Method and apparatus for network load balancing optimization

Abstract

A method for performing mobility load balancing includes: receiving current load data of a plurality of cells of a wireless communication network at a server; selecting a target cell(s) from the plurality of cells, wherein the value of the current load data of the target cell exceeds a first predetermined threshold; and selecting a set of neighboring cells of the target cell from a list of neighboring cells corresponding to the target cell. The method further includes: calculating the value of at least one utilization parameter of the target cell; determining a CIO value and an E-tilt value of the target cell based on the value of the at least one utilization parameter of the target cell; and configuring one or more physical layer parameters of the target cell based on the determined CIO value and E-tilt value of the target cell.

Description

Technical Field

[0001] This disclosure generally relates to wireless communication networks. More specifically, this disclosure relates to methods and apparatus for network load balancing optimization. Background Technology

[0002] While advancements in wireless communication technologies, including the advent of 5G, have significantly expanded the potential throughput of wireless communication systems, realizing these potential throughput gains requires the efficient allocation of devices across the coverage areas of network access points. Even state-of-the-art eNBs experience varying degrees of oversubscription (e.g., too many devices attempting to communicate through the eNB) or underutilization (e.g., an eNB utilizing only a small fraction of its potential connections). Both scenarios lead to inefficient, suboptimal network performance. Therefore, achieving optimal load balancing among cells in a wireless network remains a source of technical challenges and opportunities for improvement in this field. Summary of the Invention

[0003] Technical issues

[0004] This disclosure provides methods and apparatus for optimizing network load balancing.

[0005] Solution to the problem

[0006] In one embodiment, a method for performing mobility load balancing includes: receiving current load data of a plurality of cells of a wireless communication network at a server; selecting a target cell(s) from the plurality of cells by the server, wherein the value of the current load data of the target cell exceeds a first predetermined threshold; and selecting a set of neighboring cells of the target cell from a list of neighboring cells corresponding to the target cell by the server. The method further includes: calculating a value of at least one utilization parameter of the target cell by the server; determining a cell individual offset (CIO) value and an electronic tilt (E-tilt) value of the target cell based on the value of at least one utilization parameter of the target cell by the server; and configuring one or more physical layer parameters of the target cell based on the determined CIO value and E-tilt value of the target cell. The value of at least one utilization parameter of the target cell includes multiple values ​​of physical resource block (PRB) utilization of the target cell and the selected neighboring cells.

[0007] In another embodiment, a server includes a processor and a network interface. The network interface is configured to receive current load data of a plurality of cells of a wireless communication network. The processor is configured to: select a target cell(s) from the plurality of cells, wherein the value of the current load data of the target cell exceeds a first predetermined threshold; select a set of neighboring cells of the target cell from a list of neighboring cells corresponding to the target cell; calculate the value of at least one utilization parameter of the target cell; determine a CIO value and an E-tilt value of the target cell based on the value of the at least one utilization parameter of the target cell; and configure one or more physical layer parameters of the target cell based on the determined CIO value and E-tilt value of the target cell. The value of the at least one utilization parameter of the target cell includes multiple values ​​of PRB utilization of the target cell and the selected neighboring cells.

[0008] In another embodiment, a non-transitory computer-readable medium including program code, when executed by a processor, causes a server to: receive current load data of a plurality of cells of a wireless communication network via a network interface of the server; select a target cell(s) from the plurality of cells, wherein the value of the current load data of the target cell exceeds a first predetermined threshold; select a set of neighboring cells of the target cell from a list of neighboring cells corresponding to the target cell; calculate the value of at least one utilization parameter of the target cell; determine a CIO value and an E-tilt value of the target cell based on the value of the at least one utilization parameter of the target cell; and configure one or more physical layer parameters of the target cell based on the determined CIO value and E-tilt value of the target cell. The value of at least one utilization parameter of the target cell includes multiple values ​​of PRB utilization of the target cell and the selected neighboring cells.

[0009] Other technical features will be readily apparent to those skilled in the art from the following drawings, description and claims.

[0010] Before proceeding with the following detailed description, it may be advantageous to define certain words and phrases used throughout this patent document. The term “coupled” and its derivatives refer to any direct or indirect communication between two or more elements, regardless of whether those elements are physically in contact with each other. The terms “transmit,” “receive,” and “transmit,” and their derivatives encompass both direct and indirect communication. The terms “comprise” and “include,” and their derivatives mean inclusion without limitation. The term “or” is concurrent, meaning both and / or. The phrase “associated with,” and its derivatives mean including, being included, interconnected, containing, being contained, connected to or connected with, coupled to or coupled with, communicable with, cooperating with, intertwined, juxtaposed, proximate, bound to or bound with, having, possessing attributes, having a relationship with, or having a relationship with, etc. The term “controller” means any device, system, or part thereof that controls at least one operation. Such a controller may be implemented in hardware or a combination of hardware and software and / or firmware. The functionality associated with any particular controller, whether local or remote, may be centralized or distributed. The phrase “at least one of” when used with a list of items means that different combinations of one or more items in the list may be used, and it may be necessary to use only one item in the list. For example, “at least one of A, B, and C” includes any of the following combinations: A only, B only, C only, A and B, A and C, B and C, and A, B, and C.

[0011] Furthermore, the various functions described below can be implemented or supported by one or more computer programs, each computer program being formed from computer-readable program code and embodied in a computer-readable medium. The terms "application" and "program" refer to one or more computer programs, software components, instruction sets, procedures, functions, objects, classes, instances, associated data, or portions thereof suitable for implementation in appropriate computer-readable program code. The phrase "computer-readable program code" includes any type of computer code, including source code, object code, and executable code. The phrase "computer-readable medium" includes any type of medium accessible by a computer, such as read-only memory (ROM), random access memory (RAM), hard disk drive, optical disc (CD), digital video disc (DVD), or any other type of storage. "Non-transitory" computer-readable media excludes wired, wireless, optical, or other communication links that transmit transient electrical or other signals. Non-transitory computer-readable media includes media capable of permanently storing data and media where data can be stored and later rewritten, such as rewritable optical discs or erasable storage devices.

