A resource scheduling method and device, and a storage medium

Abstract

The application discloses a resource scheduling method and device and a storage medium, relates to the technical field of communication, and aims to solve the problem that a general method cannot reasonably allocate resources. The method comprises the following steps: acquiring a plurality of historical state information corresponding to a plurality of base stations in a preset historical time period, then inputting the plurality of historical state information into a pre-trained target model to obtain a plurality of target state information corresponding to the plurality of base stations in a preset future time period. The target model is trained according to a plurality of sample state information. Subsequently, a resource scheduling strategy is determined according to the plurality of target state information, and resources are scheduled to a first base station requiring resources according to the resource scheduling strategy.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a resource scheduling method, apparatus and storage medium. Background Technology

[0002] In communication networks, network congestion is a frequent occurrence, leading to problems such as difficulty in user access, dropped calls, and low call quality. Therefore, it is necessary to rationally schedule network resources for each communication cell.

[0003] Common resource scheduling methods typically involve manual adjustments based on information such as the number of users and code resource utilization, resulting in high labor costs and low resource scheduling efficiency. Summary of the Invention

[0004] This application provides a resource scheduling method, apparatus, and storage medium to solve the problem that general methods cannot reasonably allocate resources.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a resource scheduling method is provided, comprising: acquiring multiple historical state information corresponding one-to-one with multiple base stations within a preset historical time period; then inputting the multiple historical state information into a pre-trained target model to obtain multiple target state information corresponding one-to-one with multiple base stations within a preset future time period. The target model is trained based on multiple sample state information. Subsequently, a resource scheduling strategy can be determined based on the multiple target state information, and resources can be scheduled to the first base station requiring resource allocation according to the resource scheduling strategy.

[0007] Optionally, the method for determining a resource scheduling strategy based on multiple target status information includes: determining at least one base station to be transferred in that meets preset resource transfer conditions based on multiple target status information, and determining the resource scheduling order of the at least one base station to be transferred in; and determining a first base station from the at least one base station to be transferred in according to the resource scheduling order.

[0008] Optionally, the multiple target status information includes: location information of multiple base stations; the resource scheduling strategy also includes: a second base station to which resources are allocated; the method for determining the resource scheduling strategy based on the multiple target status information includes: determining at least one available base station that meets preset resource allocation conditions based on the multiple target status information; and determining the available base station among the at least one available base station whose distance from the first base station is less than a preset distance as the second base station based on the location information of the multiple base stations.

[0009] Optionally, the resource scheduling strategy further includes: a first time period for scheduling resources to the first base station; and a method for scheduling resources to the first base station according to the resource scheduling strategy, including: performing security verification and adjusting the resource scheduling strategy based on a preset security strategy to obtain an adjusted resource scheduling strategy; the adjusted resource scheduling strategy includes: a second time period; the second time period includes the first time period; and during the second time period, scheduling idle resources of the second base station to the first base station.

[0010] Optionally, the resource scheduling method further includes: obtaining alarm information sent by any one of the multiple base stations; the alarm information is used to indicate that the status information of any one base station during the alarm time period meets the preset resource allocation conditions.

[0011] Secondly, a resource scheduling device is provided, comprising: an acquisition unit and a processing unit; the acquisition unit is used to acquire multiple historical state information corresponding one-to-one with multiple base stations within a preset historical time period; the processing unit is used to input the multiple historical state information into a pre-trained target model to obtain multiple target state information corresponding one-to-one with multiple base stations within a preset future time period; the target model is trained based on multiple sample state information; the processing unit is further used to determine a resource scheduling strategy based on the multiple target state information; the resource scheduling strategy includes: a first base station that needs to allocate resources; the processing unit is further used to schedule resources to the first base station according to the resource scheduling strategy.

[0012] Optionally, the processing unit is specifically used for: determining at least one base station to be transferred in that meets preset resource transfer conditions based on multiple target status information, and determining the resource scheduling order of the at least one base station to be transferred in; and determining a first base station from the at least one base station to be transferred in according to the resource scheduling order.

