A scheduling instruction allocation method, apparatus, device, medium and product

Abstract

The application discloses a dispatching instruction allocation method and device, equipment, medium and product, relates to the power system dispatching technical field, and the method comprises the following steps: acquiring a to-be-allocated resource list and total regulation demand; for each resource in the to-be-allocated resource list, acquiring historical response performance data and real-time state information of the resource, calculating a comprehensive contribution degree score, calculating an allocable regulation amount of each resource, calculating a dynamic allocation weight of each resource, calculating an initial allocation amount of each resource, performing a regulation capacity boundary constraint check on the initial allocation amount of each resource, accumulating a part exceeding the regulation capacity range as an unallocated residual error, and then allocating the unallocated residual error to resources still having a regulation margin in proportion to obtain a final allocation amount of each resource. The application realizes adaptive optimization of the allocation strategy in long-term operation, improves resource contribution degree, and provides a precise, efficient and traceable dispatching instruction allocation scheme for a virtual power plant and a demand response business.

Description

Technical Field

[0001] This application relates to the field of power system dispatching technology, and in particular to a method, apparatus, equipment, medium and product for distributing dispatching instructions. Background Technology

[0002] In power system dispatching and demand response operations, when the grid dispatching agency issues regulation requests such as peak shaving, frequency regulation, or peak shaving and valley filling, the aggregator needs to decompose the total regulation power (i.e., the total dispatching command) into multiple sub-commands and distribute them to various adjustable resources (such as distributed generation, energy storage systems, and interruptible loads). This command allocation process is a key link in ensuring the balance of power grid supply and demand and the effectiveness of the response.

[0003] Currently, the mainstream scheduling instruction allocation methods mainly include the following categories: (1) Proportional allocation method The total regulation demand is proportionally allocated based on the rated capacity or maximum adjustable capacity of each resource. A representative technology is the IEC 61850 resource allocation protocol. This method is simple to implement and computationally inexpensive, but it uses capacity as the sole allocation criterion and fails to consider the significant differences in historical response performance among different resources. This results in high-accuracy and high-speed resources failing to play a greater role, making it difficult to optimize the overall response performance.

[0004] (2) Fixed priority allocation method Instructions are allocated sequentially according to a preset priority order, with higher-priority resources receiving allocations first. A representative technology is the priority queue in traditional SCADA systems. This method ensures priority response for key resources, but once the priority is set, it remains fixed and cannot be dynamically adjusted based on the real-time status of the resources (such as current output, equipment health status, and adjustability margin). This results in poor flexibility and can easily lead to overload of high-priority resources.

[0005] (3) Random allocation method Indiscriminate random allocation of adjustment parameters. Representative techniques include the basic round-robin allocation algorithm. This type of method is the simplest to implement, but the allocation result is uncontrollable and it is not suitable for scheduling scenarios with strict requirements on response quality and reliability.

[0006] (4) Allocation method based on mathematical optimization Optimization models are established to solve for the optimal allocation scheme. Representative techniques include second-order cone programming and genetic algorithms. While these methods can theoretically obtain the optimal solution, they have the following drawbacks: First, they have high computational complexity, making it difficult to meet the real-time requirements of scheduling; second, they are highly dependent on the accuracy of the system model, and deviations in model parameters can lead to deterioration of the optimization results; third, they also struggle to effectively integrate the historical response characteristics of resources into the optimization objective.

[0007] While the aforementioned methods have some applicability in specific scenarios, they still suffer from the following fundamental technical shortcomings in dynamic instruction allocation that considers differences in response quality and real-time state constraints: (1) The historical response performance of resources was not quantitatively assessed and included in the allocation basis.

[0008] Existing methods use fixed capacity ratios, fixed priorities, or single-cycle optimization models for allocation, failing to construct a systematic contribution evaluation system. They also fail to quantify historical resource response performance (such as response accuracy, timeliness, stability, and participation rate) into calculable contribution indicators and incorporate them into the dynamic calculation of allocation weights. The direct consequence of this deficiency is that resources with good response quality do not receive a larger share of instructions, while resources with poor response quality still bear the same or even a higher proportion of tasks. There is a lack of effective incentive mechanisms to guide resources to proactively improve response quality, making it difficult to continuously optimize the overall response performance.

[0009] (2) The allocation weight is statically fixed and cannot take into account the differences in the real-time adjustment capabilities of resources.

[0010] In existing methods, the allocation weights remain unchanged once set, or are calculated solely based on static parameters, failing to simultaneously integrate the overall contribution score of resources and real-time allocable adjustability during the allocation process. This results in two consequences: on the one hand, resources with high contribution but insufficient current adjustability are still assigned a large number of tasks, leading to a high failure rate; on the other hand, resources with strong adjustability but whose contribution is not taken into account cannot be prioritized, resulting in insufficient resource utilization.

