Power system computing power cooperative scheduling method, system and device based on regional-level intelligent computing center and medium

Abstract

The invention discloses an electric power system computing power cooperative scheduling method and system based on a regional intelligent computing center, and belongs to the technical field of computer data processing, and the method comprises the steps: obtaining the real-time operation data and prediction data of a regional power grid, and calculating the scheduling priority factor of each node of the power grid; acquiring real-time task queue data and computing resource state data of each intelligent computing center, and computing a computing power load factor of each intelligent computing center based on the real-time task queue data and the computing resource state data; acquiring a collaborative strategy library containing a co-occurrence strategy, a migration strategy and a buffer strategy, inputting the scheduling priority factor and the computing power load factor into the collaborative strategy library for matching, and generating a task scheduling strategy set; and according to the task scheduling strategy set, generating and issuing a power scheduling instruction and a computing power scheduling instruction. According to the invention, deep collaboration and global optimization configuration of power resources and computing power resources are realized.

Description

Technical Field

[0001] This invention belongs to the field of computer data processing technology, and in particular relates to a method, system, equipment and medium for collaborative scheduling of power system computing power based on a regional-level intelligent computing center. Background Technology

[0002] With the rapid development of computationally intensive applications such as artificial intelligence and big data analytics, regional intelligent computing centers, as core infrastructure to meet massive computing power demands, have been deployed on a large scale across various regions. These centers house numerous high-performance computing servers, operating with extremely high energy density and exerting an increasingly significant impact on the power system, becoming a crucial load on the power grid. Furthermore, the computing tasks they handle, especially non-real-time batch processing tasks, possess inherent flexibility in terms of time and space scheduling.

[0003] In existing technologies, the scheduling and management of power systems and intelligent computing centers are typically conducted separately. Power dispatching systems primarily manage large users such as data centers through demand response mechanisms, employing techniques such as time-of-use pricing and interruptible load compensation, which are based on indirect guidance through price signals, or issuing mandatory power reduction commands in emergency situations. The power system treats the intelligent computing center as a single, relatively slow-responding load unit. On the other hand, the task scheduling system within the intelligent computing center focuses on optimizing the utilization of computing resources and ensuring the quality of service for tasks. Its decision-making is mainly based on task priority, deadlines, data dependencies, and load balancing of internal servers, while the real-time operating status of the power grid is simply considered as an external cost factor.

[0004] The aforementioned existing technical methods have the following inherent defects:

[0005] 1. The information interaction between the power system and the intelligent computing center is one-way and shallow, lacking a deep understanding of each other's internal operating status. The power grid cannot know the specific flexibility of the computing task, and the computing power scheduling cannot predict the precise impact of its decisions on the local power grid. The independent optimization goals of the two parties often lead to behavioral conflicts and fail to form a system-level synergy.

[0006] 2. When multiple computing centers simultaneously respond to low electricity price signals and migrate tasks to the same area, it may cause new grid congestion in some areas. The lack of coordinated scheduling means that the flexibility value of the intelligent computing center load cannot be fully utilized, which limits the grid's ability to accept renewable energy and the overall economic efficiency of operation.

[0007] Therefore, there is an urgent need for a power system computing power collaborative scheduling method based on regional-level intelligent computing centers to achieve deep integration between the power grid system and the computing power system. Summary of the Invention

[0008] In view of the shortcomings of the above or existing technologies, this invention proposes a power system computing power collaborative scheduling method and system based on a regional-level intelligent computing center. This method achieves bidirectional perception by calculating scheduling priority factors and computing power load factors, and makes unified decisions based on a collaborative strategy library, thereby realizing deep collaboration and global optimized allocation of power resources and computing power resources.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0010] In a first aspect, the present invention provides a power system computing power collaborative scheduling method based on a regional-level intelligent computing center. The method is applied to a power system computing power collaborative scheduling system based on a regional-level intelligent computing center. The system includes a regional power grid object for forming the power grid, an intelligent computing center, a power grid control system for dispatching, and a control terminal. The method includes:

[0011] Obtain real-time operation data and forecast data of the regional power grid, and calculate the scheduling priority factor of each node of the power grid based on the real-time operation data and forecast data;

[0012] Obtain real-time task queue data and computing resource status data of each intelligent computing center, and calculate the computing load factor of each intelligent computing center based on the real-time task queue data and computing resource status data;

[0013] Obtain a collaborative strategy library containing symbiotic strategies, migration strategies, and buffering strategies; input the scheduling priority factor and the computing load factor into the collaborative strategy library for matching to generate a task scheduling strategy set.