[0013] Optionally, the multiple target status information includes: the location information of multiple base stations; the resource scheduling strategy also includes: a second base station to which resources are allocated; the processing unit is specifically used to: determine at least one available base station that meets the preset resource allocation conditions based on the multiple target status information; and determine the available base station among the at least one available base station whose distance from the first base station is less than a preset distance as the second base station based on the location information of the multiple base stations.

[0014] Optionally, the resource scheduling strategy further includes: a first time period for scheduling resources to the first base station; and a processing unit specifically configured to: perform security verification and adjust the resource scheduling strategy based on a preset security strategy to obtain an adjusted resource scheduling strategy; the adjusted resource scheduling strategy includes: a second time period; the second time period includes the first time period; and during the second time period, schedule idle resources of the second base station to the first base station.

[0015] Optionally, the acquisition unit is also used to: acquire alarm information sent by any one of the multiple base stations; the alarm information is used to indicate that the status information of any one base station meets the preset resource loading conditions during the alarm time period.

[0016] Thirdly, a resource scheduling device is provided, including a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory via a bus; when the resource scheduling device is running, the processor executes the computer execution instructions stored in the memory, so that the resource scheduling device performs the resource scheduling method described in the first aspect.

[0017] The resource scheduling device can be a network device or a component of a network device, such as a chip system within the network device. This chip system supports the network device in implementing the functions involved in the first aspect and any of its possible implementations, such as acquiring, determining, and transmitting data and / or information involved in the aforementioned resource scheduling method. The chip system includes a chip, but may also include other discrete devices or circuit structures.

[0018] Fourthly, a computer-readable storage medium is provided, comprising computer-executable instructions that, when executed on a computer, cause the computer to perform the resource scheduling method described in the first aspect.

[0019] Fifthly, a computer program product is also provided, which includes computer instructions that, when executed on a resource scheduling device, cause the resource scheduling device to perform the resource scheduling method as described in the first aspect above.

[0020] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on the first computer-readable storage medium. The first computer-readable storage medium may be packaged together with the processor of the resource scheduling device, or it may be packaged separately from the processor of the resource scheduling device; this application does not impose any limitations on this.

[0021] The descriptions of the second, third, fourth, and fifth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects of the second, third, fourth, and fifth aspects can be referenced to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0022] In this application, the name of the aforementioned resource scheduling device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0023] These or other aspects of this application will become more readily apparent in the following description.

[0024] The technical solution provided in this application brings at least the following beneficial effects:

[0025] Based on any of the above, this application provides a resource scheduling method that can acquire multiple historical state information corresponding one-to-one with multiple base stations within a preset historical time period, and then input the multiple historical state information into a pre-trained target model to obtain multiple target state information corresponding one-to-one with multiple base stations within a preset future time period. The target model is trained based on multiple sample state information. Subsequently, a resource scheduling strategy can be determined based on the multiple target state information, and resources can be scheduled to the first base station requiring resource allocation according to the resource scheduling strategy. This application solves the problem of insufficient network resources and inability for users to access the network through flexible resource allocation, meets the network needs of more users, and further improves resource utilization efficiency. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the structure of a resource scheduling system provided in an embodiment of this application;

[0027] Figure 2 This is a schematic diagram of the structure of a resource scheduling device provided in an embodiment of this application;

[0028] Figure 3 A schematic diagram of the hardware structure of a resource scheduling device provided in this application embodiment. Figure 1 ;

[0029] Figure 4 A schematic diagram of the hardware structure of a resource scheduling device provided in this application embodiment. Figure 2 ;

[0030] Figure 5 A flowchart illustrating a resource scheduling method provided in this application embodiment. Figure 1 ;

[0031] Figure 6 A schematic diagram illustrating model training as provided in an embodiment of this application;

[0032] Figure 7 A flowchart illustrating a resource scheduling method provided in this application embodiment. Figure 2 ;

[0033] Figure 8 A flowchart illustrating a resource scheduling method provided in this application embodiment. Figure 3 ;

[0034] Figure 9 A flowchart illustrating a resource scheduling method provided in this application embodiment.Figure 4 ;

[0035] Figure 10 A flowchart illustrating a resource scheduling method provided in this application embodiment. Figure 5 ;

[0036] Figure 11 This is a schematic diagram of the structure of a resource scheduling device provided in an embodiment of this application. Detailed Implementation

[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0038] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0039] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0040] As shown in the background section, common resource scheduling methods usually involve manual adjustments based on information such as the number of users and code resource utilization, which results in high labor costs and low resource scheduling efficiency.