[0012] Definitions for certain other words and phrases are provided throughout this patent document. Those skilled in the art will understand that, in many, if not the most, instances, such definitions apply to both prior and future use of the words and phrases defined in this way. Attached Figure Description

[0013] To gain a more complete understanding of the contents of this disclosure and its advantages, please now refer to the following description relating to the accompanying drawings, wherein similar reference numerals denote similar parts:

[0014] Figure 1 An example of a wireless communication network according to an embodiment of the present disclosure is shown;

[0015] Figure 2 An example of an evolved node B (“eNB”) according to an embodiment of the present disclosure is shown;

[0016] Figure 3 An example of a user equipment (“UE”) according to an embodiment of the present disclosure is shown;

[0017] Figure 4 An example of a server according to an embodiment of the present disclosure is shown;

[0018] Figure 5 An example of a network architecture for implementing RF parameter optimization according to embodiments of the present disclosure is shown;

[0019] Figure 6A and 6B Two examples of RF parameters according to embodiments of the present disclosure are shown, which can be optimized to facilitate load balancing;

[0020] Figure 7 An example of a network architecture for implementing AI-assisted RF parameter optimization is shown according to embodiments of the present disclosure;

[0021] Figure 8 Operation of a method for performing RF parameter optimization according to embodiments of the present disclosure is illustrated;

[0022] Figures 9A-9C Operations of a method for selecting a cell for RF parameter optimization and optimizing the parameters of the selected cell, according to at least one embodiment of the present disclosure, are illustrated. Detailed Implementation

[0023] The following discussion Figures 1 to 9C The various embodiments used to describe the principles of this disclosure in this patent document are illustrative only and should not be construed as limiting the scope of this disclosure in any way. Those skilled in the art will understand that the principles of this disclosure can be implemented in any suitably arranged system or device.

[0024] Figure 1 An example of a portion of network 100 according to this disclosure is shown. Figure 1 The embodiment of network 100 shown is for illustrative purposes only. Other embodiments of network 100 may be used without departing from the scope of this disclosure.

[0025] like Figure 1 As shown, network 100 includes eNodeB (eNB) 101, eNB 102, and eNB 103. eNB 101 communicates with eNB 102 and eNB 103. eNB 101 also communicates with at least one network control system 130 (such as a back-end computing system provided by a mobile operator) that can achieve load balancing among the eNBs of network 100.

[0026] eNB 102 provides wireless connectivity (e.g., via wireless protocols such as 5G or LTE) to network 100 for a first plurality of user equipments (UEs) within coverage area 120 of eNB 102. The first plurality of UEs includes: UE 111, which may be located in a small business; UE 112, which may be located in a business (E); UE 114, which may be located in a first residence (R); UE 115, which may be located in a second residence (R); and UE 116, which may be a mobile device (M) such as a cellular phone, wireless laptop, wireless PDA, etc. eNB 103 provides wireless connectivity to a second plurality of UEs within coverage area 125 of eNB 103. The second plurality of UEs includes UE 115 and UE 116. In some embodiments, one or more of eNBs 101-103 may communicate with each other and with UEs 111-116 using 5G, LTE, LTE-A, WiMAX, Wi-Fi, or other wireless communication technologies.

[0027] Depending on the network type, other known terms such as "base station" or "access point" may be used instead of "eNodeB" or "eNB". For convenience, the terms "eNodeB" and "eNB" are used in this patent document to refer to network infrastructure components that provide wireless connectivity to remote terminals. Furthermore, depending on the network type, other known terms such as "mobile station", "user station", "remote terminal", "wireless terminal", or "user equipment" may be used instead of "user equipment" or "UE". For convenience, the terms "user equipment" and "UE" are used in this patent document to refer to remote wireless devices that wirelessly access the eNB, regardless of whether the UE is a mobile device (such as a mobile phone or smartphone) or is generally considered a fixed device (such as a desktop computer or vending machine).

[0028] The dashed lines indicate the approximate extent of coverage areas 120 and 125, which are shown as approximately circular for illustrative and explanatory purposes only. It should be clearly understood that coverage areas such as 120 and 125 associated with the eNB can have other shapes, including irregular shapes, depending on the eNB configuration and variations in the radio environment associated with natural and man-made obstacles. Furthermore, according to some embodiments, the size and location of coverage areas 120 and 125 can be controlled by adjusting the operating parameters of the physical hardware of the eNB communicating with the UE, such that a given UE occupying a location within the coverage areas of both the first and second eNBs can switch from the first eNB to the second eNB, thereby helping to balance communication load across available eNBs on the network.

[0029] although Figure 1 An example of network 100 is shown, but it is possible to compare it with other networks. Figure 1 Various modifications can be made. For example, the wireless network 100 can include any number of eNBs and any number of UEs in any suitable arrangement. Moreover, the eNB 101 can communicate directly with any number of UEs. In addition, eNBs 101, 102, and / or 103 can provide access to other or additional external networks such as external telephone networks or other types of data networks.

[0030] It should be further noted that Figure 1 Examples are not necessarily related to any specific generation of a wireless communication protocol and the associated technologies used to implement such a protocol. To meet the increased demand for wireless data services due to the deployment of 4G communication systems and to enable various vertical applications, efforts have been made to develop and deploy improved 5G / NR or quasi-5G / NR communication systems. Therefore, 5G / NR or quasi-5G / NR communication systems are also referred to as “super 4G networks” or “post-LTE systems.” Consider implementing 5G / NR communication systems in higher frequency (mmWave) bands, such as 28 GHz or 60 GHz, to achieve higher data rates, or in lower frequency bands, such as 6 GHz, to achieve robust coverage and mobility support. To reduce radio wave propagation loss and increase transmission distance, beamforming, massive MIMO, full-dimensional MIMO (FD-MIMO), array antennas, analog beamforming, and massive MIMO technologies are discussed in 5G / NR communication systems.

[0031] In addition, in 5G / NR communication systems, development is underway to improve system networks based on advanced small cells, cloud radio access networks (RAN), ultra-density networks, device-to-device (D2D) communication, wireless backhaul, mobile networks, cooperative communication, cooperative multipoint (CoMP), and receiver interference cancellation.

[0032] Since some embodiments of this disclosure can be implemented in 5G systems, the discussion of 5G systems and associated frequency bands is provided for reference only. However, this disclosure is not limited to 5G systems or associated frequency bands, and embodiments of this disclosure can be used with respect to any frequency band. For example, aspects of this disclosure can also be applied to deploying 5G communication systems, 6G, or even later versions that can use megahertz (THz) frequency bands.

[0033] Figure 2 Example eNB 102 according to this disclosure is shown. Figure 2 The embodiment of eNB 102 shown is for illustrative purposes only, and Figure 1 eNBs 101 and 103 can have the same or similar configurations. However, eNBs come in a variety of configurations, and Figure 2 This disclosure is not intended to limit the scope to any particular implementation of the eNB.

