs 1012) to core network 1006 over one or more wireless connections.

[0228] In some embodiments, telecommunication network 1002 can also include one or more Network Management (NM) nodes 1018, which can be part of an operation support system (OSS), a business support system (BSS), and / or an operation / administration / maintenance (0AM) system. The NM nodes can monitor and / or control operations of other nodes in access network 1004 and core network 1006. Although not shown in Figure 10, NM node 1018 is configured to communicate with other nodes in access network 1004 and core network 1006 for these purposes.

[0229] 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, 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. 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.

[0230] UEs 1012 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with network nodes 1010 and other communication devices. Similarly, network nodes 1010 are arranged, capable, configured, and / or operable to communicate directly or indirectly with UEs 1012 and / or with other network nodes or equipment in telecommunication network 1002 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in telecommunication network 1002.

[0231] In the depicted example, core network 1006 connects network nodes 1010 to one or more hosts, 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. Core network 1006 includes one or more core network nodes (e.g., 1008) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of core network node 1008. Example core network nodes include 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).

[0232] Host 1016 may be under the ownership or control of a service provider other than an operator or provider of access network 1004 and / or telecommunication network 1002, and may be operated by the service provider or on behalf of the service provider. 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.

[0233] In some embodiments, access network 1004 can include a service management and orchestration (SMO) system or node 1020, which can monitor and / or control operations of the access network nodes 1010. This arrangement can be used, for example, when access network 1004 utilizes an O-RAN architecture. SMO system 1020 can be configured to communicate with core network 1006 and / or host 1016, as shown in Figure 10.

[0234] In some embodiments, one or more of network node 1010, core network node 1008, host 1016, NM node 1018, and SMO system 1020 can be configured to perform various operations of exemplary methods (e.g., procedures) performed by an analytics system, such as described above in relation to other figures.

[0235] As a whole, communication system 1000 of Figure 10 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 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 (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0236] In some examples, telecommunication network 1002 is a cellular network that implements 3GPP standardized features. Accordingly, telecommunication network 1002 may support network slicing to provide different logical networks to different devices that are connected to telecommunication network 1002. For example, telecommunication 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.

[0237] In some examples, 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 access network 1004 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from 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).

[0238] In the example, hub 1014 communicates with access network 1004 to facilitate indirect communication between one or more UEs (e.g., 1012c and / or 1012d) and network nodes (e.g., network node 1010b). In some examples, hub 1014 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, hub 1014 may be a broadband router enabling access to core network 1006 for the UEs. As another example, 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 hub 1014. As another example, 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, hub 1014 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, hub 1014 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which hub 1014 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, 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.

[0239] Figure 11 shows a network node 1100 in accordance with some embodiments. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (e.g., radio base stations, Node Bs, eNBs, gNBs), and 0-RAN nodes or components of an 0-RAN node (e.g, 0-RU, 0-DU, O-CU).

[0240] Base stations 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. A base station may be a relay node or a relay donor node controlling a relay. A network node 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 0-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).

[0241] Other examples of network nodes 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, and positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs))). In some embodiments, network node 1100 can be configured to perform various operations of exemplary methods (e.g., procedures) performed by an analytics system, such as described above in relation to other figures.

[0242] Network node 1100 includes processing circuitry 1102, memory 1104, communication interface 1106, and power source 1108. Network node 1100 may be composed of multiple physically separate components (e.g., a NodeB component and an RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which network node 1100 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components 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, network node 1100 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1104 for different RATs) and some components may be reused (e.g., a same antenna 1110 may be shared by different RATs). Network node 1100 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1100, for example GSM, WCDMA, LTE, NR, WiFi, 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 1100.

[0243] Processing circuitry 1102 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 network node 1100 components, such as memory 1104, to provide network node 1100 functionality.

[0244] In some embodiments, processing circuitry 1102 includes a system on a chip (SOC). In some embodiments, processing circuitry 1102 includes radio frequency (RF) transceiver circuitry 1112 and / or baseband processing circuitry 1114. In some embodiments, RF transceiver circuitry 1112 and baseband processing circuitry 1114 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 1112 and / or baseband processing circuitry 1114 may be on the same chip or set of chips, boards, or units.

[0245] Memory 1104 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), read-only 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 computer-executable memory devices that store information, data, and / or instructions that may be used by processing circuitry 1102. Memory 1104 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 (collected denoted computer program 1104a, which may be in the form of a computer program product) capable of being executed by processing circuitry 1102 and utilized by network node 1100. Memory 1104 may be used to store any calculations made by processing circuitry 1102 and / or any data received via communication interface 1106. In some embodiments, processing circuitry 1102 and memory 1104 is integrated.