[0041] This application provides a resource scheduling method that acquires multiple historical state information entries corresponding to multiple base stations within a preset historical time period. These historical state entries are then input into a pre-trained target model to obtain multiple target state information entries corresponding to multiple base stations within a preset future time period. The target model is trained based on multiple sample state information entries. Subsequently, a resource scheduling strategy can be determined based on the multiple target state information entries, and resources can be scheduled to the first base station requiring resource allocation according to the strategy. This application solves the problem of insufficient network resources and user access issues through flexible resource allocation, meeting the network needs of more users and further improving resource utilization efficiency.

[0042] This resource scheduling method is applicable to resource scheduling systems. Figure 1 A schematic diagram of a resource scheduling system is shown. Figure 1 As shown, the resource scheduling system includes: resource scheduling device 101 and multiple base stations (including base station 102 and base station 103).

[0043] The resource scheduling device 101 can be connected to multiple base stations via wired or wireless means.

[0044] In some embodiments, the resource scheduling device 101 can be a functional module on any base station or an independently configured physical device.

[0045] It is easy to understand that when the resource scheduling device 101 is a functional module on the base station 102, the interaction between the resource scheduling device 101 and the base station 102 is the same as the interaction between internal modules of the base station 102. In this case, the interaction process between the two is the same as the interaction process between the two when the resource scheduling device 101 is an independently configured physical device.

[0046] Optionally, when the resource scheduling device 101 is an independently configured physical device, the resource scheduling device 101 can be an independent server or other form of physical device. The physical device can be a server in a server cluster (composed of multiple servers), a chip in the physical device, a system-on-a-chip in the physical device, or a virtual machine deployed on a physical machine. This application embodiment does not limit this.

[0047] For ease of understanding, this application uses the example of "resource scheduling device 101 being an independently configured physical device" for illustration.

[0048] Optionally, the base station can be a base transceiver station (BTS) in Global System for Mobile Communication (GSM), a base station (node ​​B) in Wideband Code Division Multiple Access (WCDMA), a base station (eNB) in Internet of Things (IoT) or Narrowband Internet of Things (NB-IoT), a base station in a future 5G mobile communication network, or a future evolved public land mobile network (PLMN). This application embodiment does not impose any limitations on this.

[0049] Combination Figure 1 ,like Figure 2 As shown, the resource scheduling device 101 may include: a status information prediction module 201, a network element configuration module 202, and a resource allocation module 203.

[0050] Among them, the status information prediction module 201 is used to predict the status information of the base station through data mining and deep neural networks.

[0051] The network element configuration module 202 is used to obtain parameter information of the network element controller and base station information.

[0052] The resource allocation module 203 is used to call the network element controller to complete the allocation action.

[0053] Combination Figure 1 The resource scheduling device 101 and multiple base stations in the resource scheduling system all include Figure 3 or Figure 4 The components included in the communication device shown. The following are examples... Figure 3 and Figure 4 Taking the communication device shown as an example, the hardware structure of the resource scheduling device 101 and multiple base stations is introduced.

[0054] like Figure 3 The diagram shown is a hardware structure schematic of a communication device provided in an embodiment of this application. The communication device includes a processor 21, a memory 22, a communication interface 23, and a bus 24. The processor 21, the memory 22, and the communication interface 23 are connected via the bus 24.

[0055] Processor 21 is the control center of the communication device. It can be a single processor or a collective term for multiple processing elements. For example, processor 21 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0056] As one embodiment, processor 21 may include one or more CPUs, for example Figure 3 CPU 0 and CPU 1 are shown in the diagram.

[0057] The memory 22 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0058] In one possible implementation, the memory 22 can exist independently of the processor 21. The memory 22 can be connected to the processor 21 via a bus 24 and is used to store instructions or program code. When the processor 21 calls and executes the instructions or program code stored in the memory 22, it can implement the resource scheduling method provided in the following embodiments of the present invention.

