Apparatus and method for providing maintenance planning in a telecommunications network

Abstract

An apparatus and method for selecting an upgrade sequence for cell sites in a radio access network is provided, the apparatus comprising: a memory storing instructions; and at least one processor configured to execute the instructions to: determine, for each pair of cell sites among a plurality of cell sites, a pairing score based on a coverage overlap between the cell sites, divide the plurality of cell sites into at least two batches based on the determined pairing score for each pair of cell sites, and determine which cell sites of the plurality of cell sites may be upgraded simultaneously based on the division into the at least two batches.

Description

[Technical Field]

[0001] Apparatus and methods according to example embodiments of the present disclosure relate to maintenance planning for telecommunications networks, and more particularly to a method for selecting an upgrade sequence for cell sites in a radio access network for updating the network infrastructure. [Background technology]

[0002] Downtime loss during network maintenance negatively impacts both random access network (RAN) operators and users alike. Because downtime, even short in duration, can have a substantial negative impact on RAN users, RAN operators strive to operate the RAN without downtime. However, in practice, it is often necessary to perform security-critical updates to the RAN infrastructure. Therefore, RAN operators must shut down cell sites during RAN operation to perform critical updates, risking adverse impacts to their user base. Therefore, minimizing the negative impact of downtime, especially during cell site maintenance, is paramount for optimal, up-to-date operation of RAN networks.

[0003] In the related art, techniques for minimizing adverse impacts include strategies that focus on upgrading a small number of cell sites at a time (i.e., serially upgrading a small number of simultaneously upgraded cell sites in a network reduces the risk of adverse impacts). This serial upgrade in the related art results in a multi-day upgrade schedule. In the related art, random selection of cell sites to be upgraded simultaneously can speed up the upgrade schedule, but the adverse impacts of randomly selected cell sites being upgraded simultaneously can be significant and unsatisfactory for both network operators and RAN users. For example, random selection of cell sites for simultaneous upgrades can cause adjacent cell sites with overlapping coverage areas to both be shut down at the same time, leaving subscribers in those areas with no coverage at all. Summary of the Invention [Means for solving the problem]

[0004] According to embodiments, a system and method are provided for selecting an upgrade sequence for cell sites in a radio access network, where the upgrade sequence selection takes into account coverage overlap when determining cell sites for simultaneous upgrade. As a result, the system and method of example embodiments can achieve significantly faster execution of maintenance schedules (i.e., upgrade schedules) and minimize additional risk of adverse impacts to the RAN (i.e., to RAN users).

[0005] According to an embodiment, an apparatus for selecting an upgrade sequence for cell sites in a wireless access network includes a memory that stores instructions and at least one processor, wherein the at least one processor is configured to execute the instructions to: determine, for each pair of cell sites from among a plurality of cell sites, a pairing score based on coverage overlap between the cell sites; divide the plurality of cell sites into at least two batches based on the determined pairing score for each pair of cell sites; and determine which cell sites of the plurality of cell sites can be upgraded simultaneously based on the division into the at least two batches.

[0006] The at least one processor may be further configured to execute instructions to repeat, in each successive batch, determining a pairing score for each cell site pair in the batch and dividing the cell sites in the batch based on the determined pairing score for each cell site pair in the batch until a predetermined number of batches and / or network segments is reached.

[0007] The at least one processor may be further configured to execute instructions to partition the plurality of cell sites based on the determined pairing scores by using a graph neural network to partition the cell site pairs.

[0008] The at least one processor may be further configured to execute instructions to randomly split cell site pairs having pairing scores below a predetermined threshold.

[0009] The at least one processor may be further configured to execute instructions to randomly divide the cell sites in the wireless access network into initial batches a predetermined number of times, such that prior to the initial determination of pairing scores and division into batches, an initial determination of pairing scores is performed on the initial batches.

[0010] The at least one processor may be further configured to execute instructions to split the plurality of cell sites based on the determined pairing scores by using a graph neural network to split the cell site pairs until a predetermined number of batches and / or network segments is reached.

[0011] The pairing score may be determined based on the coverage overlap weighted by at least one weighting factor, and the at least one weighting factor for determining the pairing score may include at least one criterion of at least one of user count data, throughput data, and / or handover success data.

[0012] The at least one processor may be further configured to execute instructions to update each weight of the at least one weighting coefficient based on the at least one feedback parameter.

[0013] According to an embodiment, a method for selecting an upgrade sequence for cell sites in a radio access network includes: determining a pairing score for each cell site pair from among a plurality of cell sites based on coverage overlap between the cell sites; dividing the plurality of cell sites into at least two batches based on the determined pairing score for each cell site pair; and determining which cell sites of the plurality of cell sites can be upgraded simultaneously based on the division into the at least two batches.

[0014] The method may further include repeating, within each successive batch, determining a pairing score for each cell site pair in the batch and dividing the cell sites in the batch based on the determined pairing score for each cell site pair in the batch until a predetermined number of batches and / or network segments is reached.