[0246] Communication interface 1106 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, communication interface 1106 comprises port(s) / terminal(s) 1116 to send and receive data, for example to and from a network over a wired connection. Communication interface 1106 also includes radio frontend circuitry 1118 that may be coupled to, or in certain embodiments a part of, antenna 1110. Radio front-end circuitry 1118 comprises filters 1120 and amplifiers 1122. Radio front-end circuitry 1118 may be connected to an antenna 1110 and processing circuitry 1102. The radio front-end circuitry may be configured to condition signals communicated between antenna 1110 and processing circuitry 1102. Radio front-end circuitry 1118 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. Radio front-end circuitry 1118 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1120 and / or amplifiers 1122. The radio signal may then be transmitted via antenna 1110. Similarly, when receiving data, antenna 1110 may collect radio signals which are then converted into digital data by radio front-end circuitry 1118. The digital data may be passed to processing circuitry 1102. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0247] In certain alternative embodiments, network node 1100 does not include separate radio front-end circuitry 1118, instead, processing circuitry 1102 includes radio front-end circuitry and is connected to antenna 1110. Similarly, in some embodiments, all or some of RF transceiver circuitry 1112 is part of communication interface 1106. In still other embodiments, communication interface 1106 includes one or more ports or terminals 1116, radio front-end circuitry 1118, and RF transceiver circuitry 1112, as part of a radio unit (not shown), and communication interface 1106 communicates with baseband processing circuitry 1114, which is part of a digital unit (not shown).

[0248] Antenna 1110 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. Antenna 1110 may be coupled to radio front-end circuitry 1118 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, antenna 1110 is separate from network node 1100 and connectable to network node 1100 through an interface or port.

[0249] Antenna 1110, communication interface 1106, and / or processing circuitry 1102 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, antenna 1110, communication interface 1106, and / or processing circuitry 1102 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0250] Power source 1108 provides power to the various components of network node 1100 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). Power source 1108 may further comprise, or be coupled to, power management circuitry to supply the components of network node 1100 with power for performing the functionality described herein. For example, network node 1100 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 power source 1108. As a further example, power source 1108 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.

[0251] Embodiments of network node 1100 may include additional components beyond those shown in Figure 11 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, network node 1100 may include user interface equipment to allow input of information into network node 1100 and to allow output of information from network node 1100. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for network node 1100.

[0252] Figure 12 is a block diagram of a host 1200, which may be an embodiment of host 1516 of Figure 15, in accordance with various aspects described herein. Host 1200 may be or comprise various combinations hardware and / or software, including a standalone server, a blade server, a cloud-implemented server, a distributed server, a virtual machine, container, or processing resources in a server farm.

[0253] Host 1200 includes processing circuitry 1202 that is operatively coupled via a bus 1204 to an input / output interface 1206, a network interface 1208, a power source 1210, and a memory 1212. Other components may be included in other embodiments. Features of these components may be substantially similar to those described with respect to the devices of previous figures, such as Figure 18, such that the descriptions thereof are generally applicable to the corresponding components of host 1200.

[0254] Memory 1212 may include one or more computer programs including one or more host application programs 1214 and data 1216, which may include user data, e.g., data generated by a UE for host 1200 or data generated by host 1200 for a UE. Embodiments of host 1200 may utilize only a subset or all of the components shown. Host application programs 1214 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Versatile Video Coding (VVC), High Efficiency Video Coding (HEVC), Advanced Video Coding (AVC), MPEG, VP9) and audio codecs (e.g., FLAC, Advanced Audio Coding (AAC), MPEG, G.711), including transcoding for multiple different classes, types, or implementations of UEs (e.g., handsets, desktop computers, wearable display systems, heads-up display systems). Host application programs 1214 may also provide for user authentication and licensing checks and may periodically report health, routes, and content availability to a central node, such as a device in or on the edge of a core network. Accordingly, host 1200 may select and / or indicate a different host for over-the-top services for a UE. Host application programs 1214 may support various protocols, such as the HTTP Live Streaming (HLS) protocol, Real-Time Messaging Protocol (RTMP), Real- Time Streaming Protocol (RTSP), Dynamic Adaptive Streaming over HTTP (MPEG-DASH), etc.

[0255] In some embodiments, host 1200 can be configured to perform various operations of exemplary methods (e.g., procedures) performed by an analytics system, such as described above in relation to other figures.

[0256] Figure 13 is a block diagram illustrating a virtualization environment 1300 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 1300 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node 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 1300 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.