[0011] (3) The allocation scheme lacks constraint verification and residual redistribution mechanism.

[0012] Existing methods typically lack an active verification step for the adjustment capacity boundaries of each resource after generating the allocation scheme, or only perform simple over-limit truncation. This deficiency leads to the following: when the amount of resources allocated exceeds their actual adjustable upper and lower limits, the excess portion is not systematically accumulated and redistributed, resulting in the inability to fully decompose the total adjustment demand; or some resources fail to execute instructions due to overload, while the capacity of some resources is not fully utilized, resulting in low executability and resource utilization efficiency of the overall allocation scheme. Summary of the Invention

[0013] The purpose of this application is to provide a method, apparatus, equipment, medium, and product for allocating dispatch instructions, which can effectively incentivize high-quality resources, significantly improve overall response accuracy, greatly reduce the proportion of resources with excessive response deviation, significantly improve instruction execution success rate, and significantly increase the average resource load rate. It enables adaptive optimization of allocation strategies in long-term operation, continuously improves resource contribution, and provides a precise, efficient, and traceable dispatch instruction allocation solution for virtual power plants and demand response operations.

[0014] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for allocating scheduling instructions, including: Obtain the list of resources to be allocated and the total adjustment requirements; and for each resource in the list of resources to be allocated, obtain the historical response performance data and real-time status information of that resource, wherein the historical response performance data includes response accuracy, response timeliness, response stability and historical participation rate; Based on the historical response performance data, the response accuracy score, response timeliness score, response stability score, and historical participation rate score of the resource are calculated. The response accuracy score, response timeliness score, response stability score, and historical participation rate score are then weighted and summed to obtain the comprehensive contribution score of the resource. Based on the response direction of the total adjustment demand and the real-time status information of each resource, calculate the allocatable adjustment amount for each resource; Based on the comprehensive contribution score of all resources in the list of resources to be allocated and the allocable adjustment amount, calculate the dynamic allocation weight of each resource; Calculate the initial allocation amount for each resource based on the total adjustment demand and the dynamic allocation weight of each resource; The initial allocation amount of each resource is constrained and verified against the adjustment capacity boundary. The portion exceeding the adjustment capacity range is accumulated as an unallocated residual. The unallocated residual is then allocated proportionally to resources with remaining adjustment margins to obtain the final allocation amount for each resource.

[0015] Optionally, the formula for calculating the comprehensive contribution score is: ; In the formula, This indicates the overall contribution score. This indicates the accuracy score of the response. The score indicates the timeliness of the response. This indicates the response stability score. Indicates the historical participation rate score. Indicates the weighting coefficient; Among them, the response accuracy score The calculation formula is: ; In the formula, This represents the single-response accuracy of resource r in the i-th response. Indicates the number of historical responses; The response timeliness score The calculation formula is: ; In the formula, This indicates the timeliness of the i-th response of resource r. The response stability score The calculation formula is: ; In the formula, The standard deviation of the historical bias of resource r is represented by This represents the mean of the historical deviations of resource r; Historical participation rate score The calculation formula is: ; In the formula, This indicates the number of times resource r actually participated in the response. This represents the total number of times resource r has been notified to participate in scheduling.

[0016] Optionally, calculating the allocatable adjustment amount for each resource based on the response direction of the total adjustment demand and the real-time status information of each resource specifically includes: When the total adjustment demand is positive, the allocatable adjustment amount is the resource's upward adjustment capacity, which is the difference between the maximum adjustable output of the resource and the current output. When the total adjustment demand is negative, the allocatable adjustment amount is the resource's downward adjustment capability, which is the difference between the current output of the resource and the minimum adjustable output. If the equipment operating status of the resource is abnormal, then the allocatable adjustment amount is zero.

[0017] Optionally, the formula for calculating the dynamically allocated weights is: ; In the formula, This represents the dynamic allocation weight of resource r. This indicates the overall contribution score. This represents the allocatable adjustment amount of resource r. Indicates the sensitivity coefficient of contribution. Represents the sensitivity coefficient of allocatable quantity. This represents the list of resources to be allocated. This indicates the index for summation and traversal.

[0018] Optionally, the formula for calculating the initial allocation is: ; In the formula, This represents the initial allocation amount of resource r. Indicates aggregate adjustment demand. This represents the dynamic allocation weight of resource r.

[0019] Optionally, the step of allocating unallocated residuals proportionally to resources with remaining adjustment margins specifically includes: From the list of resources to be allocated, select resources whose allocated amount is less than the upward adjustment capacity and whose equipment is operating normally, and use them as the set of remaining resources. Calculate the remaining allocable capacity of each resource in the remaining resource set, where the remaining allocable capacity is the resource's upscaling capacity minus the resource's already allocated amount; The unallocated residual is allocated to the corresponding resource based on the proportion of the remaining allocable capacity of each resource to the total remaining allocable capacity of the remaining resource set.