[0014] Based on the set of task scheduling strategies, power scheduling instructions and computing power scheduling instructions are generated and issued to the corresponding power grid control system and intelligent computing center task management system.

[0015] As a further preferred embodiment of the present invention, the step of acquiring real-time operation data and forecast data of the regional power grid, and calculating the scheduling priority factor of each node of the power grid based on the real-time operation data and forecast data, includes:

[0016] The power supply margin parameters, line transmission congestion parameters, and real-time electricity price parameters of each node are extracted from the real-time operation data, and the renewable energy output prediction parameters are extracted from the prediction data to form a multi-dimensional power grid state parameter set.

[0017] Obtain the first weight allocation to characterize the importance attached to grid stability, transmission economy, electricity cost, and green energy consumption;

[0018] The first weight configuration is used to weight and fuse the multidimensional power grid state parameter set to generate the scheduling priority factor.

[0019] As a further preferred embodiment of the present invention, the step of acquiring real-time task queue data and computing resource status data of each intelligent computing center, and calculating the computing load factor of each intelligent computing center based on the real-time task queue data and computing resource status data, includes:

[0020] The computational parameters, delay time parameters, and data migration cost parameters of the tasks to be processed are parsed from the real-time task queue data to form a set of task flexibility parameters;

[0021] Obtain the unit computing energy consumption coefficient for calibrating the power consumption per unit of computing load, and calculate the predicted power load increment based on the computing load parameters and the unit computing energy consumption coefficient;

[0022] The predicted power load increment is corrected by combining the task flexibility parameter set to generate the computing power load factor.

[0023] As a further preferred embodiment of the present invention, the step of obtaining a collaborative strategy library containing symbiotic strategies, migration strategies, and buffering strategies, and inputting the scheduling priority factor and the computing load factor into the collaborative strategy library for matching to generate a task scheduling strategy set includes:

[0024] Based on the numerical combination of the scheduling priority factor and the computing load factor, the highest priority local collaborative strategy is matched from the collaborative strategy library;

[0025] Obtain the rule parameters used to convert the local collaboration strategy into executable instructions;

[0026] Based on the local collaboration strategy and the rule parameters, the tasks in the real-time task queue data are processed to generate specific scheduling strategies that include task execution location, task execution time and task processing method, and these strategies are aggregated to form the task scheduling strategy set.

[0027] As a further preferred embodiment of the present invention, the step of generating and issuing power dispatching instructions and computing power dispatching instructions to the corresponding power grid control system and intelligent computing center task management system according to the task scheduling strategy set specifically includes:

[0028] Receive instruction execution result data fed back by the power grid control system and the intelligent computing center task management system;

[0029] Obtain system optimization targets for evaluating the economy and efficiency of system operation, and generate adjustment signals based on the performance deviation between the instruction execution result data and the system optimization targets;

[0030] Based on the adjustment signal, adjust the first weight configuration and the rule parameters.

[0031] Furthermore, the step of generating and issuing power dispatching instructions and computing power dispatching instructions to the corresponding power grid control system and intelligent computing center task management system based on the task scheduling strategy set also includes:

[0032] When the matched local collaboration strategy is the migration strategy.

[0033] Based on the scheduling priority factor, a target node is selected from all power grid nodes, and a task migration negotiation request is sent to the intelligent computing center associated with the target node.

[0034] Receive the task migration negotiation response returned by the intelligent computing center, which includes its real-time load parameters;

[0035] The optimal migration target is selected based on the real-time load parameters in the task migration negotiation response, and the final task migration path and migration task replica are determined accordingly. The task migration path and the migration task replica are then written into the specific scheduling strategy.

[0036] As a further preferred embodiment of the present invention, after selecting the optimal migration target based on the real-time load parameters in the task migration negotiation response, and determining the final task migration path and the migration task replica accordingly, and writing the task migration path and the migration task replica into the specific scheduling strategy, the method further includes:

[0037] In the Source Computing Center, a clone copy of the task to be migrated is generated, and the clone copy is marked as the migration task copy;

[0038] The copy of the migration task is transmitted to the intelligent computing center corresponding to the optimal migration target;

[0039] Before the migration command takes effect, the cloned copy is computed in parallel at the source computing center and the computing center corresponding to the optimal migration target to achieve seamless succession of computing tasks.