[0059] In another possible implementation, the memory 22 can also be integrated with the processor 21.

[0060] Communication interface 23 is used for connecting the communication device to other devices via a communication network, such as Ethernet, wireless access network, wireless local area network (WLAN), etc. Communication interface 23 may include a receiving unit for receiving data and a transmitting unit for sending data.

[0061] Bus 24 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0062] Figure 4 Another hardware structure of the communication device in an embodiment of the present invention is shown. For example... Figure 4 As shown, the communication device may include a processor 31 and a communication interface 32. The processor 31 is coupled to the communication interface 32.

[0063] The functions of processor 31 can be referred to in the description of processor 21 above. In addition, processor 31 also has a storage function, and can perform the functions of memory 22 mentioned above.

[0064] The communication interface 32 is used to provide data to the processor 31. The communication interface 32 can be an internal interface of the communication device or an external interface of the communication device (equivalent to communication interface 23).

[0065] It should be pointed out that, Figure 3 (or Figure 4 The structure shown in the diagram does not constitute a limitation on the communication device, except... Figure 3 (or Figure 4 In addition to the components shown in the diagram, the communication device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0066] The resource scheduling method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. Figure 5 As shown, the resource scheduling method includes:

[0067] S501, The resource scheduling equipment acquires multiple historical status information corresponding to multiple base stations within a preset historical time period.

[0068] Optionally, the status information may include: hourly data of the base station on the wireless network side, base station operating parameter information, cell geographic information, etc., such as the average number of effective radio resource control (RRC) connection re-establishment requests, the maximum number of RRC connections, the number of successful RRC connections, the number of RRC connection releases, uplink utilization (physical uplink shared channel, PUSCH), downlink utilization (PDSCH), downlink utilization (PDCCH), PRB (permeable reactive barriers) utilization, user-perceived number, etc.

[0069] In one possible approach, the resource scheduling device can periodically acquire the status information of multiple base stations in the network and store it in a performance data (PM) database, so that the resource scheduling device can read historical status information from the PM database.

[0070] S502, the resource scheduling device inputs multiple historical state information into the pre-trained target model to obtain multiple target state information corresponding to multiple base stations within a preset future time period.

[0071] The target model is trained based on the state information of multiple samples.

[0072] In one feasible approach, during the training parameter construction process, the resource scheduling device can select multiple sample status information (including network information of base stations and geographical information of base station distribution) from the source database distributed file system (HDFS) over the past month to construct training sample data.

[0073] Optionally, training samples may include base station alarm information on the wireless network side, such as province name, city name, alarm occurrence time, alarm clearance time, and unique identifier of the alarm station.

[0074] In one feasible approach, the resource scheduling device can input training sample data into the current neural network model for iterative training until the loss value of the current neural network model meets a preset condition.

[0075] The loss value characterizes the error between the training parameters and the output. The output is the target network state predicted by the current neural network model.

[0076] In one feasible approach, the training sample data required for model training can be synchronized in real time from the wireless performance data acquisition system and the engineering parameter data acquisition system to the source database's distributed file HDFS system via file transfer protocol (FTP) or message subscription acquisition.

[0077] In one feasible approach, the resource scheduling device can standardize the input training sample data, scaling it proportionally to a small, specific interval. Then, it centers each dimension of the training sample data to 0 for mean reduction, employs principal component analysis (PCA) for dimensionality reduction, and uses whitening techniques to normalize the amplitude of each feature, enabling the neural network to converge quickly. The introduction of the neural network allows the model to accept higher-dimensional, richer information from the training sample data, combining base station information as input to the neural network.

[0078] Optionally, the neural network can be a deep double Q-learning network (DDQN) algorithm. For example... Figure 6 As shown, the algorithm uses a loss function to iteratively update the model parameters, with the loss function serving as the optimization objective. The link between the base station and the user is considered the environment, and a centralized training method is used. The implementation data obtained during training is shared by all agents, thereby reducing the computational resources required for training. Agents acquire state information by perceiving the surrounding communication environment, inputting this information into the neural network. The neural network selects an action and provides a reward. By continuously repeating this process, the RRC adaptive allocation strategy is trained and optimized.