[0020] Secondly, this application provides a scheduling instruction allocation device, comprising: The data acquisition module is used to acquire the list of resources to be allocated and the total adjustment requirements; and for each resource in the list of resources to be allocated, to acquire the historical response performance data and real-time status information of that resource, wherein the historical response performance data includes response accuracy, response timeliness, response stability and historical participation rate; The contribution calculation module is used to calculate the response accuracy score, response timeliness score, response stability score, and historical participation rate score of the resource based on the historical response performance data, and to perform a weighted summation of the response accuracy score, response timeliness score, response stability score, and historical participation rate score to obtain the comprehensive contribution score of the resource. The allocatable quantity calculation module is used to calculate the allocatable adjustment quantity of each resource based on the response direction of the total adjustment demand and the real-time status information of each resource. The dynamic weight calculation module is used to calculate the dynamic allocation weight of each resource based on the comprehensive contribution score of all resources in the resource list to be allocated and the allocable adjustment amount. The initial allocation module is used to calculate the initial allocation amount of each resource based on the total adjustment demand and the dynamic allocation weight of each resource. The constraint verification and residual redistribution module is used to perform constraint verification on the adjustment capability boundary of the initial allocation amount of each resource, accumulate the part exceeding the adjustment capability range as unallocated residual, and then allocate the unallocated residual proportionally to the resources that still have adjustment margin to obtain the final allocation amount of each resource.

[0021] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the scheduling instruction allocation method described in any one of the above.

[0022] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the scheduling instruction allocation method described in any one of the above.

[0023] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the scheduling instruction allocation method described above.

[0024] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a scheduling instruction allocation method, apparatus, device, medium, and product. Through the steps of "obtaining a list of resources to be allocated and total adjustment demand; and for each resource in the list, obtaining historical response performance data and real-time status information of that resource, including response accuracy, response timeliness, response stability, and historical participation rate; calculating the response accuracy score, response timeliness score, response stability score, and historical participation rate score of that resource based on the historical response performance data, and weighting and summing the response accuracy score, response timeliness score, response stability score, and historical participation rate score to obtain the comprehensive contribution score of that resource," this application solves the technical problems of static allocation weights and failure to incorporate historical response performance into the allocation criteria in existing technologies. It achieves a quantitative assessment of resource response quality, enabling resources with excellent historical response performance to receive higher allocation weights, thereby incentivizing resources to continuously improve response quality and enhance overall response accuracy. By employing the steps of "calculating the allocatable adjustment amount for each resource based on the response direction of the overall adjustment demand and the real-time status information of each resource; calculating the dynamic allocation weight for each resource based on the comprehensive contribution score and allocatable adjustment amount of all resources in the resource list to be allocated; and calculating the initial allocation amount for each resource based on the overall adjustment demand and the dynamic allocation weight of each resource," the technical problems of fixed allocation weights and inability to take into account the differences in real-time adjustment capabilities of resources in existing technologies are solved. This achieves dynamic adjustment of allocation weights, ensuring that the generated initial allocation scheme reflects both the incentive for high-quality resources and matches the actual adjustability of each resource. It avoids allocating adjustment tasks to resources without adjustment capabilities, ensuring the executability of the allocation scheme. Furthermore, through the parameterized configuration of contribution sensitivity coefficients and allocatable amount sensitivity coefficients, it can flexibly adapt to the differentiated needs of different business scenarios such as peak shaving, valley filling, frequency regulation, and peak adjustment. By performing constraint verification on the adjustment capacity boundary of the initial allocation amount of each resource, accumulating the portion exceeding the adjustment capacity range as unallocated residuals, and then proportionally allocating the unallocated residuals to resources with remaining adjustment margins to obtain the final allocation amount of each resource, this technology solves the technical problems in existing technologies where allocation schemes do not fully consider the real-time output upper and lower limits of resources, leading to command execution failures, and where residuals generated after constraint verification prevent the complete decomposition of total adjustment demand. This achieves a dual technical effect: on the one hand, constraint verification ensures that the final allocation amount of each resource does not exceed its actual adjustment capacity boundary, improving the command execution success rate; on the other hand, the residual redistribution mechanism proportionally allocates the unallocated residuals to resources with remaining adjustment margins, enabling the complete decomposition of total adjustment demand, while simultaneously increasing the average load rate of resources and significantly improving the utilization efficiency of the entire network's adjustment resources. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a diagram illustrating the application environment of a scheduling instruction allocation method according to an embodiment of this application. Figure 2 A flowchart illustrating a scheduling instruction allocation method provided in an embodiment of this application; Figure 3 A schematic diagram of the functional modules of a scheduling instruction allocation device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0027] 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 this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] The scheduling instruction allocation method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, the scheduling terminal 102 communicates with the scheduling decision server 104 via a network. The data storage system can store the data that the scheduling decision server 104 needs to process, including a resource registration database, a historical response database, and real-time monitoring data. The data storage system can be set up separately, integrated into the scheduling decision server 104, or placed in the cloud or on other servers. The scheduling terminal 102 can send scheduling requests to be allocated (including a list of resources to be allocated and overall adjustment requests) to the scheduling decision server 104. After receiving a scheduling request, the scheduling decision server 104 obtains historical response performance data and real-time status information for each resource in the resource list to be allocated. The historical response performance data includes response accuracy, response timeliness, response stability, and historical participation rate. Based on the historical response performance data, it calculates the response accuracy score, response timeliness score, response stability score, and historical participation rate score for each resource, and performs a weighted sum to obtain the comprehensive contribution score for that resource. According to the response direction of the overall adjustment request and the real-time status information of each resource, it calculates the allocatable adjustment amount for each resource. Based on the comprehensive contribution score and allocatable adjustment amount of all resources in the resource list to be allocated, it calculates the dynamic allocation weight for each resource. Based on the overall adjustment request and the dynamic allocation weight for each resource, it calculates the initial allocation amount for each resource. It performs constraint verification on the adjustment capacity boundary of the initial allocation amount for each resource, accumulates the portion exceeding the adjustment capacity range as unallocated residual, and then allocates the unallocated residual proportionally to resources with remaining adjustment margin to obtain the final allocation amount for each resource. The scheduling decision server 104 can feed back the final allocation of each resource to the scheduling terminal 102, and the instruction management server can generate scheduling instructions and issue them to each resource. Furthermore, after each resource executes the scheduling instructions, it feeds back the actual response power to the scheduling decision server 104 to update the historical response performance data of each resource in the historical response database. In some embodiments, the scheduling instruction allocation method can also be implemented separately by the scheduling decision server 104 or the scheduling terminal 102. For example, the scheduling terminal 102 can directly perform scheduling instruction allocation processing based on scheduling needs, or the scheduling decision server 104 can obtain scheduling needs from the data storage system and perform scheduling instruction allocation processing based on those needs.