[0257] Applications 1302 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 1300 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein. In some embodiments, one or more applications 1302 can be configured to perform various operations of exemplary methods (e.g., procedures) performed by an analytics system, such as described above in relation to other figures.

[0258] Hardware 1304 includes processing circuitry, memory that stores software and / or instructions (collected denoted computer program 1304a, which may be in the form of a computer program product) 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 1306 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 1308a-b (one or more of which may be generally referred to as VMs 1308), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. Virtualization layer 1306 may present a virtual operating platform that appears like networking hardware to VMs 1308.

[0259] VMs 1308 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 1306. Different embodiments of the instance of a virtual appliance 1302 may be implemented on one or more of VMs 1308, 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.

[0260] In the context of NFV, each VM 1308 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each VM 1308, and that part of hardware 1304 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others 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 VMs 1308 on top of hardware 1304 and corresponds to application 1302.

[0261] Hardware 1304 may be implemented in a standalone network node with generic or specific components. Hardware 1304 may implement some functions via virtualization. Alternatively, hardware 1304 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 function 1310, which, among others, oversees lifecycle management of applications 1302. In some embodiments, hardware 1304 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 1312 which may alternatively be used for communication between hardware nodes and radio units.

[0262] The foregoing merely illustrates the principles of the disclosure. Various modifications and alterations to the described embodiments will be apparent to those skilled in the art in view of the teachings herein. It will thus be appreciated that those skilled in the art will be able to devise numerous systems, arrangements, and procedures that, although not explicitly shown or described herein, embody the principles of the disclosure and can be thus within the spirit and scope of the disclosure. Various embodiments can be used together with one another, as well as interchangeably therewith, as should be understood by those having ordinary skill in the art.

[0263] The term unit, as used herein, can have conventional meaning in the field of electronics, electrical devices and / or electronic devices and can include, for example, electrical and / or electronic circuitry, devices, modules, processors, memories, logic solid state and / or discrete devices, computer programs or instructions for carrying out respective tasks, procedures, computations, outputs, and / or displaying functions, and so on, as such as those that are described herein.

[0264] Any appropriate steps, methods, features, functions, or benefits disclosed herein may be performed through one or more functional units or modules of one or more virtual apparatuses. Each virtual apparatus may comprise a number of these functional units. These functional units may be implemented via processing circuitry, which may include one or more microprocessor or microcontrollers, as well as other digital hardware, which may include Digital Signal Processor (DSPs), special-purpose digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory such as Read Only Memory (ROM), Random Access Memory (RAM), cache memory, flash memory devices, optical storage devices, etc. Program code stored in memory includes program instructions for executing one or more telecommunications and / or data communications protocols as well as instructions for carrying out one or more of the techniques described herein. In some implementations, the processing circuitry may be used to cause the respective functional unit to perform corresponding functions according one or more embodiments of the present disclosure.

[0265] As described herein, device and / or apparatus can be represented by a semiconductor chip, a chipset, or a (hardware) module comprising such chip or chipset; this, however, does not exclude the possibility that a functionality of a device or apparatus, instead of being hardware implemented, be implemented as a software module such as a computer program or a computer program product comprising executable software code portions for execution or being run on a processor. Furthermore, functionality of a device or apparatus can be implemented by any combination of hardware and software. A device or apparatus can also be regarded as an assembly of multiple devices and / or apparatuses, whether functionally in cooperation with or independently of each other. Moreover, devices and apparatuses can be implemented in a distributed fashion throughout a system, so long as the functionality of the device or apparatus is preserved. Such and similar principles are considered as known to a skilled person.

[0266] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0267] In addition, certain terms used in the present disclosure, including the specification and drawings, can be used synonymously in certain instances (e.g., “data” and “information”). It should be understood, that although these terms (and / or other terms that can be synonymous to one another) can be used synonymously herein, there can be instances when such words can be intended to not be used synonymously.

Claims

CLAIMS1. A method performed by an analytics system (230; 811; 821; 810, 820) configured to manage performance of a communication network (220) deployed in an enterprise environment, the method comprising: obtaining (920), from one or more network nodes or functions (NNFs) of the communication network (220), a plurality of metrics representative of performance of the communication network (220) based on current values for one or more configuration parameters; obtaining (930) performance requirements for one or more applications (210) that utilize the communication network (220) in the enterprise environment; determining (940) updated values for one or more configuration parameters of the communication network (220) for the communication network (220), based on the following: the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters; and configuring (950) the communication network (220) based on the updated values for the one or more configuration parameters.