[0079] The model input data package contains geographical information at the provincial and municipal levels, as well as time-related information, including the maximum number of RRC connections in the past month, the number of successful RRC connections in the past month, and the number of RRC connection releases in the past month. The input data integrates long-term and short-term data trends, as well as the influence of time and location factors, making the prediction results more accurate.

[0080] The model uses the ReLU function for activation parameters to prevent gradient vanishing, and batch normalization is employed for rapid parameter tuning, enabling fast training convergence. The mean absolute error (MAE) function is used for loss. Residual connections are introduced into the model to increase its robustness. Learning rate warm-up and decay mechanisms are implemented to reduce oscillations during training. Dropout and early stopping mechanisms are used to prevent overfitting.

[0081] The model output is the maximum number of RRC connected users for each base station in the city during a future time period (e.g., 24 hours).

[0082] Combination Figure 6 The model uses convolutional neural networks (CNNs) to approximate the Q-value function, and then updates the target Q-value through a target Q-network, enabling rapid convergence. An experience replay pool is used to store historical data for training the neural network model. First, historical data is stored in the experience replay pool. Then, a batch of data is randomly selected from the experience replay pool to update the neural network parameters. The experience replay pool breaks the correlation between data, satisfying the CNN requirement for unordered input data.

[0083] Not all data used for agent training is meaningful; some data may not be useful for the agent's learning. Therefore, the experience replay pool employs a priority replay strategy to maximize learning efficiency and increase sampling weights. Different Q-value functions are used for action selection and evaluation to avoid overestimation.

[0084] This model combines reinforcement learning and deep neural networks to obtain the maximum reward by calculating the value function based on the policy and updating the policy based on the value function. This enables the link to intelligently learn the inherent connections between base stations in each cell and predict the future RRC usage of each base station in the city, effectively reducing the number of dispatching and alarms.

[0085] In one feasible approach, after the resource scheduling device obtains training sample data, it can use a deep double-Q network algorithm to solve the RRC adaptive allocation problem. Specifically, this includes steps S1-S7.

[0086] S1. The resource scheduling device inputs the following data into the current Q network model as the state space: geographic information (including province and city), time information, maximum number of RRC connections in the past month, number of successful RRC connections in the past month, and number of RRC connection releases in the past month. The RRC allocation action is used as the action space to initialize the parameters of the current Q network and the target Q network.

[0087] S2. The resource scheduling equipment instructs the base station state space to select a scheduling action based on a greedy strategy using the current Q network.

[0088] S3. The resource scheduling equipment instructs the base station to perform RRC allocation actions, and will receive excitation function feedback from the control units of each base station in the city.

[0089] S4. The resource scheduling device obtains the next base station status and stores the previous base station status, RRC allocation action, next base station status and excitation function feedback into the experience playback pool.

[0090] S5. If the current step size is greater than the fixed step size training target, the resource scheduling device will retrieve a batch of data from the experience replay pool to train the network.

[0091] S6. The resource scheduling device calculates the target Q network value and loss function, and minimizes the loss function to update the current network parameters.

[0092] S7. After a certain number of iterations, the resource scheduling device updates the target Q-network parameters based on the current Q-network parameters until the model reaches the expected number of iterations or a reasonable error range.

[0093] Since the prediction result set is the maximum number of RRC connected users for each base station in the next 24 hours, in order to ensure that the prediction data is as accurate as possible, the model can periodically acquire new data and output the latest prediction results to the big data file system.

[0094] S503, the resource scheduling equipment determines the resource scheduling strategy based on the status information of multiple targets.

[0095] Optionally, the resource scheduling strategy may include: a first base station that needs to allocate resources, and a second base station that can allocate resources.

[0096] In one feasible approach, the resource scheduling device can determine at least one base station to be transferred in that meets preset resource transfer conditions based on multiple target status information, determine the resource scheduling order of the at least one base station to be transferred in, and then determine the first base station from the at least one base station to be transferred in according to the resource scheduling order.

[0097] Optionally, the preset resource allocation condition can be: when the ratio of the predicted number of RRC connections to the maximum number of connections of the base station is greater than or equal to the manually revised user over-limit ratio.

[0098] S504. The resource scheduling equipment schedules resources to the first base station according to the resource scheduling strategy.