[0030] The dispatch terminal 102 can be, but is not limited to, various desktop computers, laptops, tablets, industrial control computers, dispatch workstations, etc. The dispatch decision server 104 can be an independent server, a server cluster composed of multiple servers, or a cloud server. Each resource end can be an adjustable resource such as a distributed power source, energy storage system, or interruptible load, and its local control system can be an energy management system, energy storage management system, or load control system.

[0031] In one exemplary embodiment, such as Figure 2 As shown, a scheduling instruction allocation method is provided. This method is executed by a computer device, specifically, it can be executed alone by a scheduling terminal 102 or a scheduling decision server 104, or it can be executed jointly by the scheduling terminal and the scheduling decision server. In this embodiment, the method is applied to... Figure 1 Taking the scheduling decision server 104 as an example, the process includes the following steps 201 to 206. Wherein: Step 201: Obtain the list of resources to be allocated and the total adjustment requirements; and for each resource in the list of resources to be allocated, obtain the historical response performance data and real-time status information of that resource. The historical response performance data includes response accuracy, response timeliness, response stability and historical participation rate. Specifically, total regulation demand includes total target regulation power. (Positive values ​​indicate peak shaving, negative values ​​indicate valley filling, unit: kW), ResponseType (including peak shaving, valley filling, frequency regulation, and peak shaving), and allowable response time. (Maximum time allowed to complete adjustment, in minutes). The list of resources to be allocated is as follows: It includes information such as resource ID, name, and type.

[0032] The scheduling decision server retrieves historical response performance data for each resource from the historical response database, including the most recent N response event records (N defaults to 20), specifically including: (1) Response accuracy data: historical accuracy set ; (2) Response timeliness data: historical timeliness set ; (3) Response stability data: historical deviation set ; (4) Historical participation rate.

[0033] All of the above data are known quantities and come from a historical response database.

[0034] Meanwhile, the scheduling decision server obtains the current status information of each resource from the real-time monitoring system, including the current output. Maximum adjustable output Minimum adjustable output force Current SOC status (energy storage resources only, value 0-100%), equipment operating status (Including normal, alarm, fault, offline) Real-time data update time .

[0035] Step 202: Based on historical response performance data, calculate the response accuracy score, response timeliness score, response stability score, and historical participation rate score of the resource, and perform a weighted sum of the response accuracy score, response timeliness score, response stability score, and historical participation rate score to obtain the comprehensive contribution score of the resource. As an optional implementation method, the formula for calculating the overall contribution score is: ; In the formula, This indicates the overall contribution score. This indicates the accuracy score of the response. The score indicates the timeliness of the response. This indicates the response stability score. Indicates the historical participation rate score. Indicates the weighting coefficient; Weighting coefficient satisfy The values ​​can be 0.35, 0.25, 0.25, and 0.15. It should be noted that the above weighting coefficients can be configured and adjusted according to different business scenarios. For example, in frequency modulation scenarios, where timeliness of response is more important, the weighting coefficients can be appropriately increased. The value of is important; in demand response scenarios, where accuracy is paramount, the value can be appropriately increased. The value of can be flexibly adapted to the differentiated needs of different scenarios by configuring the weight coefficients through parameterization, without modifying the core algorithm logic.