[0040] As a further preferred embodiment of the present invention, the method further includes:

[0041] Periodically aggregate the scheduling priority factors of all power grid nodes and the computing power load factors of all intelligent computing centers to form a global system state snapshot;

[0042] Based on the global system state snapshot, system-level conflicts and coordination opportunities are identified. All intelligent computing centers that plan to execute migration strategies are traversed, and the predicted load increment contained in the computing load factor is aggregated to the target node. When the aggregated load increment of a target node exceeds the acceptance capacity represented by the scheduling priority factor, migration congestion conflict is marked.

[0043] Based on the identification results, global evolution parameters are dynamically generated and broadcast to adjust the local decision-making logic. When a conflict or opportunity is identified, global evolution parameters are dynamically generated and broadcast to correct the decision-making logic of the local agent and reduce the convergence of load increments to the target node. If a collaborative opportunity for large-scale renewable energy grid connection is identified, global evolution parameters are broadcast to increase the weight of the renewable energy output prediction parameters in that area and guide more computing power loads to gather there.

[0044] Furthermore, the identification of synergistic opportunities for large-scale renewable energy grid integration also includes:

[0045] Initiate an overload proposal that includes the reorganization time period and target region for the computing power flow;

[0046] Receive feedback data from each intelligent computing center regarding the suggestions, including a list of tasks that can be participated in;

[0047] Based on the feedback data, deferred tasks are orchestrated, and centralized scheduling instructions are generated that are directed to the target area.

[0048] Secondly, the present invention provides a power system computing power collaborative scheduling system based on a regional-level intelligent computing center, comprising:

[0049] The power grid situation awareness module is used to acquire real-time operation data and forecast data of the regional power grid, and to calculate the scheduling priority factor of each node in the power grid.

[0050] The computing power situation awareness module is used to acquire real-time task queue data and computing resource status data of each intelligent computing center, and to calculate the computing power load factor of each intelligent computing center.

[0051] The collaborative decision engine module is used to obtain a collaborative strategy library, input the scheduling priority factor and the computing load factor into the collaborative strategy library for matching, and generate a set of task scheduling strategies.

[0052] The instruction generation and distribution module is used to generate and issue power dispatch instructions and computing power dispatch instructions according to the task scheduling strategy set.

[0053] The global evolution coordination module is used to periodically aggregate system states, identify system-level conflicts and opportunities for collaboration, and generate global evolution parameters for adjusting local decision-making logic.

[0054] Thirdly, an electronic device includes: a processor and a memory; the memory is used to store a computer program, which, when executed by the processor, causes the electronic device to perform the power system computing power and power coordinated scheduling method based on a regional-level intelligent computing center as described in the first aspect.

[0055] Fourthly, a computer-readable storage medium includes: a computer program or instructions; when the computer program or instructions are executed on a computer, the computer causes the computer to perform the power system computing power and power coordinated dispatch method based on a regional-level intelligent computing center as described in the first aspect.

[0056] The beneficial effects of this invention are as follows:

[0057] This invention achieves deep integration of the power system and the computing system through a bidirectional sensing collaborative scheduling model. Through data processing and modeling, the power grid can understand the flexibility of the computing load, and the computing system can perceive the carrying capacity of the power grid. This transforms computing scheduling from a passive cost response to an active resource coordination. By using scheduling priority factors and computing load factors, the state of the power grid and the intelligent computing center is quantified in multiple dimensions. Based on a comprehensive evaluation of multiple factors such as power supply margin, line congestion, task timeliness, and migration costs, the accuracy of resource matching and the scientific nature of decision-making are improved. By introducing a global evolutionary coordination and closed-loop feedback adjustment mechanism, the system is endowed with the ability to dynamically adapt and self-optimize. By learning from historical scheduling effects, the internal decision-making model is continuously corrected, enhancing the robustness to uncertainties such as renewable energy fluctuations and sudden computing tasks, and ensuring long-term stable and efficient operation. Attached Figure Description

[0058] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 A flowchart illustrating the power system computing power collaborative scheduling method based on a regional-level intelligent computing center provided by this invention;

[0060] Figure 2 A flowchart of a power system computing power collaborative scheduling system based on a regional-level intelligent computing center, provided by the present invention;

[0061] Figure 3 The structural diagram of the power system computing power collaborative scheduling system based on a regional-level intelligent computing center provided by the present invention. Detailed Implementation

[0062] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0063] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0064] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "comprising" or "including," and similar terms as used in this disclosure, mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, but do not exclude other elements or objects. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments. It should be noted that the embodiments of the present invention can be applied to any applicable scenario.