[0034] like Figure 2 As shown, the eNB 102 includes multiple antennas 205a-205n, multiple RF transceivers 210a-210n, transmit (TX) processing circuitry 215, and receive (RX) processing circuitry 220. The eNB 102 also includes a controller / processor 225, a memory 230, and a backhaul or network interface 235.

[0035] RF transceivers 210a-210n receive incoming RF signals, such as signals transmitted by the UE in network 100, from antennas 205a-205n. RF transceivers 210a-210n down-convert the incoming RF signals to generate IF or baseband signals. The IF or baseband signals are sent to RX processing circuitry 220, which generates a processed baseband signal by filtering, decoding, and / or digitizing the baseband or IF signals. RX processing circuitry 220 sends the processed baseband signal to controller / processor 225 for further processing.

[0036] TX processing circuitry 215 receives analog or digital data (such as voice data, web data, email, or interactive video game data) from controller / processor 225. TX processing circuitry 215 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate processed baseband or IF signals. RF transceivers 210a-210n receive the processed baseband or IF signals from TX processing circuitry 215 and up-convert the baseband or IF signals into RF signals transmitted via antennas 205a-205n. According to some embodiments, the RF signals transmitted via antennas 205a-205n are encoded such that the data to be transmitted and associated signaling are assigned to time / frequency resource blocks (“RBs”). In this illustrative example, the throughput of eNB 102 (and other eNBs in the network) is partially limited by the number of resource blocks available. As more UEs or other devices attempt to communicate through eNB 102, eNB 102 must allocate fewer RBs to each device's communication, leading to a decline in communication performance as the number of supported devices increases. Therefore, allocating UEs and other radio devices among eNBs in a way that balances the load and avoids large variations in RB utilization among eNBs in the network is crucial for ensuring fast and reliable network operation.

[0037] The controller / processor 225 may include one or more processors or other processing devices that control the overall operation of the eNB 102. For example, the controller / processor 225 may control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceivers 210a-210n, the RX processing circuitry 220, and the TX processing circuitry 215, based on known principles. The controller / processor 225 may also support additional functions, such as more advanced wireless communication functions. For example, the controller / processor 225 may support beamforming or directional path selection operations, wherein signals emitted from multiple antennas 205a-205n are weighted differently to effectively redirect the emitted signals in a desired direction. Any of a variety of other functions can be supported in the eNB 102 by the controller / processor 225. In some embodiments, the controller / processor 225 includes at least one microprocessor or microcontroller.

[0038] The controller / processor 225 is also capable of executing programs and other processes, such as the basic operating system, located in the memory 230. The controller / processor 225 can move data into or out of the memory 230 as needed by the executing process.

[0039] The controller / processor 225 is also connected to a backhaul or network interface 235. The backhaul or network interface 235 allows the eNB 102 to communicate with other devices or systems via a backhaul connection or over a network. Interface 235 can support communication via any suitable wired or wireless connection. For example, when the eNB 102 is implemented as part of a cellular communication system (such as a cellular communication system supporting 5G, LTE, or LTE-A), interface 235 can allow the eNB 102 to communicate with other eNBs via a wired or wireless backhaul connection. When the eNB 102 is implemented as an access point, interface 235 can allow the eNB 102 to communicate via a wired or wireless local area network or via a wired or wireless connection to a larger network (such as the Internet). Interface 235 includes any suitable infrastructure that supports communication via wired or wireless connections, such as Ethernet or RF transceivers.

[0040] The memory 230 is connected to the controller / processor 225. A portion of the memory 230 may include RAM, and another portion of the memory 230 may include flash memory or other ROM.

[0041] although Figure 2 An example of an eNB 102 is shown, but more can be found on other eNBs. Figure 2 Various changes can be made. For example, eNB 102 can include any number of... Figure 2 Each component is shown in the diagram. As a specific example, an access point may include multiple interfaces 235, and the controller / processor 225 may support routing capabilities for routing data between different network addresses. As another specific example, although shown as a single instance of TX processing circuitry 215 and a single instance of RX processing circuitry 220, the eNB 102 may include multiple instances of each (such as one per RF transceiver). For example, Figure 2 The various components can be combined, further subdivided, or omitted, and additional components can be added as needed.

[0042] Figure 3 Example UE 116 according to this disclosure is shown. Figure 3 The embodiment of UE 116 shown is for illustrative purposes only, and Figure 1 UEs 111-115 can have the same or similar configurations. However, UEs appear in multiple configurations, and Figure 3 This disclosure is not intended to limit the scope to any particular implementation of the UE.

[0043] like Figure 3As shown, UE 116 includes an antenna 305, a radio frequency (RF) transceiver 310, a transmit (TX) processing circuitry 315, a microphone 320, and a receive (RX) processing circuitry 325. UE 116 also includes a speaker 330, a processor 340 (e.g., a main processor), an input / output (I / O) interface (IF) 345, a keypad 350, a display 355, and a memory 360. The memory 360 includes a basic operating system (OS) program 361 and one or more applications 362.

[0044] RF transceiver 302 receives incoming RF signals transmitted by the eNB of network 100 from antenna 305. RF transceiver 310 down-converts the incoming RF signals to generate intermediate frequency (IF) or baseband signals. The IF or baseband signals are sent to RX processing circuitry 325, which generates processed baseband signals by filtering, decoding, and / or digitizing the baseband or IF signals. RX processing circuitry 325 sends the processed baseband signals to speaker 330 (e.g., for voice data) or processor 340 for further processing (e.g., for web browsing data).

[0045] TX processing circuitry 315 receives analog or digital voice data from microphone 320 or other outgoing baseband data (such as web data, email, or interactive video game data) from processor 340. TX processing circuitry 315 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate a processed baseband or IF signal. RF transceiver 310 receives the processed baseband or IF signal from TX processing circuitry 315 and up-converts the baseband or IF signal into an RF signal transmitted via antenna 305. According to some embodiments, TX processing circuitry 315 and RX processing circuitry 325 encode and decode data and signaling used for wireless communication in resource blocks (“RBs” or physical resource blocks “PRBs”), particularly those generated by wireless networks (e.g., Figure 1 The eNB (electronic new network) of the wireless network 100 transmits and receives data. In other words, the TX processing circuit 215 and the RX processing circuit 220 generate and receive RBs, which contribute to the load measured at the eNB.

[0046] Processor 340 may include one or more processors or other processing devices and executes a basic OS program 361 stored in memory 360 to control the overall operation of UE 116. For example, processor 340 may control the reception of forward channel signals and the transmission of reverse channel signals by RF transceiver 310, RX processing circuitry 325, and TX processing circuitry 315 according to known principles. In some embodiments, processor 340 includes at least one microprocessor or microcontroller.