[0036] Among them, the response accuracy score The calculation formula is: ; In the formula, This represents the single-response accuracy of resource r in the i-th response. Indicates the number of historical responses; Response timeliness score The calculation formula is: ; In the formula, This indicates the timeliness of the i-th response of resource r. Response stability score The calculation formula is: ; In the formula, The standard deviation of the historical bias of resource r is represented by This represents the mean of the historical deviations of resource r; the lower the volatility, the higher the stability score. It should be noted that when... When the average deviation of the historical response of the resource is zero, it is defined as follows: .

[0037] Historical participation rate score The calculation formula is: ; In the formula, This indicates the number of times resource r actually participated in the response. This represents the total number of times resource r has been notified to participate in scheduling.

[0038] Step 203: Calculate the allocatable adjustment amount for each resource based on the response direction of the total adjustment demand and the real-time status information of each resource. As an optional implementation, the allocatable adjustment amount for each resource is calculated, specifically including: When the total adjustment demand is positive, the allocable adjustment amount is the resource's upward adjustment capacity, which is the difference between the maximum adjustable output of the resource and the current output. When the total adjustment demand is negative, the allocable adjustment amount is the resource's downward adjustment capacity, which is the difference between the current output of the resource and the minimum adjustable output. If the equipment operating in the resource is in an abnormal state, the available adjustment amount is zero.

[0039] Specifically, for peak shaving response ( The upward and downward adjustment capabilities are as follows: ; ; The adjustable amount is: ; For valley filling response ( The calculation logic is the opposite: ; Simultaneously perform device status verification: If Normal, then .

[0040] Step 204: Calculate the dynamic allocation weight of each resource based on the comprehensive contribution score and allocable adjustment amount of all resources in the resource list to be allocated; As an optional implementation method, the formula for calculating dynamically allocated weights is: ; In the formula, This represents the dynamic allocation weight of resource r. This indicates the overall contribution score. This represents the allocatable adjustment amount of resource r. This represents the sensitivity coefficient of contribution, which can be set to 1.0. This represents the sensitivity coefficient for allocable quantity, which can be set to 0.5. This represents the list of resources to be allocated. This indicates the index for summation and traversal.

[0041] Specifically, and The value of can be adjusted according to the actual scheduling scenario. For example, in scenarios where priority needs to be given to ensuring response quality, can be increased. The value is used to reinforce the impact of contribution on weight; in scenarios requiring full utilization of large-capacity resources, it can be increased. The value is used to reinforce the influence of the allocatable quantity on the weight.

[0042] Step 205: Calculate the initial allocation amount for each resource based on the total adjustment demand and the dynamic allocation weight of each resource; As an optional implementation method, the formula for calculating the initial allocation is: ; In the formula, This represents the initial allocation amount of resource r. Indicates aggregate adjustment demand. This represents the dynamic allocation weight of resource r.

[0043] Specifically, for peak shaving response, a positive value indicates a requirement for increased resource output; for valley filling response, a negative value indicates a requirement for reduced resource load.

[0044] Step 206: Perform constraint verification on the adjustment capacity boundary for the initial allocation of each resource, accumulate the portion exceeding the adjustment capacity range as unallocated residual, and then allocate the unallocated residual proportionally to resources with remaining adjustment margin to obtain the final allocation of each resource.

[0045] As an optional implementation, unallocated residuals are allocated proportionally to resources with remaining adjustment margins, specifically including: Select resources from the list of resources to be allocated that have been allocated less than the capacity to be increased and whose equipment is operating normally, and use them as the set of remaining resources. Calculate the remaining allocable capacity of each resource in the remaining resource set. The remaining allocable capacity is the resource's upscaling capacity minus the resource's already allocated amount. The unallocated residuals are allocated to the corresponding resources based on the proportion of each resource's remaining allocable capacity to the total remaining allocable capacity of the remaining resource set.

[0046] Specifically, the constraint verification process includes: Initialize residual For each resource: Upper limit check: If ,but: ; ; Lower limit check: If ,but: ; ; Normal situation: .

[0047] Among them, the known quantities include , , The unknown quantity is and (Unallocated residuals).