[0015] The method may further include partitioning the plurality of cell sites based on the determined pairing scores by using a graph neural network to partition the cell site pairs.

[0016] The method may further include randomly splitting cell site pairs having pairing scores below a predetermined threshold.

[0017] The method may further include randomly dividing the cell sites in the wireless access network into initial batches a predetermined number of times, prior to the initial determination of the pairing scores and division into batches, such that the initial determination of the pairing scores is performed on the initial batches.

[0018] The method may further include splitting the plurality of cell sites based on the determined pairing scores by using a graph neural network to split the cell site pairs until a predetermined number of batches and / or network segments is reached.

[0019] The pairing score may be determined based on the coverage overlap weighted by at least one weighting factor, and the at least one weighting factor may include at least one of a factor of user count data, a factor of throughput data, or a factor of handover success data.

[0020] The method may further include updating each weight of the at least one weighting factor based on the at least one feedback parameter.

[0021] According to an embodiment, a non-transitory computer-readable storage medium has stored thereon instructions executable by at least one processor to perform a method for selecting an upgrade sequence for cell sites in a wireless access network, the method including: determining, for each pair of cell sites from among a plurality of cell sites, a pairing score based on coverage overlap between the cell sites; dividing the plurality of cell sites into at least two batches based on the determined pairing score for each pair of cell sites; and determining which cell sites of the plurality of cell sites can be upgraded simultaneously based on the division into the at least two batches.

[0022] Additional aspects will be set forth in part in the description that follows, and in part will be apparent from the description, or may be learned by practice of presented embodiments of the present disclosure. [Brief explanation of the drawings]

[0023] Features, aspects, and advantages of certain exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which like reference numerals refer to like elements.

[0024] [Figure 1] FIG. 2 is a diagram of exemplary components of a device according to one embodiment. [Figure 2] 1 illustrates a flow diagram of a method for selecting an upgrade sequence for cell sites in a wireless access network, according to one or more embodiments. [Figure 3A] 1 illustrates an example for selecting an upgrade sequence for cell sites in a radio access network, according to one embodiment. [Figure 3B] 1 illustrates an example for selecting an upgrade sequence for cell sites in a radio access network, according to one embodiment. [Figure 3C] 1 illustrates an example for selecting an upgrade sequence for cell sites in a radio access network, according to one embodiment. [Figure 3D] 1 illustrates an example for selecting an upgrade sequence for cell sites in a radio access network, according to one embodiment. [Figure 4] 10 illustrates updating at least one weighting coefficient based on a feedback parameter, according to one embodiment. [Figure 5] 1 illustrates the effect of different weighting factors on a method for selecting an upgrade sequence for cell sites in a wireless access network, according to one or more embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0025] The following detailed description of the exemplary embodiments refers to the accompanying drawings, in which the same reference numbers in different drawings may identify the same or similar elements.

[0026] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit implementations to the precise form disclosed. Modifications and variations are possible in light of the above disclosure or may be acquired from practice of an implementation. Moreover, one or more features or components of one embodiment may be combined with or incorporated into other embodiments (or one or more features of other embodiments). Additionally, in the flowcharts and descriptions of operations provided below, it should be understood that one or more operations may be omitted, one or more operations may be added, one or more operations may occur (at least partially) concurrently, or the order of one or more operations may be rearranged.

[0027] It will be apparent that the systems and / or methods described herein may be implemented in different forms of hardware, firmware, or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods is not limiting of the implementation. Thus, the operation and behavior of the systems and / or methods have been described herein without reference to specific software code. It should be understood that software and hardware may be designed to implement the systems and / or methods based on the description herein.

[0028] Although particular combinations of features are recited in the claims and / or disclosed herein, these combinations do not limit the disclosure of possible implementations. Indeed, many of these features can be combined in ways not specifically recited in the claims and / or disclosed herein. Although each dependent claim listed below may depend directly on only one claim, the disclosure of possible implementations includes each dependent claim in combination with all other claims in the claim set.

[0029] No element, act, or instruction used herein should be construed as critical or required unless explicitly described as such. Also, as used herein, the articles "a" and "an" are intended to include one or more items and may be used interchangeably with "one or more." Where only one item is intended, the term "one" or similar language is used. Also, as used herein, the terms "has," "have," "having," "include," "including," etc. are intended to be open-ended terms. Furthermore, the phrase "based on" is intended to mean "based at least in part on," unless expressly stated otherwise. Furthermore, phrases such as "at least one of [A] and [B]" or "at least one of [A] or [B]" should be understood to include A only, B only, or both A and B.