[0047] Processor 340 is also capable of executing other processes and programs located in memory 360. Processor 340 can move data into or out of memory 360 as needed by the executing processes. In some embodiments, processor 340 is configured to execute application 362 based on OS program 361 or in response to signals received from eNB or operator. Processor 340 is also connected to I / O interface 345, which provides UE 116 with the ability to connect to other devices such as laptops and laptops. I / O interface 345 is the communication path between these accessories and processor 340.

[0048] The processor 340 is also connected to the keypad 350 and the display unit 355. The operator of the UE 116 can use the keypad 350 to type data into the UE 116. The display 355 may be an LCD or other display capable of rendering text and / or at least limited graphics from a website.

[0049] The memory 360 is connected to the processor 340. A portion of the memory 360 may include random access memory (RAM), and another portion of the memory 360 may include flash memory or other read-only memory (ROM).

[0050] although Figure 3 An example of UE 116 is shown, but it is possible to... Figure 3 Various changes can be made. For example, depending on specific needs, elements can be combined, further subdivided, or omitted. Figure 3 The various components within it, and the ability to add additional components. As a specific example, processor 340 can be divided into multiple processors, such as one or more central processing units (CPUs) and one or more graphics data processing units (GPUs). Moreover, although Figure 3 The UE116 is shown configured as a mobile phone or smartphone. The UE can also be configured to operate as other types of mobile or fixed devices.

[0051] Figure 4 An example of a server 400 according to some embodiments of the present disclosure is shown.

[0052] like Figure 4 As shown, server 400 includes bus system 405 that supports communication between at least one processing device 410, at least one storage device 415, at least one communication unit 420 and at least one input / output (I / O) unit 425.

[0053] Processing device 410 executes instructions that can be loaded into memory 430. Processing device 410 can include any suitable number and type of processors or other devices in any suitable arrangement. Example types of processing device 410 include microprocessors, microcontrollers, digital signal processors, field-programmable gate arrays, application-specific integrated circuits, and discrete circuits.

[0054] Memory 430 and permanent storage device 435 are examples of storage device 415, which represents any structure capable of storing and facilitating retrieval of information such as data, program code, and / or other suitable temporary or permanent information. Memory 430 may represent random access memory or any other suitable volatile or non-volatile storage device. Permanent storage device 435 may include one or more components or devices supporting longer-term storage of data, such as read-only memory, hard disk drive, flash memory, or optical disk.

[0055] Communication unit 420 supports communication with other systems or devices. For example, communication unit 420 may include a network interface card or wireless transceiver that facilitates communication over a network. Communication unit 420 may support communication over any suitable physical or wireless communication links(s). According to some embodiments, communication unit 420 includes a network interface or other communication interface through which server 400 can receive status data from hardware of a wireless communication network (e.g., eNB, digital unit (“DU”), and remote wireless headend (“RRH”)) and also send commands for adjusting one or more operating parameters of such hardware (e.g., power level, electronic tilt (“E-tilt”)).

[0056] I / O unit 425 allows for data input and output. For example, I / O unit 425 can provide connectivity for user input via a keyboard, mouse, keypad, touchscreen, or other suitable input device. I / O unit 425 can also send output to a display, printer, or other suitable output device.

[0057] Figure 5 Examples of a radio access network (“RAN”) architecture 500 for implementing network parameter optimization based on artificial intelligence (AI) according to various embodiments of the present disclosure are shown.

[0058] refer to Figure 5 As a non-limiting example, the RAN architecture 500 includes a central unit (“CU”) 505. According to some embodiments, the CU is a server or other logical node of the computing network that operates at the core of the RAN architecture 500. The CU 505 handles high-level functions of the network, including but not limited to managing radio access network sharing, mobility control, and session management among multiple eNBs of the network.

[0059] like Figure 5 As shown, CU 505 is communicatively connected to a network via a CU (e.g., Figure 4 The network interface of the communication unit 420 in the middle sends and receives data to and from multiple digital units (“DU”) 510a to 510n. In this illustrative example, DU 510a-510n are base stations or eNBs (e.g., Figure 2 In the eNB 102), each of DU 510a-510n directs to one or more user equipments (e.g., Figure 3 The UE 116 in the system provides wireless connectivity.

[0060] In addition, such as Figure 5 As illustrated in the illustrative examples, each of the DUs 510a-510n includes, or at least communicatively connects to, one or more Remote Radio Headers (RRHs) 515a-515n and 520a-520n. According to various embodiments, each RRH provides power transmission signals to one or more antennas, creating an area of ​​radio coverage—also referred to as a cell—within which the UE can receive signals from the DU and transmit data to the DU via a radio beam established between the RRH and the UE. Each of the RRHs 515a-515n and 520a-520n can control one or more operating parameters that determine the effective area of ​​the radio coverage provided by the DU.

[0061] Figure 6A and 6B Two examples of operating parameters are shown, which can be adjusted by one or more RRHs to change the effective radio coverage area (or "cell") of the DU. According to some embodiments of this disclosure, changing the radio coverage area of ​​a DU in a wireless network can balance the load of DUs across the network, such that each node or DU in the network can provide approximately the same number of resource blocks to each connected device.

[0062] refer to Figure 6A This is a non-limiting example illustrating how the Cell Individual Offset (“CIO”) can be adjusted to change the effective coverage area of ​​an eNB. According to some embodiments, the effective coverage area of ​​an eNB is defined as an area where the received power of the signal received at the UE from the eNB, relative to the received power of the signal received at the UE from one or more neighboring eNBs, satisfies the condition that the UE should not be transferred or handed over to a neighboring eNB. Since the condition for transferring the UE from one eNB is controlled by operator-regulated parameters, the effective coverage area of ​​the cell is an adjustable parameter. CIO is one of at least two parameters used to control the handover point of the eNB and implicitly control the effective coverage area of ​​the eNB.

[0063] In this illustrative example, a first eNB 601 and a second eNB 603 are shown in the figure. A first ellipse 605 shows the radio coverage area of ​​the first eNB 601, and a second ellipse 607 shows the radio coverage area of ​​the second eNB 603. According to some embodiments, the boundaries of the respective coverage areas of the first eNB 601 and the second eNB 603 are defined according to the following mathematical formula 1 (e.g., Formula 1), which describes the standard or A3 event for handover, in which the UE moves from the coverage area of ​​the first eNB to the second eNB.