[0048] After the constraint verification is completed, if Then, residual redistribution is performed: Calculate the set of resources for acceptable residual allocation: ; Calculate the remaining allocable capacity: For , ; Calculate the residual redistribution weights: ; Calculate the residual allocation: ; Update final allocation: ; Update residuals: ; like If it is still greater than 0, it is marked as "partially unallocated".

[0049] Implementing steps 201 to 206 addresses the technical problems of static allocation weights and failure to incorporate historical resource response performance into allocation in existing technologies. It enables quantitative evaluation of resource response quality, allowing resources with excellent historical response performance to receive higher allocation weights, thereby incentivizing resources to continuously improve response quality and enhance overall response accuracy. It also solves the technical problems of fixed allocation weights and inability to account for differences in real-time resource adjustment capabilities in existing technologies. This allows for dynamic adjustment of allocation weights, ensuring that the generated initial allocation scheme both incentivizes high-quality resources and matches the actual adjustability of each resource. This avoids assigning adjustment tasks to resources without adjustment capabilities, guaranteeing the executability of the allocation scheme. Furthermore, it achieves... The parameterized configuration of contribution sensitivity coefficient and allocable quantity sensitivity coefficient can flexibly adapt to the differentiated needs of different business scenarios such as peak shaving, valley filling, frequency regulation, and peak adjustment. It solves the technical problems in existing technologies, such as the allocation scheme not fully considering the real-time output upper and lower limits of resources, which leads to command execution failure, and the residuals generated after constraint verification, which lead to the incomplete decomposition of total regulation demand. It achieves a dual technical effect: on the one hand, constraint verification ensures that the final allocation of each resource does not exceed its actual regulation capacity boundary, improving the command execution success rate; on the other hand, the residual redistribution mechanism allocates the unallocated residuals proportionally to resources with regulation margins, so that the total regulation demand can be completely decomposed, while improving the average load rate of resources and significantly improving the utilization efficiency of the entire network regulation resources.

[0050] As an optional implementation, after obtaining the final allocation of each resource, the process also includes the steps of instruction generation and issuance. The instruction management server generates standardized scheduling instructions from the final allocation results and issues them: (1) Instruction generation: Instruction(r)={instruction_id,resource_id:r,P_target:P_final(r), response_type:ResponseType,start_time:CurrentTime,end_time:CurrentTime+T_allowable,priority:priority calculated based on C_total(r)}; (2) Instruction issuance: Send Instruction(r) to the local control system of the corresponding resource through the instruction issuance interface; (3) Instruction status tracking: Set the instruction status to "issued" and wait for the execution result to be returned; (4) Record log: Write the command issuance log, which includes information such as issuance time, resources, and allocation amount.

[0051] As an optional implementation, after the instruction is issued and executed, a contribution feedback loop step is also included. After the resource completes the scheduling instruction, the actual response power of the resource is obtained, the historical response performance data of the resource is updated according to the actual response power, and the overall contribution score of the resource is updated.

[0052] Specifically, after each response event, the scheduling decision server records the actual performance data of the resource (actual power, response time, participation status, etc.) and updates the contribution score, forming a closed-loop continuous optimization mechanism of "evaluation-allocation-response-reevaluation". This mechanism enables resources that consistently maintain high-quality responses to obtain more task opportunities, effectively incentivizing resources to proactively improve response quality.

[0053] To more clearly illustrate the technical solution of this application, the scheduling instruction allocation method provided in the embodiments of this application will be described below with reference to a specific application example.

[0054] In this application example, assume the total regulation demand P_target = 1000kW issued by the dispatching agency is for peak shaving response. The list of resources to be allocated contains three resources: ResourceList = {Resource A, Resource B, Resource C}.

[0055] The scheduling decision server acquires historical response performance data and real-time status information for each resource. The overall contribution scores for each resource are calculated as follows: , , ; The allocatable adjustment amounts for each resource are as follows: , , ; Pick , Calculate the dynamic allocation weights of each resource: Resource A: ; Resource B: ; Resource C: ; The normalized dynamic allocation weights for each resource are as follows: , , ; The initial allocation of each resource is as follows: , , .

[0056] Constraint verification: Resource A's upscaling capacity is 100kW, and the initial allocation of 320kW exceeds the upper limit. Therefore... residual .

[0057] Resource B's capacity can be increased by 300kW, but the initial allocation of 350kW exceeds the limit. Therefore... residual .

[0058] Resource C's capacity can be increased by 150kW, but the initial allocation of 330kW exceeds the upper limit. residual .

[0059] Since the initial allocation of all resources exceeds their respective upsizing capabilities, in the residual reallocation step, If the value is empty, the 450kW residual cannot be redistributed and is marked as "partially unallocated," and the dispatching agency is notified.

[0060] It should be noted that the above examples are simplified illustrations provided to facilitate understanding of the technical solutions of this application. In practical applications, the number of resources to be allocated is usually greater, and the differences in the allocatable adjustment amounts of each resource are also more diverse. The residual redistribution mechanism can effectively allocate the residuals after constraint verification to resources that still have adjustment margins, thereby achieving a complete decomposition of the total adjustment requirements.