[0099] The technical solution provided by the above embodiments brings at least the following beneficial effects: As shown in S501-S504, the resource scheduling device can obtain multiple historical state information corresponding to multiple base stations within a preset historical time period, and then input the multiple historical state information into a pre-trained target model to obtain multiple target state information corresponding to multiple base stations within a preset future time period. The target model is trained based on multiple sample state information. Subsequently, a resource scheduling strategy can be determined based on the multiple target state information, and resources can be scheduled to the first base station that needs to allocate resources according to the resource scheduling strategy. This application solves the problem of insufficient network resources and inability for users to access the network through flexible resource allocation, meets the network needs of more users, and further improves resource utilization efficiency.

[0100] In one alternative embodiment, combined with Figure 5 ,like Figure 7 As shown in S503, the method by which the resource scheduling device determines the resource scheduling strategy based on multiple target status information includes:

[0101] S701. The resource scheduling device determines at least one base station to be transferred in that meets the preset resource transfer conditions based on multiple target status information, and determines the resource scheduling order of at least one base station to be transferred in.

[0102] In one feasible approach, the resource scheduling device can identify at least one base station whose ratio of the predicted number of RRC connections to the maximum number of base station connections is greater than or equal to the manually revised user over-limit ratio as at least one base station to be scheduled in. The ratios are then sorted from largest to smallest, and the order of these at least one base station to be scheduled in determines the resource scheduling order.

[0103] In one possible implementation, the resource scheduling device can also mark at least one base station to be scheduled with different levels of urgency, with the higher the urgency level being the more severe the over-limit.

[0104] S702. The resource scheduling device determines the first base station from at least one base station to be scheduled in, according to the resource scheduling order.

[0105] In one feasible approach, the resource scheduling device can prioritize scheduling resources to base stations with a higher ratio of the predicted number of RRC connections to the maximum number of base station connections.

[0106] The technical solution provided by the above embodiments brings at least the following beneficial effects: As shown in S701-S702, the resource scheduling device can determine at least one base station to be scheduled in that meets the preset resource scheduling conditions based on multiple target status information, and determine the resource scheduling order of the at least one base station to be scheduled in. Then, the resource scheduling device can determine the first base station from the at least one base station to be scheduled in according to the resource scheduling order. This application provides a method for determining a resource scheduling strategy to achieve flexible resource allocation, solve the problem of insufficient network resources and inability for users to access the network, meet the network needs of more users, and further improve resource utilization efficiency.

[0107] In an optional embodiment, when the multiple target status information includes the location information of multiple base stations, the resource scheduling strategy further includes: allocating resources to a second base station. In this case, combined with... Figure 7 ,like Figure 8 As shown in S503, the method by which the resource scheduling device determines the resource scheduling strategy based on multiple target status information includes:

[0108] S801. The resource scheduling equipment determines at least one base station that meets the preset resource dispatch conditions based on multiple target status information.

[0109] In one feasible approach, the resource scheduling device can identify at least one base station as a callable base station if the ratio of the predicted number of RRC connections to the maximum number of base station connections is less than a preset lower threshold.

[0110] S802. Based on the location information of multiple base stations, the resource scheduling device identifies at least one of the callable base stations that is less than a preset distance from the first base station as the second base station.

[0111] The technical solution provided by the above embodiments brings at least the following beneficial effects: As shown in S801-S802, the resource scheduling device can determine at least one available base station that meets the preset resource allocation conditions based on multiple target status information. Then, based on the location information of multiple base stations, the available base station whose distance from the first base station is less than a preset distance can be determined as the second base station. This application provides a method for determining a resource scheduling strategy to achieve flexible resource allocation, solve the problem of insufficient network resources and inability for users to access the network, meet the network needs of more users, and further improve resource utilization efficiency.

[0112] In an optional embodiment, when the resource scheduling strategy further includes: scheduling resources to the first base station for a first time period, combined with... Figure 8 ,like Figure 9As shown in S504, the method by which the resource scheduling device schedules resources to the first base station according to the resource scheduling strategy includes:

[0113] S901. The resource scheduling device performs security verification and adjusts the resource scheduling strategy based on the preset security strategy to obtain the adjusted resource scheduling strategy.