[0066] In this embodiment of the invention, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In specific implementation, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a correlation between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0067] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be elaborated upon here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In specific implementation, the required indication method can be selected according to specific needs. This embodiment of the invention does not limit the selected indication method; therefore, the indication methods involved in this embodiment of the invention should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0068] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this embodiment of the invention. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0069] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This embodiment of the invention does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or electronic device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or electronic device. The type of memory can be any form of storage medium, and this embodiment of the invention does not limit this.

[0070] In the embodiments of this invention, the “protocol” may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to a future power system computing power collaborative scheduling method system based on a regional-level intelligent computing center. The embodiments of this invention do not specifically limit this.

[0071] In this embodiment of the invention, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0072] See Figure 1This invention provides a power system computing power collaborative scheduling method based on a regional-level intelligent computing center. This method is applied to a power system computing power collaborative scheduling system based on a regional-level intelligent computing center. The regional-level intelligent computing center-based power system computing power collaborative scheduling system includes regional power grid objects for forming the power grid, an intelligent computing center, a power grid control system for dispatching, and control terminals. Specifically, this method includes:

[0073] Step 101: Obtain real-time operation data and forecast data of the regional power grid, and calculate the scheduling priority factor of each node of the power grid based on the real-time operation data and forecast data;

[0074] Step 102: Obtain real-time task queue data and computing resource status data of each intelligent computing center, and calculate the computing load factor of each intelligent computing center based on the real-time task queue data and computing resource status data;

[0075] Step 103: Obtain a collaborative strategy library containing symbiotic strategy, migration strategy and buffer strategy; input the scheduling priority factor and the computing load factor into the collaborative strategy library for matching to generate a task scheduling strategy set.

[0076] Step 104: Based on the set of task scheduling strategies, generate and issue power scheduling instructions and computing power scheduling instructions to the corresponding power grid control system and intelligent computing center task management system.

[0077] This invention collects real-time power grid operation data and intelligent computing center task and resource data, cleans, merges, and calculates the collected data to generate scheduling priority factors and computing load factors. Based on a collaborative strategy library, it performs multi-factor matching to generate a set of scheduling strategies and issues scheduling instructions to the power grid control system and the intelligent computing center task management system, thereby achieving real-time monitoring of scheduling execution effects and forming a closed-loop optimization.

[0078] See Figure 2 In step 101, real-time operating data and forecast data of the regional power grid are acquired, and the scheduling priority factor of each node of the power grid is calculated based on the real-time operating data and forecast data, including:

[0079] The power supply margin parameters, line transmission congestion parameters, and real-time electricity price parameters of each node are extracted from the real-time operation data, and the renewable energy output prediction parameters are extracted from the prediction data to form a multi-dimensional power grid state parameter set.

[0080] Obtain the first weight allocation to characterize the importance attached to grid stability, transmission economy, electricity cost, and green energy consumption;

[0081] The first weight configuration is used to weight and fuse the multidimensional power grid state parameter set to generate the scheduling priority factor.

[0082] Real-time operational data is collected through SCADA systems, PMUs, and smart meters. This real-time data includes node voltage, current, power, frequency, and load curves. Forecast data is generated based on meteorological data, historical load data, and user behavior, using LSTM and Transformer models to produce load forecasts and renewable energy output forecasts for the next 1 to 24 hours. The real-time and forecast data are clarified and normalized to eliminate the influence of dimensions. Then, node feature vectors are constructed, and a weighted comprehensive evaluation and machine learning classification model is used to calculate the scheduling priority factor for each node.

[0083] In step 102, real-time task queue data and computing resource status data of each intelligent computing center are obtained, and the computing load factor of each intelligent computing center is calculated based on the real-time task queue data and computing resource status data, including:

[0084] The computational parameters, delay time parameters, and data migration cost parameters of the tasks to be processed are parsed from the real-time task queue data to form a set of task flexibility parameters;

[0085] Obtain the unit computing energy consumption coefficient for calibrating the power consumption per unit of computing load, and calculate the predicted power load increment based on the computing load parameters and the unit computing energy consumption coefficient;

[0086] The predicted power load increment is corrected by combining the task flexibility parameter set to generate the computing power load factor.