[0061] This application also provides an application scenario in which the above-described dispatch instruction allocation method is applied. Specifically, the dispatch instruction allocation method provided in this embodiment can be applied to power system dispatch and demand response business scenarios. After a dispatch demand is issued by the dispatching agency, it enters the dispatch instruction processing link. Through data acquisition and processing, contribution evaluation, dynamic weight calculation, constraint verification, and residual reallocation, the final allocation amount for each resource is obtained, and then it enters the downstream instruction generation and execution link. The dispatch instruction allocation method provided in this embodiment belongs to the core decision-making link in the dispatch instruction processing link. Specifically, in the dispatch instruction processing process, dispatch instructions can be allocated based on machine decision-making. That is, the dispatch decision server automatically obtains the list of resources to be allocated and the total adjustment demand. For each resource, it obtains historical response performance data and real-time status information, calculates the comprehensive contribution score, allocable adjustment amount, dynamic allocation weight, and initial allocation amount sequentially, and finally generates the final allocation amount for each resource through constraint verification and residual reallocation. The entire allocation process is automatically completed by computer equipment without human intervention, ensuring the timeliness and consistency of dispatch instruction allocation.

[0062] In a typical application scenario, after the power grid dispatching agency issues a peak-shaving or demand response request, the method of this application is deployed in the dispatch management platform of a virtual power plant or aggregator. Upon receiving the overall dispatch request, the platform automatically retrieves the list of currently available resources from the resource registration database and, in conjunction with the historical response database and real-time monitoring system, executes a contribution assessment and dynamic allocation process. The generated final allocation amounts for each resource are converted into standardized dispatch instructions by the instruction management server and issued to the local control systems of each resource for execution. After a resource completes its response, the actual response power is automatically transmitted back and the historical response database is updated, forming a closed-loop continuous optimization mechanism of "assessment-allocation-response-reassessment," providing a more accurate data foundation for the allocation of subsequent dispatch instructions.

[0063] Based on the same inventive concept, this application also provides a scheduling instruction allocation device for implementing the scheduling instruction allocation method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more scheduling instruction allocation device embodiments provided below can be found in the limitations of the scheduling instruction allocation method described above, and will not be repeated here.

[0064] In one exemplary embodiment, such as Figure 3 As shown, a scheduling instruction allocation device is provided, comprising: The data acquisition module is used to acquire the list of resources to be allocated and the total adjustment requirements; and for each resource in the list of resources to be allocated, it acquires the historical response performance data and real-time status information of that resource. The historical response performance data includes response accuracy, response timeliness, response stability and historical participation rate. The contribution calculation module is used to calculate the response accuracy score, response timeliness score, response stability score, and historical participation rate score of the resource based on historical response performance data. It also performs a weighted sum of the response accuracy score, response timeliness score, response stability score, and historical participation rate score to obtain the comprehensive contribution score of the resource. The allocatable quantity calculation module is used to calculate the allocatable adjustment quantity of each resource based on the response direction of the total adjustment demand and the real-time status information of each resource. The dynamic weight calculation module is used to calculate the dynamic allocation weight of each resource based on the comprehensive contribution score and allocable adjustment amount of all resources in the resource list to be allocated. The initial allocation module is used to calculate the initial allocation amount for each resource based on the total adjustment demand and the dynamic allocation weight of each resource. The constraint verification and residual redistribution module is used to perform constraint verification on the adjustment capability boundary of the initial allocation of each resource, accumulate the part exceeding the adjustment capability range as unallocated residual, and then allocate the unallocated residual proportionally to the resources that still have adjustment margin to obtain the final allocation of each resource.

[0065] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores resource registration databases, historical response databases, and real-time monitoring data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a scheduling instruction allocation method.

[0066] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0067] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0068] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0069] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0070] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0071] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0072] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain. The processors involved in the embodiments provided in this application may be, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc.

[0073] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0074] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for allocating scheduling instructions, characterized in that, The scheduling instruction allocation method includes: Obtain the list of resources to be allocated and the total adjustment requirements; and for each resource in the list of resources to be allocated, obtain the historical response performance data and real-time status information of that resource, wherein the historical response performance data includes response accuracy, response timeliness, response stability and historical participation rate; Based on the historical response performance data, the response accuracy score, response timeliness score, response stability score, and historical participation rate score of the resource are calculated. The response accuracy score, response timeliness score, response stability score, and historical participation rate score are then weighted and summed to obtain the comprehensive contribution score of the resource. Based on the response direction of the total adjustment demand and the real-time status information of each resource, calculate the allocatable adjustment amount for each resource; Based on the comprehensive contribution score of all resources in the list of resources to be allocated and the allocable adjustment amount, calculate the dynamic allocation weight of each resource; Calculate the initial allocation amount for each resource based on the total adjustment demand and the dynamic allocation weight of each resource; The initial allocation amount of each resource is constrained and verified against the adjustment capacity boundary. The portion exceeding the adjustment capacity range is accumulated as an unallocated residual. The unallocated residual is then allocated proportionally to resources with remaining adjustment margins to obtain the final allocation amount for each resource.