[0114] The adjusted resource scheduling strategy includes a second time period. The second time period includes the first time period.

[0115] In one feasible approach, the resource scheduling equipment is pre-configured with information on each base station and provincial / municipal network management personnel. After the network management personnel confirm and authorize the system to execute the operation, the resource scheduling equipment can manually configure the desired allocation time window, frequency, and start and end time period. The resource scheduling equipment then first filters the range of base stations authorized by the network management personnel, and then configures the corresponding Operation and Maintenance Center (OMC) parameters and base station parameters required for the RRC allocation task.

[0116] S902, the resource scheduling equipment will schedule the idle resources of the second base station to the first base station during the second time period.

[0117] The technical solution provided by the above embodiments brings at least the following beneficial effects: As shown in S901-S902, the resource scheduling device can perform security verification and adjustment on the resource scheduling strategy based on a preset security policy to obtain an adjusted resource scheduling strategy. The adjusted resource scheduling strategy includes a second time period. The second time period includes the first time period. Then, the resource scheduling device can schedule idle resources of the second base station to the first base station during the second time period. This application provides a method for scheduling resources, which can improve the security of network data during resource scheduling.

[0118] In one alternative embodiment, combined with Figure 5 ,like Figure 10 As shown, the resource scheduling method also includes:

[0119] S1001, the resource scheduling device obtains alarm information sent by any one of the multiple base stations.

[0120] Among them, alarm information is used to indicate that the status information of any base station during the alarm period meets the preset resource loading conditions.

[0121] Optionally, base station alarm information may include: province name, city name, alarm occurrence time, alarm clearance time, and unique identifier of the alarm station.

[0122] The technical solution provided by the above embodiments brings at least the following beneficial effects: As can be seen from S1001, the resource scheduling device can obtain alarm information sent by any one of the multiple base stations, so as to execute the resource scheduling process in response to the alarm information.

[0123] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] This application embodiment can divide the resource scheduling device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0125] like Figure 11 The diagram shown is a structural schematic of a resource scheduling device provided in an embodiment of this application. This resource scheduling device can be used to perform... Figure 5 to Figure 10 The resource scheduling method shown. Figure 11 The resource scheduling device shown includes: an acquisition unit 1101 and a processing unit 1102.

[0126] The acquisition unit 1101 is used to acquire multiple historical status information that correspond one-to-one with multiple base stations within a preset historical time period.

[0127] The processing unit 1102 is used to input multiple historical state information into a pre-trained target model to obtain multiple target state information corresponding to multiple base stations in a preset future time period; the target model is trained based on multiple sample state information.

[0128] The processing unit 1102 is further configured to determine a resource scheduling strategy based on multiple target status information; the resource scheduling strategy includes: a first base station that needs to allocate resources; the processing unit 1102 is further configured to schedule resources to the first base station according to the resource scheduling strategy.

[0129] Optionally, the processing unit 1102 is specifically used to: determine at least one base station to be transferred in that meets the preset resource transfer conditions based on multiple target status information, and determine the resource scheduling order of the at least one base station to be transferred in; and determine the first base station from the at least one base station to be transferred in according to the resource scheduling order.

[0130] Optionally, the multiple target status information includes: the location information of multiple base stations; the resource scheduling strategy also includes: a second base station to which resources are allocated; the processing unit 1102 is specifically used to: determine at least one available base station that meets the preset resource allocation conditions based on the multiple target status information; and determine the available base station among the at least one available base station whose distance from the first base station is less than a preset distance as the second base station based on the location information of the multiple base stations.

[0131] Optionally, the resource scheduling strategy further includes: a first time period for scheduling resources to the first base station; the processing unit 1102 is specifically used to: perform security verification and adjust the resource scheduling strategy based on a preset security strategy to obtain an adjusted resource scheduling strategy; the adjusted resource scheduling strategy includes: a second time period; the second time period includes the first time period; during the second time period, the idle resources of the second base station are scheduled to the first base station.

[0132] Optionally, the acquisition unit 1101 is further configured to: acquire alarm information sent by any one of the multiple base stations; the alarm information is used to indicate that the status information of any one base station during the alarm time period meets the preset resource loading conditions.