[0087] Real-time task queue data, including task type, computational load, deadline, and priority, is obtained through the intelligent computing center's task management system. Computing resource status data, including GPU / CPU utilization, memory usage, network bandwidth, and storage I / O, is acquired through the resource monitoring system. A computing load factor model is constructed by calculating task density, the proportion of urgent tasks, average remaining time, overall resource utilization, and bottleneck indices for each resource dimension. This model outputs a computing load factor for each intelligent computing center; the computing load factor model is a weighted sum of static and dynamic loads.

[0088] In step 103, a collaborative strategy library containing symbiotic strategies, migration strategies, and buffering strategies is obtained. The scheduling priority factor and the computing load factor are input into the collaborative strategy library for matching to generate a task scheduling strategy set, including:

[0089] Based on the numerical combination of the scheduling priority factor and the computing load factor, the highest priority local collaborative strategy is matched from the collaborative strategy library;

[0090] Obtain the rule parameters used to convert the local collaboration strategy into executable instructions;

[0091] Based on the local collaboration strategy and the rule parameters, the tasks in the real-time task queue data are processed to generate specific scheduling strategies that include task execution location, task execution time and task processing method, and these strategies are aggregated to form the task scheduling strategy set.

[0092] The symbiotic strategy is suitable for scenarios with high power grid load and low computing load. It releases local power grid pressure by scheduling computing tasks to centers with lighter loads. The migration strategy is suitable for scenarios where one computing center is overloaded, while other centers have spare resources. It performs task migration. The buffering strategy is suitable for scenarios where both power grid and computing power are strained. It buffers pressure by adjusting task execution time, such as delaying low-priority tasks and using spare computing resources.

[0093] Based on the priority factor list of each node and the computing power load factor list of each intelligent computing center, strategy recommendations are made to generate one or more feasible task scheduling strategy sets. Each task scheduling strategy includes the target intelligent computing center, the list of scalable tasks, the expected execution time window, the expected degree of grid load relief, and the expected change in computing power utilization.

[0094] In step 104, based on the task scheduling strategy set, power dispatch instructions and computing power dispatch instructions are generated and issued to the corresponding power grid control system and intelligent computing center task management system, specifically including:

[0095] Receive instruction execution result data fed back by the power grid control system and the intelligent computing center task management system;

[0096] Obtain system optimization targets for evaluating the economy and efficiency of system operation, and generate adjustment signals based on the performance deviation between the instruction execution result data and the system optimization targets;

[0097] Based on the adjustment signal, adjust the first weight configuration and the rule parameters.

[0098] Power dispatch instructions are for the power grid control system, including adjusting the output of generation-side nodes, suggesting load transfer for electricity consumption, and charging and discharging instructions for energy storage. Computing power dispatch instructions are for the intelligent computing center task management system, including task migration instructions for source centers, target centers, and task IDs, new task allocation instructions, and resource reservation and release instructions. They are sent to each system through standard communication protocols and can support instruction confirmation and acknowledgment mechanisms.

[0099] The process of generating and issuing power dispatch instructions and computing power dispatch instructions to the corresponding power grid control system and intelligent computing center task management system based on the set of task scheduling strategies also includes:

[0100] When the matched local collaboration strategy is the migration strategy.

[0101] Based on the scheduling priority factor, a target node is selected from all power grid nodes, and a task migration negotiation request is sent to the intelligent computing center associated with the target node.

[0102] Receive the task migration negotiation response returned by the intelligent computing center, which includes its real-time load parameters;

[0103] The optimal migration target is selected based on the real-time load parameters in the task migration negotiation response, and the final task migration path and migration task replica are determined accordingly. The task migration path and the migration task replica are then written into the specific scheduling strategy.

[0104] In this embodiment of the invention, after selecting the optimal migration target based on the real-time load parameters in the task migration negotiation response, and determining the final task migration path and migration task replica accordingly, and writing the task migration path and the migration task replica into the specific scheduling strategy, the method further includes:

[0105] In the Source Computing Center, a clone copy of the task to be migrated is generated, and the clone copy is marked as the migration task copy;

[0106] The copy of the migration task is transmitted to the intelligent computing center corresponding to the optimal migration target;

[0107] Before the migration command takes effect, the cloned copy is computed in parallel at the source computing center and the computing center corresponding to the optimal migration target to achieve seamless succession of computing tasks.