2. The scheduling instruction allocation method according to claim 1, characterized in that, The formula for calculating the overall contribution score is as follows: ； In the formula, This indicates the overall contribution score. This indicates the accuracy score of the response. The score indicates the timeliness of the response. This indicates the response stability score. Indicates the historical participation rate score. Indicates the weighting coefficient; Among them, the response accuracy score The calculation formula is: ； In the formula, This represents the single-response accuracy of resource r in the i-th response. Indicates the number of historical responses; The response timeliness score The calculation formula is: ； In the formula, This indicates the timeliness of the i-th response of resource r. The response stability score The calculation formula is: ； In the formula, The standard deviation of the historical bias of resource r is represented by This represents the mean of the historical deviations of resource r; Historical participation rate score The calculation formula is: ； In the formula, This indicates the number of times resource r actually participated in the response. This represents the total number of times resource r has been notified to participate in scheduling.

3. The scheduling instruction allocation method according to claim 1, characterized in that, The step of calculating the allocatable adjustment amount for each resource based on the response direction of the total adjustment demand and the real-time status information of each resource specifically includes: When the total adjustment demand is positive, the allocatable adjustment amount is the resource's upward adjustment capacity, which is the difference between the maximum adjustable output of the resource and the current output. When the total adjustment demand is negative, the allocatable adjustment amount is the resource's downward adjustment capability, which is the difference between the current output of the resource and the minimum adjustable output. If the equipment operating status of the resource is abnormal, then the allocatable adjustment amount is zero.

4. The scheduling instruction allocation method according to claim 1, characterized in that, The formula for calculating the dynamically allocated weights is as follows: ； In the formula, This represents the dynamic allocation weight of resource r. This indicates the overall contribution score. This represents the allocatable adjustment amount of resource r. Indicates the sensitivity coefficient of contribution. Represents the sensitivity coefficient of allocatable quantity. This represents the list of resources to be allocated. This indicates the index for summation and traversal.

5. The scheduling instruction allocation method according to claim 1, characterized in that, The formula for calculating the initial allocation is: ； In the formula, This represents the initial allocation amount of resource r. Indicates aggregate adjustment demand. This represents the dynamic allocation weight of resource r.

6. The scheduling instruction allocation method according to claim 1, characterized in that, The provision of allocating unallocated residuals proportionally to resources with remaining adjustment margins specifically includes: From the list of resources to be allocated, select resources whose allocated amount is less than the upward adjustment capacity and whose equipment is operating normally, and use them as the set of remaining resources. Calculate the remaining allocable capacity of each resource in the remaining resource set, where the remaining allocable capacity is the resource's upscaling capacity minus the resource's already allocated amount; The unallocated residual is allocated to the corresponding resource based on the proportion of the remaining allocable capacity of each resource to the total remaining allocable capacity of the remaining resource set.

7. A scheduling instruction allocation device, characterized in that, The scheduling instruction allocation device includes: The data acquisition module is used to acquire the list of resources to be allocated and the total adjustment requirements; and for each resource in the list of resources to be allocated, to acquire the historical response performance data and real-time status information of that resource, wherein the historical response performance data includes response accuracy, response timeliness, response stability and historical participation rate; The contribution calculation module is used to calculate the response accuracy score, response timeliness score, response stability score, and historical participation rate score of the resource based on the historical response performance data, and to perform a weighted summation of the response accuracy score, response timeliness score, response stability score, and historical participation rate score to obtain the comprehensive contribution score of the resource. The allocatable quantity calculation module is used to calculate the allocatable adjustment quantity of each resource based on the response direction of the total adjustment demand and the real-time status information of each resource. The dynamic weight calculation module is used to calculate the dynamic allocation weight of each resource based on the comprehensive contribution score of all resources in the resource list to be allocated and the allocable adjustment amount. The initial allocation module is used to calculate the initial allocation amount of each resource based on the total adjustment demand and the dynamic allocation weight of each resource. The constraint verification and residual redistribution module is used to perform constraint verification on the adjustment capability boundary of the initial allocation amount of each resource, accumulate the part exceeding the adjustment capability range as unallocated residual, and then allocate the unallocated residual proportionally to the resources that still have adjustment margin to obtain the final allocation amount of each resource.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the scheduling instruction allocation method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the scheduling instruction allocation method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the scheduling instruction allocation method according to any one of claims 1-6.

Images