[0133] This application also provides a computer-readable storage medium, which includes computer-executable instructions. When the computer-executable instructions are run on a computer, the computer performs the resource scheduling method provided in the above embodiments.

[0134] This application also provides a computer program that can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program can implement the resource scheduling method provided in the above embodiments.

[0135] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer-readable storage media and communication media, wherein communication media include any medium that facilitates the transfer of a computer program from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0136] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and other division methods may exist in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate; components shown as units may be one physical unit or multiple physical units, i.e., they may be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, in essence, or the part that contributes to the general technology, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0139] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A resource scheduling method, characterized in that, include: Obtain multiple historical status information that correspond one-to-one with multiple base stations within a preset historical time period; The multiple historical state information is input into the pre-trained target model to obtain multiple target state information that correspond one-to-one with the multiple base stations within a preset future time period; The target model is trained based on the state information of multiple samples; The multiple target status information includes: the location information of the multiple base stations; Based on the multiple target status information, at least one base station to be transferred in that meets the preset resource transfer conditions is determined, and the resource scheduling order of the at least one base station to be transferred in is determined. According to the resource scheduling order, the first base station that needs to be allocated resources is determined from the at least one base station to be allocated. Based on the multiple target status information, at least one base station that meets the preset resource retrieval conditions is determined; Based on the location information of the multiple base stations, the base station that is less than a preset distance from the first base station among the at least one callable base stations is determined as the second base station for calling up resources. Based on a preset security policy, the resource scheduling policy for the first base station that needs to load resources and the second base station that needs to load resources is verified and adjusted to obtain an adjusted resource scheduling policy; the adjusted resource scheduling policy includes: a second time period; the second time period includes a first time period for scheduling resources to the first base station; During the second time period, the idle resources of the second base station are scheduled to be allocated to the first base station.

2. The resource scheduling method according to claim 1, characterized in that, Also includes: Obtain alarm information sent by any one of the multiple base stations; The alarm information is used to indicate that the status information of any one of the base stations meets the preset resource loading conditions during the alarm period.

3. A resource scheduling device, characterized in that, include: Acquisition unit and processing unit; The acquisition unit is used to acquire multiple historical status information that corresponds one-to-one with multiple base stations within a preset historical time period; The processing unit is used to input the multiple historical state information into a pre-trained target model to obtain multiple target state information that corresponds one-to-one with the multiple base stations within a preset future time period. The target model is trained based on the state information of multiple samples; The multiple target status information includes: the location information of the multiple base stations; The processing unit is further configured to determine a resource scheduling strategy based on the plurality of target status information; wherein, based on the plurality of target status information, at least one base station to be transferred in that meets preset resource transfer-in conditions is determined, and the resource scheduling order of the at least one base station to be transferred in is determined; based on the resource scheduling order, a first base station that needs to transfer resources is determined from the at least one base station to be transferred in; based on the plurality of target status information, at least one base station that can be transferred out that meets preset resource transfer-out conditions is determined; based on the location information of the plurality of base stations, the base station that can be transferred out from the at least one base station whose distance from the first base station is less than a preset distance is determined as the second base station from which resources are transferred out. The processing unit is further configured to perform security verification and adjust the resource scheduling policy of the first base station that needs to load resources and the second base station that needs to load resources, based on a preset security policy, to obtain an adjusted resource scheduling policy; the adjusted resource scheduling policy includes: a second time period; the second time period includes a first time period for scheduling resources to the first base station; During the second time period, the idle resources of the second base station are scheduled to be allocated to the first base station.

4. The resource scheduling device according to claim 3, characterized in that, The acquisition unit is further configured to: Obtain alarm information sent by any one of the plurality of base stations; the alarm information is used to indicate that the status information of any one base station during the alarm time period meets the preset resource loading conditions.

5. A resource scheduling device, characterized in that, It includes a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory via a bus; when the resource scheduling device is running, the processor executes the computer execution instructions stored in the memory, so that the resource scheduling device performs the resource scheduling method as described in any one of claims 1-2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer-executable instructions that, when executed on a computer, cause the computer to perform the resource scheduling method as described in any one of claims 1-2.

Images