[0108] The power system computing power collaborative scheduling method based on a regional-level intelligent computing center provided by this invention further includes:

[0109] Step 105: Periodically aggregate the scheduling priority factors of all power grid nodes and the computing power load factors of all intelligent computing centers to form a global system state snapshot;

[0110] Based on the global system state snapshot, system-level conflicts and coordination opportunities are identified. All intelligent computing centers that plan to execute migration strategies are traversed, and the predicted load increment contained in the computing load factor is aggregated to the target node. When the aggregated load increment of a target node exceeds the acceptance capacity represented by the scheduling priority factor, migration congestion conflict is marked.

[0111] Based on the identification results, global evolution parameters are dynamically generated and broadcast to adjust the local decision-making logic. When a conflict or opportunity is identified, global evolution parameters are dynamically generated and broadcast to correct the decision-making logic of the local agent and reduce the convergence of load increments to the target node. If a collaborative opportunity for large-scale renewable energy grid connection is identified, global evolution parameters are broadcast to increase the weight of the renewable energy output prediction parameters in that area and guide more computing power loads to gather there.

[0112] If synergistic opportunities for large-scale renewable energy grid integration are identified, these also include:

[0113] Initiate an overload proposal that includes the reorganization time period and target region for the computing power flow;

[0114] Receive feedback data from each intelligent computing center regarding the suggestions, including a list of tasks that can be participated in;

[0115] Based on the feedback data, deferred tasks are orchestrated, and centralized scheduling instructions are generated that are directed to the target area.

[0116] This invention achieves deep integration of the power system and the computing system through a bidirectional sensing collaborative scheduling model. Through data processing and modeling, the power grid can understand the flexibility of the computing load, and the computing system can perceive the carrying capacity of the power grid. This transforms computing scheduling from a passive cost response to an active resource coordination. By using scheduling priority factors and computing load factors, the state of the power grid and the intelligent computing center is quantified in multiple dimensions. Based on a comprehensive evaluation of multiple factors such as power supply margin, line congestion, task timeliness, and migration costs, the accuracy of resource matching and the scientific nature of decision-making are improved. By introducing a global evolutionary coordination and closed-loop feedback adjustment mechanism, the system is endowed with the ability to dynamically adapt and self-optimize. By learning from historical scheduling effects, the internal decision-making model is continuously corrected, enhancing the robustness to uncertainties such as renewable energy fluctuations and sudden computing tasks, and ensuring long-term stable and efficient operation.

[0117] Example 2:

[0118] See Figure 3 This invention provides a power system computing power collaborative scheduling system based on a regional-level intelligent computing center, comprising:

[0119] The power grid situation awareness module 201 is used to acquire real-time operation data and forecast data of the regional power grid, and to calculate the scheduling priority factor of each node of the power grid.

[0120] The computing power situation awareness module 202 is used to acquire real-time task queue data and computing resource status data of each intelligent computing center, and to calculate the computing power load factor of each intelligent computing center.

[0121] The collaborative decision engine module 203 is used to obtain a collaborative strategy library, input the scheduling priority factor and the computing load factor into the collaborative strategy library for matching, and generate a set of task scheduling strategies.

[0122] The instruction generation and distribution module 204 is used to generate and issue power dispatch instructions and computing power dispatch instructions according to the task scheduling strategy set;

[0123] The global evolution coordination module 205 is used to periodically aggregate system states, identify system-level conflicts and cooperation opportunities, and generate global evolution parameters for adjusting local decision-making logic.

[0124] The various variations and specific examples of the power system computing power collaborative scheduling method based on the regional intelligent computing center in the foregoing embodiments are also applicable to the power system computing power and power collaborative scheduling system of the regional intelligent computing center in this embodiment. Through the foregoing detailed description of the power system computing power collaborative scheduling method based on the regional intelligent computing center, those skilled in the art can clearly understand the power system computing power and power collaborative scheduling system of the regional intelligent computing center in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0125] Example 3:

[0126] This invention proposes an electronic device, which can be a network device, or a chip (system) or other component or assembly that can be disposed in a network device. The electronic device may include a processor. Optionally, the electronic device may also include a memory and / or a transceiver. The processor is coupled to the memory and transceiver, for example, by means of a communication bus connection.

[0127] The following is a detailed introduction to the various components of the electronic device:

[0128] In this context, the processor is the control center of the electronic device. It can be a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0129] Optionally, the processor can perform various functions of the electronic device by running or executing software programs stored in memory and calling data stored in memory, such as executing the above-mentioned power system computing power collaborative scheduling method based on regional intelligent computing centers.