[0030] Exemplary embodiments of the present disclosure provide an apparatus, method, and non-transitory computer-readable storage medium for selecting cell sites to be upgraded simultaneously in a Radio Access Network (RAN) upgrade schedule, taking into account the coverage areas of cell sites within the RAN, thereby minimizing the number of devices that are disconnected from the RAN (e.g., have no coverage at all) at any given time.

[0031] 1 is a diagram of example components of a device 100. Device 100 may correspond to a user device 110 and / or a platform 120. As shown in FIG. 1, device 100 may include a bus 110, a processor 120, a memory 130, a storage component 140, an input component 150, an output component 160, and a communication interface 170.

[0032] Bus 110 includes components that enable communication between components of device 100. Processor 120 may be implemented in hardware, firmware, or a combination of hardware and software. Processor 120 may be a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), a microprocessor, a microcontroller, a digital signal processor (DSP), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or another type of processing component. In some implementations, processor 120 includes one or more processors that can be programmed to perform functions. Memory 130 may include random access memory (RAM), read only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, and / or optical memory) that stores information and / or instructions for use by processor 120.

[0033] Storage component 140 stores information and / or software related to the operation and use of device 100. For example, storage component 140 may include a hard disk (e.g., a magnetic disk, optical disk, magneto-optical disk, and / or solid-state disk), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, magnetic tape, and / or another type of non-transitory computer-readable medium and corresponding drive. Input component 150 includes components that enable device 100 to receive information, such as via user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, buttons, switches, and / or a microphone). Additionally or alternatively, input component 150 may include sensors for sensing information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, and / or an actuator). Output components 160 include components that provide output information from device 100, such as a display, a speaker, and / or one or more light-emitting diodes (LEDs).

[0034] Communication interface 170 includes transceiver-like components (e.g., a transceiver and / or a separate receiver and transmitter) that enable device 100 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 170 may enable device 100 to receive information from and / or provide information to another device. For example, communication interface 170 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, a cellular network interface, etc. Device 100 may perform one or more processes described herein. Device 100 may perform these processes in response to processor 120 executing software instructions stored by a non-transitory computer-readable medium, such as memory 130 and / or storage component 140. Computer-readable medium is defined herein as a non-transitory memory device. A memory device may include memory space within a single physical storage device or memory space distributed across multiple physical storage devices.

[0035] The software instructions may be loaded into memory 130 and / or storage component 140 from another computer-readable medium or from another device via communication interface 170. When executed, the software instructions stored in memory 130 and / or storage component 140 may cause processor 120 to perform one or more of the processes described herein.

[0036] Additionally or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to implement one or more processes described herein. Thus, implementations described herein are not limited to any specific combination of hardware circuitry and software.

[0037] The number and arrangement of components shown in Figure 1 are provided as an example. In practice, device 100 may include additional, fewer, different, or differently arranged components than those shown in Figure 1. Additionally or alternatively, a set of components (e.g., one or more components) of device 100 may perform one or more functions that are described as being performed by another set of components of device 100.

[0038] In an embodiment, any one of the operations or processes of FIGS. 2-5 may be implemented by using any one of the elements shown in FIG.

[0039] 2 illustrates a flow diagram of a method for selecting an upgrade sequence for cell sites in a wireless access network, according to one or more embodiments. The method may be implemented by at least one processor executing instructions. The method of FIG. 2 determines the upgrade sequence by determining an optimal batch of cell sites to be upgraded simultaneously.

[0040] Referring to FIG. 2, in step 200, the method may include network segmentation. That is, before initially determining pairing scores in step 201 and dividing into batches based on the pairing scores in step 203, cell sites in a radio access network are divided into initial batches (or into a predetermined number of batches) a predetermined number of times. For example, the division may be random (although in other embodiments, the division may be based on one or more parameters of the coefficients). The initial division of cell sites in a radio access network has the advantage of being able to decompose a large number of cell sites into a smaller number of cell sites in each initial batch, which are processed in subsequent steps. For example, if the number of cell sites to be upgraded is 1,000, step 200 may randomly divide the 1,000 cell sites into four batches of 250 cell sites each. As a result, subsequent processing for each pair of cell sites in the batches can start with a smaller number of cell sites in each batch, thereby reducing the processing load, computational complexity, and processing time. That is, by first dividing the total number of cell sites into multiple batches, the total number of pairs on which subsequent processing (as described below) is performed is reduced because the pairing of cell sites is batch-specific.

[0041] Referring to the following steps in FIG. 2, coverage overlaps that exist between different cell sites are determined to accurately determine which cell sites should belong to which batch in the upgrade plan. For this purpose, network topology data (e.g., key performance indicators (KPIs)) can be used to quantify the coverage overlap between cell sites. As a result, cell sites with overlapping coverage (or significant overlapping coverage) are not placed in the same final batch (i.e., are not upgraded at the same time). This allows devices within the coverage area of ​​a cell site that is shut down due to an upgrade to maintain connectivity to the RAN through the overlapping cell site.