[0064]

Mathematical Formula 1

[0065]

[0066] in, It is a measure of the received power value of the serving cell, and It is a measure of the received power of neighboring cells. It is the CIO value between cell i and cell j, and H i This is the value of the hysteresis constant to avoid frequent handovers between cells i and j. When the difference in received power between the UE and cell j exceeds the value of CIO plus the hysteresis constant, the UE will switch from cell i to cell j.

[0067] As the UE's received power decreases proportionally to its distance from the eNB, adjusting the CIO value can change the distance from the eNB required to satisfy the handover conditions. For example... Figure 6A As shown, the first CIO value generates a first effective coverage area 609, and the second CIO value generates a second effective coverage area 611.

[0068] Figure 6B This illustrates how electronic tilt (“E-tilt”) according to some embodiments of the present disclosure can be an additional parameter that adjusts the effective coverage area of ​​the eNB and implicitly adjusts the load on the eNB.

[0069] A set of controllable mechanical actuators is provided for the antennas of certain eNBs, which can perform azimuth adjustments to the antennas, thereby controlling the range of the RF beam generated by the eNB trained above, at, or below the horizon. By increasing the value of the E-tilt angle (e.g., training the range of the RF beam at an angle above or below the horizon), the broadcast power of the eNB can be concentrated over a smaller coverage area. Similarly, by decreasing the value of the E-tilt angle (e.g., training the RF beam down to or below the horizon), the broadcast power of the eNB can be distributed over a larger coverage area.

[0070] refer to Figure 6BAn illustrative example is the eNB 651 with a multi-antenna array (e.g., Figure 2 The eNB 102 projects a beam with a lobe shape (including lobe 653). As shown in the figure, by setting the E-tilt value to a first value of 4 degrees above the horizontal line, the radio beam of lobe 653 covers a first coverage area 655. By increasing the E-tilt value to 9 degrees above the horizontal line, the radio beam of lobe 653 covers a larger second coverage area 657.

[0071] Figure 7 Examples of an architecture 700 for implementing artificial intelligence (AI)-based network parameter optimization according to various embodiments of the present disclosure are shown.

[0072] refer to Figure 7 As a non-limiting example, architecture 700 includes the physical element portion of the eNB and one or more computing platforms 701 (e.g., Figure 5 CU 505 or Figure 4 In the feedback / decision loop between servers 400 in the eNB, computing platform 701 implements a deep reinforcement learning model. The computing platform 701 receives observation data as input from the RF hardware (e.g., DU and RRH) of the eNB and outputs actions including the values ​​of parameters (e.g., CIO and E-tilt) of the RF hardware.

[0073] As in Figure 7 As shown in the illustrative example, architecture 700 also includes at least one digital unit 703 (“DU”) communicatively connected to computing platform 701 (e.g., Figure 5 (DU 510a in the original text). In addition to providing control over one or more remote radio heads 705a-705n, DU 703 is configured to acquire observation data about the current operational status of the eNB and provide it to the computing platform 701. Examples of observation data that can be acquired by DU 703 and sent to the computing platform 701 include, but are not limited to, the current value of physical resource block (“PRB”) utilization, the edge user ratio, and a measure of throughput through the DU. As used in this disclosure, the edge user ratio includes the ratio of users (i.e., UEs and other devices currently attached to and communicating with the eNB) who can switch to another eNB if one or more network parameters (such as CIO) change, relative to the total number of users in the cell. Figure 7 In the illustrative example, DU 703 is further configured to receive actions from computing platform 701 and control one or more RRH 705a-705n according to the received actions.

[0074] In some embodiments, architecture 700 includes one or more remote radio headends (RRHs) 705a-705n that generate RF signals and receive RF signals through multiple antennas. The operation of the RRHs 705a-705n (specifically, the area of ​​radio coverage provided by the eNB) can vary depending on the RF parameters of the RRHs 705a-705n, such as CIO and E-tilt.

[0075] Figure 8 The operation of an example method 800 for performing network parameter optimization according to various embodiments of the present disclosure is illustrated. References Figure 8 The described operations can be performed on any suitable network architecture including the following computing platforms (e.g., Figure 7 The computing platform is executed in the architecture 700, and is capable of implementing a DRL model that provides hardware communication connectivity with the eNB.

[0076] refer to Figure 8 In a non-limiting example, at operation 805, a parameter optimization process for optimizing the RF parameters of one or more eNBs or cells of a wireless network is triggered at a computing platform implementing the DRL model. In some embodiments, the optimization process is triggered based on a clock indicating that a predetermined interval (one hour or one day) has elapsed since the last iteration of the parameter optimization process. In some embodiments, the optimization process is triggered by other processes managed by the computing platform, such as determining that a particular eNB or cell of the wireless network is a suitable candidate for parameter optimization.

[0077] According to some embodiments, in operation 810, a computing platform (e.g., a server) reads observation data from the DU of the eNB, whose RF parameters will be optimized via method 800. The observation data includes, but is not limited to: the value of PRB utilization at the eNB (i.e., which portion of the available time-frequency block is currently in use), the ratio of edge users (i.e., the ratio of users potentially switching to neighboring cells to the total number of users), and the throughput of the DU (e.g., the number of bytes of data sent and received per second). Other indicators of network performance or load per cell may be included in the observation data read in operation 810.

[0078] As another example of observation data read from Operation 810, consider a network comprising N cells, where the load of the N cells at a given time t can be represented as ρ1. t , ..., ρ N t And the ratio of edge users at time t can be expressed as Therefore, for a given time t, the observation information read by the computing platform in operation 810 can be represented as state s according to the following mathematical formula 2 (e.g., formula 2). tValue:

[0079]

Mathematical Formula 2

[0080]

[0081] refer to Figure 8 An illustrative example is given in operation 815, where observation data is fed into one or more deep reinforcement learning (DRL) models to obtain a set of actions. In this example, the DRL model comprises a neural network that has been trained with the set of observation data. According to various embodiments, the DRL model receives the observation data output at operation 810 as input, and in the action space a t The internal output is associated with one or more actions by the value of an RF parameter such as E-tilt or CIO, where the action space a t It can be represented as:

[0082]

Mathematical Formula 3

[0083]

[0084] in, It is between community i and community j It is the tilt angle of cell i. In short, the DRL model outputs a set of candidate actions from the observed data and selects one or more candidate actions to provide RF parameters, which are used to reconfigure one or more eNBs based on the expected reward value calculated in subsequent operations of method 800.