2. The method of claim 1, wherein determining (940) updated values for the one or more configuration parameters is based on a reinforcement learning (RL) model that uses a Markov Decision Process.

3. The method of claim 2, further comprising, prior to using the RL model to manage performance of the communication network (220), training (910) the RL model offline based on a digital twin (DT) of the communication network.

4. The method of any of claims 2-3, wherein determining (940) updated values for the one or more configuration parameters based on the RL model comprises: determining (941) a current state based on the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters; determining (942) a reward function based on the current state and a plurality of candidate actions, wherein each candidate action includes different values for the one or more configuration parameters; andselecting (943) the updated values for the one or more configuration parameters, based on the candidate action for which the reward function is largest.

5. The method of claim 4, wherein for each candidate action, the reward function is a function of the following: a first reward metric related to an effect of the candidate action on a first one of the plurality of metrics; and a second reward metric related to an effect of the candidate action on a second one of the plurality of metrics.

6. The method of claim 5, wherein for each candidate action, the reward function comprises: a first function of the first and second reward metrics, when the candidate action satisfies the performance requirements; and a second function of the first and second reward metrics, when the candidate action does not satisfy the performance requirements.

7. The method of any of claims 4-6, wherein the reward function is a penalty function having a maximum value of zero.

8. The method of any of claims 1-7, wherein the communication network (220) includes a radio access network (RAN) that provides respective communication links to one or more terminal equipment operating in the enterprise environment.

9. The method of claim 8, wherein: the plurality of metrics include the following for the respective communication links: a link robustness metric, and a link resource utilization metric; and the one or more application requirements include a quality of service (QoS) requirement.

10. The method of claim 9, wherein the link robustness metric is measured BLER, and the link resource utilization metric is ratio of used resource blocks (RBs) to available RBs.

11. The method of any of claims 8-10, wherein the one or more configuration parameters includes a block error rate (BLER) target for the respective communication links, and theplurality of candidate actions include a corresponding plurality different value of the BLER target.

12. The method of any of claims 8-11, wherein the QoS requirement includes one or more of the following for the respective communication links to the terminal equipment: maximum latency, minimum throughput, and minimum reliability.

13. The method of claim 8, wherein obtaining (920) the plurality of metrics comprises: obtaining (921) performance management (PM) data from the RAN; and determining (922) the plurality of metrics based on the PM data.

14. The method of claim 13, wherein the obtained PM data includes at least two of the following: uplink (UL) and / or downlink (DL) medium access control (MAC) acknowledgements (ACKs) and negative ACKs (NACKs) for different modulation orders used by the RAN;UL and / or DL radio link control (RLC) ACK and NACKs; signal-to-interference-and-noise ratio (SINR) for UL channels; interference-plus-noise (I+N) resource block (RB) distribution;UL and / or DL pathloss; distribution of modulation and coding schemes (MCS) used in UL and / or DL;UL power headroom;UL and / or DL MAC volume or throughput;UL and / or DL MAC contention delays; andUL and / or DL RB utilization.

15. The method of any of claims 8 and 13-14, wherein the configuration parameters for the RAN include one or more of the following: uplink (UL) and / or downlink (DL) block error rate (BLER) target; enable or disable packet data convergence protocol (PDCP) out of order delivery of packets; outer loop link adaptation (OLLA) step size; maximum number of hybrid ARQ (HARQ) retransmissions in UL and / or DL; least robust modulation and coding scheme (MCS) for UL and / or DL; most robust MCS for UL and / or DL;enable or disable 256 QAM in UL and / or DL; maximum number of resource blocks (RBs) used in UL and / or DL PRBs; enable or disable prescheduling; prescheduling data size; enable or disable UL robust link adaptation; time-division duplexing (TDD) pattern; location of TDD special slot; subcarrier spacing (SCS);UL sounding reference signal (SRS) periodicity;DL demodulation reference signal (DMRS) signal-to-interference-and-noise ratio (SINK) threshold; enable or disable terminal equipment discontinuous reception (DRX);DRX timer value; dual-connectivity (DC) configurations used for terminal equipment; and power control for one or more UL channels.

16. The method of any of claims 8 and 13-15, wherein the enterprise environment is a mobile lineless assembly system and the terminal equipment are respective autonomous mobile robots (AMRs, 200a-200e).

17. The method of any of claims 1-16, wherein the applications (210) are hosted by an edge data center (212) in the environment, and obtaining (930) performance requirements for the one or more applications (210) is performed via an application programming interface (API, 234) to the edge data center (212).