[0042] In step 201, the method may include determining a pairing score for each cell site pair from among the multiple cell sites in each batch (i.e., from the multiple cell sites in the initial batch). The pairing score is determined based on a coverage overlap (e.g., a coverage overlap percentage determined from network topology data) multiplied by a weighted sum of at least one weighting factor. The at least one weighting factor may include at least one RAN performance parameter (i.e., a key performance indicator of the RAN) of the cell site pair related to the impact of simultaneously shutting down the cell site pair. That is, the at least one weighting factor further quantifies the relationship between the cell sites in the cell site pair. The pairing score of the cell site pair is used as a criterion for selecting whether the two cell sites of the cell site pair can be assigned to the same batch (e.g., to the same network segment that is upgraded simultaneously) or whether the two cell sites of the cell site pair can be split into separate batches (e.g., to separate network segments that are upgraded at different times).

[0043] 2, in step 201, the at least one weighting factor may be one of user count data, throughput data, handover success data, etc. For example, relevant factors in determining whether a cell site pair having coverage overlap can be shut down simultaneously include the number of users typically distributed between the two cell sites of the cell site pair, the amount of data traffic that is the throughput at the two cell sites, and the frequency of users traveling between the two cell sites.

[0044] As a result, each weighting factor can improve the determination of the pairing score (i.e., be more accurate in quantifying the coverage overlap of two cell sites). For example, with respect to user count data, a cell site pair hosting 20,000 users should be ranked more importantly than a cell site pair hosting only two users (i.e., a coverage-overlapping pair with a higher total number of connected devices is at greater risk of negative impact from simultaneously upgrading than a coverage-overlapping pair with a lower total number of connected devices). Furthermore, a cell site pair with a large number of successful handovers means that users can easily switch between the cell sites of the cell site pair if one of the cell sites is upgraded (i.e., shut down). As a result, if both cell sites are upgraded simultaneously, users in this cell site pair are more likely to experience connection loss to the RAN. Furthermore, the amount of data traffic in a cell site pair is a performance indicator of the number of users active at the cell sites of that cell site pair. Therefore, data traffic is an important indicator of the number of users who may be exposed to potential negative impacts if both cell sites of a cell site pair are upgraded simultaneously.

[0045] 2, the pairing score between cell sites in a batch (e.g., cell site A and cell site B) can be calculated as a weighted percentage of coverage overlap between the cell sites. If the overlap between cell site A and cell site B is zero, then the pairing score between cell sites A and B is zero. This relationship satisfies the principle that independent cell sites with zero coverage overlap can be upgraded simultaneously because two cell sites do not affect each other (e.g., a cell site in Osaka does not affect a cell in Tokyo).

[0046] Still referring to step 201 of FIG. 2 , in an exemplary embodiment, the method may include updating each weight of at least one weighting factor based on at least one feedback parameter. Thus, each weight of each weighting factor may individually affect the calculation of the pairing score (i.e., the weight may update the weighting factor to make the pairing score more optimal and reduce negative feedback). In an exemplary embodiment, the calculation of the pairing score for a cell site pair may include unidirectional or directional weighting factors. For example, the pairing score for a cell site pair may be defined by the following equation:

[0047] (Formula 1) TIFF0007742502000001.tif48157Where, COVERAGE AB is the coverage overlap percentage between cell site A and cell site B in the cell site pair, USER WEIGHT is the weight applied to the average number of users hosted at cell site A and the number of users hosted at cell site B (i.e., the weighting factor for user count data), THROUGHPUT WEIGHT is the weight applied to the average number of traffic throughput at cell site A and the traffic throughput at cell site B (i.e., the weighting factor for throughput data), and HANDOVER WEIGHT is the weight applied to the average number of handover success rates from cell site A to cell site B and from cell site B to cell site A (i.e., the weighting factor for handover success data).

[0048] 2, in step 202, the method may include dividing the plurality of cell sites into at least two batches based on the pairing score determined for each cell site pair. For example, the division may separate the cell sites of a cell site pair within the batch into two batches (e.g., if there are four initial batches, the division results in eight batches). To this end, a high pairing score for a cell site pair may mean high coverage overlap between the cell sites of the cell site pair. The purpose of the division is to form two or more batches of cell sites, with the cell sites within each batch having minimal coverage overlap with each other (thus minimizing the adverse effects of simultaneous upgrades).