[0085] According to various embodiments, in operation 820, the server or other computing platform reads and calculates the expected reward associated with the action obtained in operation 815. In some embodiments, the calculated expected reward associated with the pairing of state s and action a is based on the maximum load of all cells, and the purpose of training the DRL model is to optimize the RF parameters of the cells to minimize the maximum load of all cells. In this case, the expected reward value can be represented according to the following mathematical formula 4 (e.g., Formula 4):

[0086]

Mathematical Formula 4

[0087]

[0088] In some embodiments, the calculated expected reward associated with a given state s and action a is based on the sum of the maximum loads across the cells and the throughput across the given cell, with the aim of optimizing the cell's RF parameters to minimize the sum of the maximum loads across the cells and maximize the cell throughput. In this case, the value of the expected reward r can be expressed according to the following mathematical formula 5 (e.g., Formula 5).

[0089] [Mathematical Formula 5]

[0090]

[0091] in, It is the average cell throughput.

[0092] refer to Figure 8 In a non-limiting example, at operation 825, one or more network parameters, such as E-Tilt or CIO, are reconfigured based on the action and the expected reward associated with the action performed at operation 820. At operation 830, the expected rewards from previous iterations of operations 805-825 and the observation data obtained at operation 810 are added to the corpus of training data for the DRL model, and the DRL model is further tuned. By iterating through operations 805-830, the DRL model can be progressively trained to obtain actions associated with the observation data to optimize certain RF parameters (in this example, E-Tilt and CIO). With sufficient training, embodiments according to this disclosure can provide a significant improvement in throughput without an increase in average maximum load. Table 1 below reports, according to reference... Figure 8 The results of the RF modulation test implemented using the described method.

[0093] Table 1

[0094]

[0095] As shown above, the tests demonstrate that training and using DRL models to tune the CIO and E-Tilt of one or more network nodes can significantly improve the overall performance of the network. For example, the throughput of the network using DRL models to tune CIO and E-Tilt is increased by 10 Mbps compared to the same network without any tuning.

[0096] Figures 9A to 9C The operation of example methods for selectively optimizing cells of a wireless network according to various embodiments of the present disclosure is illustrated.

[0097] The increased load capacity and connectivity of modern wireless networks are largely due to the significantly higher frequencies of the RF spectrum used compared to the 800 MHz frequencies of previous generations of wireless communication. While these higher frequencies, sometimes referred to as "mmWave" frequencies, offer new, previously untapped sources of bandwidth, the physical characteristics of wave propagation dictate the cost of this spectrum increase. Specifically, all else being equal, high-frequency radio waves dissipate faster over a transmission area than low-frequency radio waves. Similarly, all else being equal, an increase in carrier frequency means more eNBs are needed to cover a given area. As the number of eNBs and transceiver nodes in the network increases, the computational burden of optimizing RF parameters to balance network load also increases. Therefore, with the increasing number of eNBs, cell selection for RF parameter optimization becomes an increasingly challenging technical problem.

[0098] Figure 9A An example of a method 900 for selecting and optimizing cells for RF parameter optimization according to various embodiments of the present disclosure is shown.

[0099] like Figure 9A As shown in the diagram, in operation 905, the network optimization server (e.g., Figure 4 The server 400 in the middle) or controls multiple cells (e.g., Figure 5 Other back-end computing platforms (CU 505) in the illustrative example obtain current load data for multiple cells of the wireless network. In this example, the current load data includes the PRB utilization value for each of the multiple cells. In some embodiments, operation 905 is triggered by the expiration of a timer (e.g., two hours since the last network optimization operation). In some embodiments, operation 905 is triggered by meeting predetermined conditions (e.g., the number of devices connected to the network exceeds a threshold number).

[0100] like Figure 9A As illustrated in the illustrative example, in operation 910, the server selects a target cell s from a plurality of cells of current load data received in operation 905. According to various embodiments, the target cell s includes one or more cells whose current load data (e.g., data received in operation 905) value exceeds a first predetermined threshold.

[0101] According to various embodiments, in operation 915, the server or other computing platform selects a defined set S of neighboring cells of the target cell from a list of neighboring cells of the target cell. According to various embodiments, the contents of the neighboring cell list may be predetermined or may include the output of a cell selection model that has been repeatedly trained on network data. In operation 920, the server calculates the value of at least one utilization parameter of the target cell as a target value for new load through the target cell. According to embodiments, the value of the utilization parameter may be determined by (e.g., as referenced in this disclosure) Figure 8 The action output by the DRL model as described.

[0102] In some embodiments, at least one utilization parameter includes one or more values ​​of the physical resource block (PRB) utilization rate of the target cell. In various embodiments, at least one utilization parameter includes the ratio of cell edge devices.

[0103] refer to Figure 9A In a non-limiting example, in operation 925, the server determines the CIO value and E-tilt value of the target cell based on calculated utilization parameters of the target cell. In some embodiments, the CIO value and E-tilt value can be determined using a DRL model that has been trained on network observation data and iteratively optimized to determine the most efficient combination of E-tilt and CIO for achieving a specific utilization objective. In some embodiments, the CIO value and E-tilt value can be calculated separately on the server or obtained from a pre-stored data structure such as a lookup table.

[0104] In operation 930, one or more physical layer parameters of the target cell are configured based on the CIO and E-Tilt values ​​determined in operation 925. In some embodiments, the server or computing platform that has performed operation 925 sends the determined CIO and E-Tilt values ​​to the DU of the cell, which determines the control parameters for RRH and the tilt actuators for the cell's antennas. In various embodiments, the server also determines the physical layer parameters of the target cell and configures the target cell remotely.

[0105] Figure 9B Examples of various embodiments of the present disclosure are shown for determining utilization parameters for RF parameter optimization and configuring further operations of the cell using the optimized RF parameters. References Figure 9B The described operations can be performed as part of a loop within larger or more conventional cell selection and optimization methods (e.g., Figure 9A The operation (920-930) of method 900 in the middle is executed.

[0106] As noted in other parts of this disclosure, as the number of neighboring cells in the network increases, the computational load that may be associated with periodically optimizing the RF parameters of the cells also increases, due to the increase in the number of cells and the overlapping coverage area, at which point it becomes possible to adjust the RF parameters to redistribute the network load.

[0107] refer to Figure 9B An illustrative example, in operation 940, the server (e.g., Figure 4 Server 400) or equivalent computing platform (e.g., Figure 5 CU 505 in the network has selected a target cell s based on current PRB data obtained from the network's cells, and has further selected a set S of neighboring cells of the target cell. According to some embodiments, the set S of neighboring cells of the target cell is based on (e.g., as referenced in...) Figure 9A The neighboring cell list is selected as described in operation 915. In operation 940, the value of σ(S∪s) (where σ(S∪s) includes a measure of the standard deviation of the PRB utilization of the union of S and s) is calculated and compared with a threshold of σ. In other words, the load variation (expressed as PRB utilization) between the target cell s and the cells in the set of neighboring cells S is determined. If the value of σ(S∪s) exceeds the threshold of σ, it indicates a potential remediable imbalance in the distribution of network load in the cells of S and s, and proceeds to operation 945 according to certain methods of this disclosure.