18. The method of any of claims 1-17, wherein the plurality of metrics are obtained and the communication network (220) is configured via sockets of respective shell instances (702) implemented by the one or more NNFs.

19. The method of any of claims 1-18, wherein the analytics system (230; 811; 821; 810, 820) is hosted by one of the following: one or more nodes of a radio access network (RAN) in the communication network (220); a network data analytics function (NWDAF) of the communication network (220); a virtualization environment for network functions of the communication network (220);a service management and orchestration (SMO) function (810) of the communication network (220); a network management (NM) function of the communication network (220); or a computing environment (708) external to the communication network (220).

20. The method of any of claims 1-19, further comprising: after configuring (950) the communication network, obtaining (960) an updated plurality of metrics representative of performance of the communication network based on the updated values for the one or more configuration parameters; and determining (970) further updated values for the one or more configuration parameters based on the following: the updated plurality of metrics, the performance requirements, and the updated values for the one or more configuration parameters.

21. The method of any of claims 1-20, wherein the communication network (220) includes one or more of the following: a 4G wireless network, a 5G wireless network, and a 6G wireless network.

22. Network equipment (1100) arranged to implement an analytics system (230; 811; 821; 810, 820) configured to manage performance of a communication network (220) deployed in an enterprise environment, the network equipment (1100) comprising: communication interface circuitry (1106) configured to communicate with one or more nodes of the communication system (220) and with applications (210) utilized in the enterprise environment; and processing circuitry (1102) operably coupled to the communication interface circuitry (1106), whereby the processing circuitry (1102) and the communication interface circuitry (1106) are configured to obtain, from one or more network nodes or functions (NNFs) of the communication network, a plurality of metrics representative of performance of the communication network (220) based on current values for one or more configuration parameters; obtain performance requirements for one or more applications (210) that utilize the communication network (220) in the enterprise environment;determine updated values for one or more configuration parameters of the communication network (220) for the communication network (220), based on the following: the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters; and configure the communication network (220) based on the updated values for the one or more configuration parameters.

23. Network equipment (1100) of claim 22, wherein the processing circuitry (1102) and the communication interface circuitry (1106) are configured to perform any of the methods of claims 1-21.

24. An analytics system (230; 811; 821; 810, 820) configured to manage performance of a communication network (220) deployed in an enterprise environment, the analytics system (230; 811; 821; 810, 820) being further configured to obtain, from one or more network nodes or functions (NNFs) of the communication network (200), a plurality of metrics representative of performance of the communication network (220) based on current values for one or more configuration parameters; obtain performance requirements for one or more applications (210) that utilize the communication network (220) in the enterprise environment; determine updated values for one or more configuration parameters of the communication network (220) for the communication network (220), based on the following: the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters; and configure the communication network (220) based on the updated values for the one or more configuration parameters.

25. The analytics system (230; 811; 821; 810, 820) of claim 24, the analytics system (230; 811; 821; 810, 820) being further configured to perform operations corresponding to any of the methods of claims 2-21.

26. An analytics system (230; 811; 821; 810, 820) configured to manage performance of a communication network (220) deployed in an enterprise environment, the analytics system (230; 811; 821; 810, 820) comprising:a data collection function (232) arranged to obtain, from one or more network nodes or functions (NNFs) of the communication network (220), a plurality of metrics representative of performance of the communication network based on current values for the one or more configuration parameters; an application programming interface (API, 234) to an edge data center (212) of the enterprise environment, wherein the data collection function (232) is further arranged to obtain, via the API, performance requirements for one or more applications (210) that utilize the communication network (220) in the enterprise environment; a network configuration function (236) arranged to: determine updated values for one or more configuration parameters of the communication network (220) for the communication network (220), based on the following: the plurality of metrics, the performance requirements, and the current values for the one or more configuration parameters; and configure the communication network (220) based on the updated values for the one or more configuration parameters.

27. A non-transitory, computer-readable medium storing computer-executable instructions that, when executed by processing circuitry (1102) associated with an analytics system (230; 811; 821; 810, 820) configured to manage performance of a communication network (220) deployed in an enterprise environment, configure the analytics system (230; 811; 821; 810, 820) to perform operations corresponding to any of the methods of claims 1-21.

28. A computer program product comprising computer-executable instructions that, when executed by processing circuitry (1102) associated with an analytics system (230; 811; 821; 810, 820) configured to manage performance of a communication network (220) deployed in an enterprise environment, configure the analytics system (230; 811; 821; 810, 820) to perform operations corresponding to any of the methods of claims 1-21.

Images