[0049] According to one embodiment, for any pairing score between two cell sites in a batch (e.g., the pairing score between cell site A and cell site B) that is highest (i.e., higher than any other pairing score of the cell site pair in the batch), the two cell sites (e.g., cell site A and cell site B) are split into different batches. For example, cell site pair A-B may have a pairing score associated with a 90% coverage overlap. Thus, splitting cell site pair A-B into separate batches and upgrading cell site A and cell site B at different times minimizes adverse impacts to the RAN (i.e., disconnected RAN users). Next, for the second highest pairing score between two cell sites in a batch (e.g., the pairing score between cell site D and cell site B), the two cell sites (e.g., cell site D and cell site D) are split into different batches. For example, cell site pair D-B may have a pairing score associated with a 70% coverage overlap. Therefore, splitting the cell site pair DB into separate batches and upgrading cell site D and cell site B at different times further minimizes adverse impacts to the RAN (i.e., disconnected RAN users). Thus, the cell sites can be split into two successive batches, starting with the cell site pair with the highest pairing score in the batch, until the cell site pair with the lowest pairing score among the cell site pairs in the batch is reached (i.e., the last cell site pair in the initial batch).

[0050] In step 203, the method may include repeating, within each successive batch, determining a pairing score for each cell site pair in the batch and partitioning the cell sites in the batch based on the determined pairing score for each cell site pair in the batch until a predetermined number of batches (or network segments) and / or a predetermined number of partitions is reached. To this end, multiple successive batches may be generated in an iterative process. As described above, if the partitioning starts with the cell site pair with the highest pairing score in the batch and ends with the last cell site pair with the lowest pairing score in the batch, the successively higher-numbered batches (i.e., the last batch created in the series) may be filled with cell sites of cell site pairs with smaller pairing scores (i.e., the higher the number in the series of batches, the smaller the pairing score between the cell sites in that batch) compared to the successively lower-numbered batches (i.e., the first batch created in the series).

[0051] Therefore, in step 203, the value of the pairing score of the cell site pair being split can be decreased with each iteration of splitting (i.e., with each successive split into two successive batches). As a result, with each split into two successive batches, the RAN network can be further separated into two smaller network segments (i.e., the smaller the network segment, the smaller the pairing score between cell sites within the network segment). This means that the smallest network segment (i.e., batch) can include cell sites with minimal coverage overlap, which has the advantageous effect of achieving minimal adverse impact on the RAN (i.e., RAN users) when upgrading cell sites.

[0052] Still referring to step 203, the method may include a combinatorial optimization algorithm, particularly an algorithm such as a mathematical maximum cut graph algorithm. To use combinatorial optimization for the partitioning in steps 202 and 203, a graph may represent locations between cell sites as nodes. Furthermore, the pairing scores may represent indices of weighted edges in the graph. The graph may be partitioned into subgraphs by pruning as many large edges as possible. In an exemplary embodiment, the method may include partitioning the multiple cell sites based on the determined pairing scores by using a graph neural network to partition the cell site pairs, where the graph neural network may be based on a combinatorial optimization algorithm, particularly an algorithm such as a mathematical maximum cut graph algorithm.

[0053] Still referring to FIG. 2 , in an exemplary embodiment, a network operator may obtain a predetermined tolerance for limiting the scope of optimization to consider the limits of what is economically and technically feasible. To do this, as described in step 200, the method may include dividing cell sites in a radio access network into initial batches (e.g., randomly dividing) a predetermined number of times, such that an initial determination of pairing scores is performed for the initial batches, prior to the initial determination of pairing scores and division into batches. Based on the initial batches generated by the pre-division, the method may include initially dividing a plurality of cell sites in each batch based on the determined pairing scores by using a graph neural network to divide cell site pairs until a predetermined number of batches and / or network segments is reached. For example, if the number of batch divisions is predetermined to be four, the first two divisions may be performed by randomly dividing the cell sites, followed by graph neural network division for two successive batch divisions to obtain faster results for the batch division operation.

[0054] In step 204, cell sites that can be upgraded simultaneously can be determined. To this end, the method may include determining which cell sites of a plurality of cell sites can be upgraded simultaneously based on a division into at least two batches (i.e., based on the batches generated in steps 202 and 203). Each batch may provide a list of cell sites that can be upgraded simultaneously in a radio access network. Furthermore, each batch is assigned an integer corresponding to the batch to which the cell site should belong during network maintenance (e.g., a network software upgrade). The batch number may be independent of the time it takes to execute a maintenance plan (e.g., a network software upgrade) or the order in which batches are executed during network maintenance. As a result, network operators can use the batches to further optimize time management of maintenance plans (i.e., determine the order of batches that allows the fastest work through the maintenance plan). The sequence of cell sites to be upgraded may be based on the sequential order (e.g., chronological order) of the batches executed during the network maintenance plan (e.g., a network software upgrade). To this end, in an exemplary embodiment, the method may include determining which cell sites of a plurality of cell sites may be upgraded simultaneously based on a sequential order of batches executed during network maintenance (e.g., network software upgrades).

[0055] 2, in step 205, the batch may be executed (or provided) as part of a maintenance plan, for example, to upgrade network software. Based on feedback from the execution of the maintenance plan (e.g., based on customer complaints and / or an evaluation of factors contributing to those complaints), the weights may be adjusted to update at least one weighting coefficient, as described in step 201.