[0108] According to various embodiments, in operation 945, because the standard deviation of the PRB utilization of the entire set of cells in (S∪s) exceeds a standard deviation threshold, the server determines a value for at least one utilization parameter for each cell in (S∪s). In some embodiments, the at least one utilization parameter includes one or more values ​​of the Physical Resource Block (PRB) utilization of the target cell. In various embodiments, the at least one utilization parameter includes the ratio of cell edge devices.

[0109] like Figure 9B As illustrated in the illustrative example, in operation 950, the server determines the values ​​of CIO and E-Tilt based on at least one cell in a union set with utilization parameters S and s. According to some embodiments, the values ​​of CIO and E-Tilt can be determined by applying the utilization parameters to a DRL model trained with network data to obtain model-based trained CIO and E-Tilt values ​​that provide the maximum reward in mitigating network load. In some embodiments, the CIO and E-Tilt values ​​based on network utilization parameters are calculated separately or obtained from a lookup table or similar data source.

[0110] In operation 955, the physical layer parameters of the serving cell (S∪s) are configured based on the CIO and E-Tilt values ​​determined in operation 950. In some embodiments, the server or computing platform that has performed operation 950 sends the determined CIO and E-Tilt values ​​to the DU of the cell, which determines the control parameters for RRH and the tilt actuators for the cell's antennas. In various embodiments, the server also determines the physical layer parameters of the target cell and remotely configures the target cell.

[0111] Figure 9C Examples of cell operation based on various embodiments of the present disclosure are described, including determining utilization parameters for RF parameter optimization and configuring the cell using the optimized RF parameters. References Figure 9C The described operations can be performed as part of a loop within a larger or more conventional cell selection and optimization approach (e.g., Figure 9A The operation (920-930) in method 900 is executed. Simply put, Figure 9B This describes the operation when the load distribution between cells S and s (represented by the standard deviation of PRB utilization relative to a threshold) is wide enough to justify optimizing the RF parameters of all cells in S and s. Figure 9C The opposite scenario is described, where the load distribution between cells S and s (again, represented by the standard deviation of PRB utilization relative to a threshold) is narrower, and it is not necessary to optimize the RF parameters on all cells of S and s. This improves the efficiency and effectiveness of the server as a tool for balancing wireless network load, as RF parameter optimization on cells that do not currently require optimization can be avoided.

[0112] refer to Figure 9C Non-restrictive examples, such as, are given here. Figure 9B As shown, in operation 940, the server (e.g., Figure 4 Server 400) or equivalent computing platform (e.g., Figure 5 CU 505 in the network has selected a target cell s based on current PRB data obtained from the network cells, and has further selected a set S of neighboring cells of the target cell. According to some embodiments, the set S of neighboring cells of the target cell is based on (e.g., as referenced in...) Figure 9A The neighboring cell list is selected (as described in operation 915). In operation 940, the value of σ(S∪s) (where σ(S∪s) includes a measure of the standard deviation of the PRB utilization of the union of S and s) is calculated and compared with a threshold for σ. In other words, the load variation (represented by PRB utilization) between the target cell s and the cells in the set of neighboring cells S is determined.

[0113] In this example, because the value of σ(S∪s) is less than the threshold of σ, the method continues to operation 960, in which the server determines that the cell of S has the highest PRB usage value. In operation 965, the server selects... This is a subset of cells in S that have been removed from the set of cells identified as having the highest PRB usage values ​​(e.g., in Operation 960). In simpler terms, in Operation 965, cells in S with the highest current load are excluded from the set of candidate cells for optimization, so that RF parameter optimization can focus on shifting network load to less-used cells in S.

[0114] During operation 970, the server recalculates the standard deviation of PRB utilization, but this time it is for... The union of s and σ is then compared again with the standard deviation value of σ. If the value of σ is lower than the threshold of σ, the server returns operation 960 to determine... The cell with the highest PRB utilization is selected, and operations 965 and 970 are repeated with a further reduced subset of cells. According to various embodiments, operations 960 to 970 may be cyclical in multiple iterations until the set of cells consisting of some subsets of S and s has a measured standard deviation of PRB utilization that exceeds a specified threshold.

[0115] refer to Figure 9C Non-restrictive examples, wherein the determined If the value is less than the threshold (or if operation 960 to 970 has been iterated more than once), then select... A subset is used for RF parameter optimization, and the server performs operations to determine the value of at least one utilization parameter, determine the CIO value and E-Tilt value based on at least one utilization parameter, and configure the physical layer parameters of the cells selected for RF parameter optimization (e.g., Figure 9B Operations 950 and 955 in the middle).

[0116] The flowcharts above illustrate example methods that can be implemented according to the principles of this disclosure, and various modifications can be made to the methods shown in the flowcharts herein. For example, although shown as a series of steps, the individual steps in each diagram may overlap, appear in parallel, appear in different orders, or appear multiple times. In another example, steps may be omitted or replaced by other steps.

[0117] The lack of description in this application should not be construed as implying that any particular element, step, or function is essential and must be included within the scope of the claims. Although this disclosure has been described with reference to exemplary embodiments, various changes and modifications may be suggested to those skilled in the art. This disclosure is intended to include such changes and modifications that fall within the scope of the appended claims. The lack of description in this application should not be construed as implying that any particular element, step, or function is essential and must be included within the scope of the claims. The scope of the claimed subject matter is defined solely by the claims.

Claims

1. A method for performing mobility load balancing in a server, the method comprising: Receives load data from each of the multiple cells in a wireless communication network; A target cell is selected from the plurality of cells, wherein the load data value of the target cell exceeds a first predetermined threshold. Select multiple neighboring cells from the list of neighboring cells corresponding to the target cell as a set of neighboring cells of the target cell; Determine the standard deviation between the load data of the target cell and the load data of the selected neighboring cells; In response to the fact that the standard deviation between the load data of the target cell and the load data of the selected neighboring cells is less than a second predetermined threshold, the first neighboring cell with the largest load data in the set of neighboring cells is determined; By excluding the first neighboring cell from the set of neighboring cells, at least one neighboring cell is selected as a subset of the set of neighboring cells; Determine the standard deviation of the load data of the target cell from the load data of at least one selected neighboring cell; In response to the standard deviation of the load data of the target cell from the load data of at least one selected neighboring cell exceeding the second predetermined threshold, the value of at least one utilization parameter of the target cell is calculated based on the load data of the target cell and the load data of at least one selected neighboring cell, wherein the value of at least one utilization parameter of the target cell includes the value of the physical resource block (PRB) utilization rate of the target cell. The server determines the cell-specific offset (CIO) value and electronic tilt (E-tilt) value of the target cell based on the calculated values ​​of at least one of the utilization parameters of the target cell; and Send the determined CIO value and E-tilt value of the target cell to the target cell.