[0130] In a specific implementation, as one example, the processor may include one or more CPUs, such as CPU0 and CPU1.

[0131] In a specific implementation, as one example, the electronic device may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0132] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0133] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic 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 not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processor through an interface circuit of an electronic device; the embodiments of the present invention do not specifically limit this.

[0134] A transceiver is used for communication with other electronic devices. For example, if the electronic device is a terminal, the transceiver can be used to communicate with a network device or with another terminal device. Similarly, if the electronic device is a network device, the transceiver can be used to communicate with a terminal or with another network device.

[0135] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0136] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the interface circuit of the electronic device. This embodiment of the invention does not specifically limit this.

[0137] It is understood that the structure of an electronic device does not constitute a limitation on the electronic device. An actual electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0138] Furthermore, the technical effects of the electronic devices can be referenced from the technical effects of the power system computing power collaborative scheduling method based on regional intelligent computing centers described in the above method embodiments, and will not be repeated here.

[0139] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0140] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DRRAM).

[0141] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0142] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0143] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software 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 implementations should not be considered beyond the scope of this invention.

[0144] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0145] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0146] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] In addition, the functional units in the various embodiments of the present 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.

[0148] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0149] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A power system computing power collaborative scheduling method based on a regional-level intelligent computing center, characterized in that, The method includes: Obtain real-time operation data and forecast data of the regional power grid, and calculate the scheduling priority factor of each node of the power grid based on the real-time operation data and forecast data; Obtain real-time task queue data and computing resource status data of each intelligent computing center, and calculate the computing load factor of each intelligent computing center based on the real-time task queue data and computing resource status data; Obtain a collaborative strategy library containing symbiotic strategies, migration strategies, and buffering strategies; input the scheduling priority factor and the computing load factor into the collaborative strategy library for matching to generate a task scheduling strategy set. Based on the set of task scheduling strategies, power dispatch instructions and computing power dispatch instructions are generated and issued to the corresponding power grid control system and intelligent computing center task management system.

2. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 1, characterized in that, The process of acquiring real-time operational data and forecast data of the regional power grid, and calculating the scheduling priority factor for each node of the power grid based on the real-time operational data and forecast data, includes: The power supply margin parameters, line transmission congestion parameters, and real-time electricity price parameters of each node are extracted from the real-time operation data, and the renewable energy output prediction parameters are extracted from the prediction data to form a multi-dimensional power grid state parameter set. Obtain the first weight allocation to characterize the importance attached to grid stability, transmission economy, electricity cost, and green energy consumption; The first weight configuration is used to weight and fuse the multidimensional power grid state parameter set to generate the scheduling priority factor.

3. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 1, characterized in that, The process of acquiring real-time task queue data and computing resource status data of each intelligent computing center, and calculating the computing load factor of each intelligent computing center based on the real-time task queue data and computing resource status data, includes: The computational parameters, delay time parameters, and data migration cost parameters of the tasks to be processed are parsed from the real-time task queue data to form a set of task flexibility parameters; Obtain the unit computing energy consumption coefficient for calibrating the power consumption per unit of computing load, and calculate the predicted power load increment based on the computing load parameters and the unit computing energy consumption coefficient; The predicted power load increment is corrected by combining the task flexibility parameter set to generate the computing power load factor.

4. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 1, characterized in that, The step of obtaining a collaborative strategy library containing symbiotic strategies, migration strategies, and buffering strategies, and inputting the scheduling priority factor and the computing load factor into the collaborative strategy library for matching to generate a task scheduling strategy set includes: Based on the numerical combination of the scheduling priority factor and the computing load factor, the highest priority local collaborative strategy is matched from the collaborative strategy library; Obtain the rule parameters used to convert the local collaboration strategy into executable instructions; Based on the local collaboration strategy and the rule parameters, the tasks in the real-time task queue data are processed to generate specific scheduling strategies that include task execution location, task execution time and task processing method, and these strategies are aggregated to form the task scheduling strategy set.

5. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 1, characterized in that, The step of generating and issuing power dispatch instructions and computing power dispatch instructions to the corresponding power grid control system and intelligent computing center task management system based on the task scheduling strategy set specifically includes: Receive instruction execution result data fed back by the power grid control system and the intelligent computing center task management system; Obtain system optimization targets for evaluating the economy and efficiency of system operation, and generate adjustment signals based on the performance deviation between the instruction execution result data and the system optimization targets; Based on the adjustment signal, adjust the first weight configuration and rule parameters.

6. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 5, characterized in that, The step of generating and issuing power dispatch instructions and computing power dispatch instructions to the corresponding power grid control system and intelligent computing center task management system based on the task scheduling strategy set also includes: When the matched local collaboration strategy is the migration strategy. Based on the scheduling priority factor, a target node is selected from all power grid nodes, and a task migration negotiation request is sent to the intelligent computing center associated with the target node. Receive the task migration negotiation response returned by the intelligent computing center, which includes its real-time load parameters; The optimal migration target is selected based on the real-time load parameters in the task migration negotiation response, and the final task migration path and migration task replica are determined accordingly. The task migration path and the migration task replica are then written into the specific scheduling strategy.

7. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 6, characterized in that, After selecting the optimal migration target based on the real-time load parameters in the task migration negotiation response, and determining the final task migration path and migration task replica accordingly, and writing the task migration path and the migration task replica into the specific scheduling strategy, the method further includes: At the Source Computing Center, a clone copy of the task to be migrated is generated, and the clone copy is marked as the migration task copy. The copy of the migration task is transmitted to the intelligent computing center corresponding to the optimal migration target; Before the migration command takes effect, the cloned copy is computed in parallel at the source computing center and the computing center corresponding to the optimal migration target to achieve seamless succession of computing tasks.

8. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 1, characterized in that, The method further includes: Periodically aggregate the scheduling priority factors of all power grid nodes and the computing power load factors of all intelligent computing centers to form a global system state snapshot; Based on the global system state snapshot, system-level conflicts and coordination opportunities are identified. All intelligent computing centers that plan to execute migration strategies are traversed, and the predicted load increment contained in the computing load factor is aggregated to the target node. When the aggregated load increment of a target node exceeds the acceptance capacity represented by the scheduling priority factor, migration congestion conflict is marked. Based on the identification results, global evolution parameters are dynamically generated and broadcast to adjust the local decision-making logic. When a conflict or opportunity is identified, global evolution parameters are dynamically generated and broadcast to correct the decision-making logic of the local agent and reduce the convergence of load increments to the target node. If a collaborative opportunity for large-scale renewable energy grid connection is identified, global evolution parameters are broadcast to increase the weight of the renewable energy output prediction parameters in that area and guide more computing power loads to gather there.

9. The power system computing power collaborative scheduling method based on a regional-level intelligent computing center according to claim 8, characterized in that, If a synergistic opportunity for large-scale renewable energy grid connection is identified, it also includes: Initiate an overload proposal that includes the reorganization time period and target region for the computing power flow; Receive feedback data from each intelligent computing center regarding the suggestions, including a list of tasks that can be participated in; Based on the feedback data, deferred tasks are orchestrated, and centralized scheduling instructions are generated that are directed to the target area.

10. A power system computing power collaborative scheduling system based on a regional-level intelligent computing center, employing the power system computing power collaborative scheduling method based on a regional-level intelligent computing center as described in any one of claims 1-9, characterized in that, include: The power grid situation awareness module is used to acquire real-time operation data and forecast data of the regional power grid, and to calculate the scheduling priority factor of each node in the power grid. The computing power situation awareness module is used to acquire real-time task queue data and computing resource status data of each intelligent computing center, and to calculate the computing power load factor of each intelligent computing center. The collaborative decision engine module is used to obtain a collaborative strategy library, input the scheduling priority factor and the computing load factor into the collaborative strategy library for matching, and generate a set of task scheduling strategies. The instruction generation and distribution module is used to generate and issue power dispatch instructions and computing power dispatch instructions according to the task scheduling strategy set. The global evolution coordination module is used to periodically aggregate system states, identify system-level conflicts and opportunities for collaboration, and generate global evolution parameters for adjusting local decision-making logic.

11. An electronic device, characterized in that, include: Processor and memory; The memory is used to store computer programs, which, when executed by the processor, cause the electronic device to perform the power system computing power collaborative scheduling method based on a regional intelligent computing center as described in any one of claims 1-9.

12. A computer-readable storage medium, comprising: Computer programs or instructions; When the computer program or instructions are run on the computer, the computer performs the power system computing power and power collaborative scheduling method based on a regional intelligent computing center as described in any one of claims 1-9.

Images