[0056] 3A, 3B, 3C, and 3D illustrate an example for selecting an upgrade sequence for cell sites in a radio access network according to one embodiment. Referring to FIG. 3A, for simplicity, the RAN may include only six cell sites A through F. In FIG. 3, cell sites A, E, and B are located closer to each other than cell sites F, D, and C. Compared to the other cell sites, cell site C is the farthest away, and cell sites F and D are located closest to each other. As a result, the pairing score between cell sites A, E, and B may be higher than the pairing score of cell sites F, D, and C, and the cell site pair that may include cell site C has the lowest pairing score.

[0057] 3B, the relationships (i.e., coverage overlap) between the cell sites in FIG. 3A may be represented by graphs. For example, graph (i.e., edge) AF represents the pairing score (i.e., the presence of coverage overlap, and therefore the pairing score) between cell site A and cell site F, graph AE represents the score between cell site A and cell site E, graph DF represents the score between cell site D and cell site F, graph DE represents the score between cell site D and cell site E, graph BD represents the score between cell site B and cell site D, and graph BC represents the score between cell site B and cell site C.

[0058] Referring to Figure 3C, each graph (i.e., cell site pair) in Figure 3B can have a respective pairing score. The terms graph and cell site pair are used interchangeably. For example, graph AF may have a pairing score of 0.8, graph AE may have a pairing score of 0.9, graph DF may have a pairing score of 0.7, graph DE may have a pairing score of 0.6, graph BE may have a pairing score of 0.6, graph BD may have a pairing score of 0.7, and graph BC may have a pairing score of 0.7.

[0059] In FIG. 3C , cell site pair AE has the highest pairing score of 0.9, so cell site A and cell site E are split into different batches. Cell site pair AF has the second highest pairing score of 0.8, so cell site A and cell site F may be split into different batches. Cell site pairs DF, BD, and BC have similar pairing scores. Therefore, cell site D and cell site F may be split into different batches, cell site B and cell site D may be split into different batches, and cell site B and cell site C may be split into different batches. Finally, cell site pair DE and BE, which have the lowest pairing score, are assigned to the same batch in the first iteration of batch splitting.

[0060] Still referring to FIG. 3C, the second batch of the first iteration in FIG. 3C may include cell sites B, E, and F. Cell site pair B-E may have a pairing score of 0.6. Furthermore, because the pairing scores of cell site pair B-F and cell site pair E-F are zero if there are no graphs (i.e., pairing scores) between the cell sites (as described above), cell site pair B-E may have the highest pairing score. Therefore, cell sites B and E may be split into different batches in successive splits. As a result, the second iteration (i.e., splitting cell sites B and E) reduces the pairing score values ​​of the remaining cell site pairs to zero, which may enable simultaneous upgrade of these cell sites. In the example of FIG. 3C, the third iteration of batch splitting may be performed randomly.

[0061] Figure 3D shows the cell site relationships (coverage overlap) after the first iteration of partitioning as shown in Figure 3C. In this example, only the graph between cell sites B and E remains (i.e., cell site pair B-E remains at a pairing score of 0.6), while all other cell sites in Figure 3D may have no coverage overlap (i.e., a pairing score of zero). After the second iteration of partitioning, all graphs between cell sites (including the graph for cell site pair B-E) are resolved (i.e., the pairing scores of all cell site pairs may be zero).

[0062] 4 illustrates updating at least one weighting factor based on feedback parameters, according to one embodiment. Referring to FIG. 4, in an exemplary embodiment, the weighting factors may include the number of users of a cell site pair, throughput, and handover success rate to generate a pairing score between two cell sites of the cell site pair according to Equation 1. In FIG. 4, each weight (i.e., user weight, throughput weight, handover weight) may be multiplied by each respective weighting factor to refine (i.e., update) the calculation of the pairing score.

[0063] To this end, weight updates are determined based on the impact of network maintenance on RAN users (i.e., the impact of running a batch during network maintenance). The impact may be measured by the volume of RAN user complaints in response to the network maintenance. The volume of user complaints after maintenance may be compared to the volume of user complaints during normal operation of the RAN (or during past network maintenance), and weight updates may be determined based on that comparison. The next time the method is executed to determine a batch of maintenance plans, an importance score (i.e., a weighted sum of weighting factors multiplied or applied to the coverage overlap percentage) is calculated using the updated weights.

[0064] 4, in an exemplary embodiment, the method may include upgrading weighting factors based on maintenance schedule shortcomings (i.e., user complaint feedback regarding connection losses at cell sites). For example, a cell site in a sports stadium may have a significant adverse impact on RAN users if it is switched off during a weekend sporting event. Or, for example, a cell site in a business district may be operating at minimum capacity during the holiday season and therefore experience less impact than usual. As a result, both cell sites may have low pairing scores (i.e., low impact) at a particular time, but network maintenance at the wrong time may cause a large number of user complaints. Based on this amount of RAN user complaints, the pairing scores may be adjusted by updating the weights as described above (i.e., updating to refine the calculation of the pairing scores for cell site pairs that include such cell sites).