2. The method according to claim 1, wherein the value of the at least one utilization parameter of the target cell includes the ratio of cell edge user equipment (UE).

3. The method according to claim 1, wherein, Determining the CIO and E-tilt values ​​also includes: In response to the standard deviation between the load data of the target cell and the load data of the selected neighboring cells exceeding the second predetermined threshold, the value of at least one utilization parameter of the target cell is calculated based on the load data of the target cell and the load data of the selected neighboring cells; The server determines the CIO value and E-tilt value of the target cell based on the calculated values ​​of at least one utilization parameter of the target cell; and Send the determined CIO value and E-tilt value of the target cell to the target cell.

4. The method according to claim 1, wherein, Based on the fact that the standard deviation between the load data of the target cell and the load data of at least one neighboring cell is less than the second predetermined threshold, an iterative selection loop is performed for the subset.

5. The method according to claim 1, wherein, At least one of the CIO value and E-tilt value of the target cell is determined by applying the value of the at least one utilization parameter using a deep reinforcement learning (DRL) model, and the method further includes: For the target cell and the selected set of neighboring cells, observation data is read from at least one digital unit (DU) and a remote radio headend (RRH). The observed data is fed into the neural network to obtain actions; Determine the value of the reward associated with the action; and The target cell's CIO value or E-tilt value is determined based on the action with the highest reward value.

6. The method according to claim 5, wherein, The observation data includes PRB utilization data, edge user ratio, and throughput data.

7. A server, the server comprising: A communication unit configured to receive load data from each of a plurality of cells in a wireless communication network; as well as A processor, operably connected to the communication unit, is configured to: A target cell is selected from the plurality of cells, wherein the load data value of the target cell exceeds a first predetermined threshold. Select multiple neighboring cells from the list of neighboring cells corresponding to the target cell as a set of neighboring cells of the target cell; Determine the standard deviation between the load data of the target cell and the load data of the selected neighboring cells; In response to the fact that the standard deviation between the load data of the target cell and the load data of the selected neighboring cells is less than a second predetermined threshold, the first neighboring cell with the largest load data in the set of neighboring cells is determined; By excluding the first neighboring cell from the set of neighboring cells, at least one neighboring cell is selected as a subset of the set of neighboring cells; Determine the standard deviation of the load data of the target cell from the load data of at least one selected neighboring cell; In response to the standard deviation of the load data of the target cell from the load data of at least one selected neighboring cell exceeding the second predetermined threshold, the value of at least one utilization parameter of the target cell is calculated based on the load data of the target cell and the load data of at least one selected neighboring cell, wherein the value of at least one utilization parameter of the target cell includes the value of the physical resource block (PRB) utilization rate of the target cell. The server determines the cell-specific offset (CIO) value and electronic tilt (E-tilt) value of the target cell based on the calculated values ​​of at least one of the utilization parameters of the target cell; and Send the determined CIO value and E-tilt value of the target cell to the target cell.

8. The server according to claim 7, wherein, The value of at least one utilization parameter of the target cell includes the ratio of cell edge user equipment (UE).

9. The server according to claim 7, wherein, To determine the CIO value and the E-tilt value, the processor is further configured to: In response to the standard deviation between the load data of the target cell and the load data of the selected neighboring cells exceeding the second predetermined threshold, the value of at least one utilization parameter of the target cell is calculated based on the load data of the target cell and the load data of the selected neighboring cells; The server determines the CIO value and E-tilt value of the target cell based on the calculated value of at least one utilization parameter of the target cell; as well as Send the determined CIO value and E-tilt value of the target cell to the target cell.

10. The server according to claim 7, wherein, Based on the fact that the standard deviation between the load data of the target cell and the load data of at least one neighboring cell is less than the second predetermined threshold, an iterative selection loop is performed for the subset.

11. The server according to claim 7, wherein, At least one of the CIO value and E-tilt value of the target cell is determined by applying the value of the at least one utilization parameter using a deep reinforcement learning (DRL) model, and the processor is further configured to: For the target cell and the selected set of neighboring cells, observation data is read from at least one digital unit (DU) and a remote radio headend (RRH). The observed data is fed into the neural network to obtain actions; Determine the value of the reward associated with the action; as well as The target cell's CIO value or E-tilt value is determined based on the action with the highest reward value.

12. The server according to claim 11, wherein, The observation data includes PRB utilization data, edge user ratio, and throughput data.

13. A non-transitory computer-readable medium comprising program code, said program code, when executed by a processor of a server, causing the server to: The server receives load data from each of the multiple cells in the wireless communication network via its network interface. Select the target cell from the plurality of cells, wherein... The load data value of the target cell exceeds a first predetermined threshold; Select multiple neighboring cells from the list of neighboring cells corresponding to the target cell as a set of neighboring cells of the target cell; Determine the standard deviation between the load data of the target cell and the load data of the selected neighboring cells; In response to the fact that the standard deviation between the load data of the target cell and the load data of the selected neighboring cells is less than a second predetermined threshold, the first neighboring cell with the largest load data in the set of neighboring cells is determined; By excluding the first neighboring cell from the set of neighboring cells, at least one neighboring cell is selected as a subset of the set of neighboring cells; Determine the standard deviation of the load data of the target cell from the load data of at least one selected neighboring cell; In response to the standard deviation of the load data of the target cell from the load data of at least one selected neighboring cell exceeding the second predetermined threshold, the value of at least one utilization parameter of the target cell is calculated based on the load data of the target cell and the load data of at least one selected neighboring cell, wherein the value of at least one utilization parameter of the target cell includes the value of the physical resource block (PRB) utilization rate of the target cell. The cell-specific offset (CIO) value and electronic tilt (E-tilt) value of the target cell are determined based on the calculated values ​​of at least one of the parameters used in the target cell; and Send the determined CIO value and E-tilt value of the target cell to the target cell.

Images