[0065] FIG. 5 illustrates experimental data regarding the effect of different weighting factors on a method for selecting an upgrade sequence for cell sites in a wireless access network, according to one or more embodiments. Referring to FIG. 5, experimental results were obtained by applying this method to 16,000 cell sites. In FIG. 5, the relationship between increasing iteration steps (i.e., the number of successive divisions or final batches) and decreasing pairing scores based on the divisions is illustrated by an iteration curve. The iteration curve illustrates the importance of weighting factors and batch number for determining meaningful pairing scores. In FIG. 5, the X-axis indicates the number of successive batches (i.e., the number of iterations) created, and the Y-axis indicates the relative remaining overlap between cell sites in each batch for each successive division.

[0066] In Figure 5, the iteration curve for the prior art (i.e., random splitting) is shown with solid dots. The related art iteration curve can provide a benchmark against the splitting iteration curve using the pairing scores determined in step 201 of Figure 2. These iteration curves are shown with solid triangles and squares, respectively. For example, pairing scores based on throughput data and handover data result in an iteration curve with solid triangles. Furthermore, pairing scores based on user data, throughput data, and handover data result in an iteration curve with solid squares.

[0067] From the different iteration curves shown in Figure 5, it can be seen that in the 40th consecutive batch, the random splitting reached a relative residual overlap score of 0.05. In comparison, according to the iteration curve with solid triangles, the relative residual overlap decreased to 0.03 in the 40th consecutive batch.

[0068] The optimal result is shown by the iterative curve with solid squares, where the relative remaining overlap decreased to a value of 0.02 (i.e., less than 50% of the pairing score of the related art) by the 40th consecutive batch.

[0069] At the 100th batch, the difference from the related art becomes even more apparent as the iterative curves decrease to 0.003 and 0.002, respectively (i.e., approximately 10-fold lower pairing scores compared to the related art).

[0070] According to example embodiments of the present disclosure, an apparatus, method, and non-transitory computer-readable storage medium provide for the selection of cell sites to be upgraded simultaneously based on quantification of coverage overlap between the cell sites, thereby minimizing the adverse impact of a network upgrade on the number of RAN users and disconnected devices.

[0071] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit implementations to the precise form disclosed. Modifications and variations are possible in light of the above disclosure or may be acquired from practice of an implementation.

[0072] Some embodiments may relate to systems, methods, and / or computer-readable media at any possible level of technical detail. Furthermore, one or more of the above components described above may be implemented as instructions stored on a computer-readable medium and executable by at least one processor (and / or may include at least one processor). The computer-readable medium may include a computer-readable non-transitory storage medium (or media) having computer-readable program instructions for causing a processor to perform operations.

[0073] A computer-readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer-readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically encoded devices such as punch cards or ridge-in-groove structures with instructions recorded thereon, and any suitable combination of the foregoing. As used herein, computer-readable storage media should not be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or electrical signals transmitted through wires.

[0074] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device or to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing / processing device.

[0075] The computer-readable program code / instructions for carrying out operations can be either source code or object-oriented programming languages ​​written in any combination of one or more programming languages, including assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, or object code such as Smalltalk, C++, and procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be to an external computer (e.g., via the Internet using an Internet Service Provider). In some embodiments, electronic circuits including, for example, programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuit to perform an aspect or operation.

[0076] These computer-readable program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that the instructions, which execute on the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams, to produce a machine. These computer-readable program instructions may also be stored on a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that a computer-readable storage medium having instructions stored therein includes an article of manufacture containing instructions that implement aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0077] The computer-readable program instructions may also be loaded into a computer, other programmable data processing apparatus, or other device and cause the computer, other programmable apparatus, or other device to perform a series of operational steps to create a computer-implemented process, such that the instructions, running on the computer, other programmable apparatus, or other device, perform the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0078] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer-readable media according to various embodiments. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions, including one or more executable instructions for implementing the specified logical function(s). The methods, computer systems, and computer-readable media may include additional, fewer, different, or differently arranged blocks than shown in the figures. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may actually be executed concurrently or substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a special-purpose hardware-based system that performs the specified functions or acts or executes a combination of special-purpose hardware and computer instructions.

[0079] It will be apparent that the systems and / or methods described herein may be implemented in different forms of hardware, firmware, or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods is not intended to limit the implementation. Thus, the operation and behavior of the systems and / or methods are described herein without reference to specific software code, and it will be understood that software and hardware can be designed to implement the systems and / or methods based on the description herein.

Claims

1. 1. An apparatus for selecting an upgrade sequence for cell sites in a radio access network, comprising: a memory for storing instructions; at least one processor, wherein the at least one processor executes the instructions to determining a pairing score for each pair of cell sites from among a plurality of cell sites based on coverage overlap between the cell sites; dividing the plurality of cell sites into at least two batches based on the determined pairing score for each cell site pair; determining which cell sites of the plurality of cell sites can be upgraded simultaneously based on the division into the at least two batches; The apparatus is configured to:

2. The at least one processor executes the instructions to: repeating, within each successive batch, determining the pairing score for each cell site pair in the batch and dividing the cell sites in the batch based on the determined pairing score for each cell site pair in the batch until a predetermined number of batches and / or network segments is reached. The apparatus of claim 1 , further configured to:

3. The at least one processor executes the instructions to: Partitioning the plurality of cell sites based on the determined pairing scores by using a graph neural network to partition the cell site pairs. The apparatus of claim 1 , further configured to:

4. The at least one processor executes the instructions to: Randomly split cell-site pairs with pairing scores below a predetermined threshold The apparatus of claim 1 , further configured to:

5. The at least one processor executes the instructions to: prior to the initial determination of pairing scores and the division into batches, randomly dividing the cell sites in the radio access network into the initial batches a predetermined number of times such that the initial determination of pairing scores is performed on the initial batches. The apparatus of claim 1 , further configured to:

6. The at least one processor executes the instructions to: Splitting the plurality of cell sites based on the determined pairing scores by using a graph neural network to split the cell site pairs until a predetermined number of batches and / or network segments is reached. The apparatus of claim 5 further configured to:

7. the pairing score is determined based on the coverage overlap weighted by at least one weighting factor; the at least one weighting factor includes at least one of a factor of user count data, a factor of throughput data, or a factor of handover success data; 10. The apparatus of claim 1.

8. The at least one processor executes the instructions to: updating each weight of the at least one weighting factor based on at least one feedback parameter; The apparatus of claim 7 further configured to:

9. 1. A method for selecting an upgrade sequence for cell sites in a radio access network, comprising: determining a pairing score for each pair of cell sites from among a plurality of cell sites based on coverage overlap between the cell sites; dividing the plurality of cell sites into at least two batches based on the determined pairing score for each cell site pair; determining which cell sites of the plurality of cell sites can be upgraded simultaneously based on the division into the at least two batches; A method comprising:

10. repeating, within each successive batch, determining the pairing score for each cell site pair in the batch and dividing the cell sites in the batch based on the determined pairing score for each cell site pair in the batch until a predetermined number of batches and / or network segments is reached. The method of claim 9 further comprising:

11. partitioning the plurality of cell sites based on the determined pairing scores by using a graph neural network to partition the cell site pairs. The method of claim 9 further comprising:

12. The dividing step comprises: Randomly splitting cell-site pairs that have pairing scores below a predetermined threshold.

10. The method of claim 9, comprising:

13. prior to the initial determination of pairing scores and division into batches, randomly dividing the cell sites in the radio access network into the initial batches a predetermined number of times, such that the initial determination of pairing scores is performed on the initial batches. The method of claim 9 further comprising:

14. partitioning the plurality of cell sites based on the determined pairing scores by using a graph neural network to partition the cell site pairs until a predetermined number of batches and / or network segments is reached. The method of claim 13 further comprising:

15. the pairing score is determined based on the coverage overlap weighted by at least one weighting factor; the at least one weighting factor includes at least one of a factor of user count data, a factor of throughput data, or a factor of handover success data; 10. The method of claim 9.

16. updating each weight of the at least one weighting factor based on at least one feedback parameter; 16. The method of claim 15, further comprising:

17. 1. A non-transitory computer-readable storage medium having instructions executable by at least one processor to perform a method for selecting an upgrade sequence for cell sites in a radio access network, the method comprising: determining a pairing score for each cell site pair from among a plurality of cell sites based on at least one weighting factor that quantifies coverage overlap between the cell sites; dividing the plurality of cell sites into at least two batches based on the determined pairing score for each cell site pair; determining which cell sites of the plurality of cell sites can be upgraded simultaneously based on the division into the at least two batches; A non-transitory computer-readable recording medium comprising:

18. repeating, within each successive batch, determining the pairing score for each cell site pair in the batch and dividing the cell sites in the batch based on the determined pairing score for each cell site pair in the batch until a predetermined number of batches and / or network segments is reached.

20. The non-transitory computer-readable storage medium of claim 17, further comprising:

19. prior to the initial determination of pairing scores and division into batches, randomly dividing the cell sites in the radio access network into the initial batches a predetermined number of times, such that the initial determination of pairing scores is performed on the initial batches.

20. The non-transitory computer-readable storage medium of claim 17, further comprising:

20. partitioning the plurality of cell sites based on the determined pairing scores by using a graph neural network to partition the cell site pairs until a predetermined number of batches and / or network segments is reached.

20. The non-transitory computer-readable storage medium of claim 17, further comprising:

Images