Cross-regional virtual power plant power mutual backup and resource autonomous negotiation scheduling platform

Abstract

The invention discloses a cross-regional virtual power plant power mutual backup and resource autonomous negotiation scheduling platform, and relates to the technical field of resource scheduling, and the platform comprises a resource pool building module which is used for building a cross-regional virtual power plant resource pool; the dynamic prediction module is used for obtaining virtual power plant operation state parameters and cross-regional power demand prediction parameters; the scheduling strategy construction module is used for constructing a virtual power plant power scheduling strategy; and the scheduling control module is used for performing power resource scheduling control. The technical problems of non-uniform resource allocation and low scheduling efficiency in cross-regional power scheduling are solved, and the technical effects of improving the supply and demand matching precision through cross-regional resource aggregation and dynamic prediction, and improving the utilization rate of power resources and the scheduling flexibility are achieved.

Description

Technical Field

[0001] This application relates to the field of resource scheduling technology, specifically to a cross-regional virtual power plant power redundancy and resource autonomous negotiation scheduling platform. Background Technology

[0002] As the global energy structure accelerates its transformation towards low-carbon and intelligent directions, the widespread penetration of distributed energy, energy storage systems, and controllable loads has driven the rapid development of virtual power plant (VPS) technology. As a crucial platform for aggregating distributed energy resources for grid dispatch, the demand for cross-regional collaborative operation of VPS is increasingly prominent. However, traditional power dispatching systems often focus on single-region or centralized power management. When faced with complex scenarios such as the dispersed distribution of VPS resources across regions, heterogeneous operating characteristics, and dynamic fluctuations in power demand, they suffer from bottlenecks such as low resource integration efficiency, lagging power supply and demand matching between regions, and insufficient coordination in dispatching decisions. In existing technologies, VPS resource pools are mostly limited to local aggregation, lacking a unified cross-regional modeling and tagging management mechanism, making it difficult for resource dispatching to transcend geographical boundaries. Simultaneously, dispatching strategies relying on static prediction models are ill-suited to the real-time changing characteristics of multi-regional power data streams, easily leading to delays in power backup response or imbalances in resource allocation. Summary of the Invention

[0003] This application solves the technical problems of uneven resource allocation and low dispatch efficiency in cross-regional power dispatch by providing a cross-regional virtual power plant power mutual backup and resource autonomous negotiation dispatch platform. It achieves the technical effect of improving the accuracy of supply and demand matching through cross-regional resource aggregation and dynamic prediction, thereby improving the utilization rate of power resources and the flexibility of dispatch.

[0004] This application provides a cross-regional virtual power plant power redundancy and autonomous resource negotiation and dispatch platform. The platform includes: a resource pool establishment module, used to aggregate and label virtual power plant resources from multiple regions to establish a cross-regional virtual power plant resource pool; a dynamic prediction module, used to monitor multiple power change data streams from the multiple regions in real time, and map the multiple power change data streams to the cross-regional virtual power plant resource pool for dynamic prediction, obtaining virtual power plant operating status parameters and cross-regional power demand prediction parameters; a dispatch strategy construction module, used to construct a virtual power plant power dispatch strategy, which includes an autonomous negotiation mechanism, power dispatch rules, and a power redundancy mechanism; and a dispatch control module, used to perform dispatch analysis on the virtual power plant operating status parameters and cross-regional power demand prediction parameters based on the virtual power plant power dispatch strategy, determine target power dispatch strategy parameters, and perform power resource dispatch control through the target power dispatch strategy parameters.

[0005] This application proposes a cross-regional virtual power plant (VDP) power redundancy and autonomous resource negotiation dispatch platform. This platform aggregates and labels virtual power plant resources from multiple regions to establish a cross-regional VDP resource pool. It monitors multiple power change data streams from these regions in real time and maps these streams to the cross-regional VDP resource pool for dynamic prediction, obtaining VDP operating status parameters and cross-regional power demand prediction parameters. A VDP power dispatch strategy is constructed, including an autonomous negotiation mechanism, power dispatch rules, and a power redundancy mechanism. Based on this strategy, the platform analyzes the VDP operating status parameters and cross-regional power demand prediction parameters to determine target power dispatch strategy parameters, and then controls power resource dispatch based on these parameters. This solution addresses the technical problems of uneven resource allocation and low dispatch efficiency in cross-regional power dispatch, achieving improved supply-demand matching accuracy, increased power resource utilization, and improved dispatch flexibility through cross-regional resource aggregation and dynamic prediction. Attached Figure Description

[0006] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the platform according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0007] Figure 1 This is a schematic diagram of the cross-regional virtual power plant power redundancy and resource autonomous negotiation and dispatch platform provided in the embodiments of this application.

[0008] Figure 2 This is a schematic diagram illustrating the execution process of the resource pool establishment module in the cross-regional virtual power plant power backup and resource autonomous negotiation scheduling platform provided in this application embodiment.

[0009] Figure labeling: Resource pool creation module 11, dynamic prediction module 12, scheduling strategy construction module 13, scheduling control module 14. Detailed Implementation

[0010] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0013] This application provides a cross-regional virtual power plant power redundancy and resource autonomous negotiation and dispatch platform, such as... Figure 1 As shown, the platform includes:

[0014] Resource pool creation module 11 is used to aggregate and label virtual power plant resources from multiple regions to create a cross-regional virtual power plant resource pool.

[0015] In one embodiment, in the resource pool establishment module 11, based on the power system's dispatching requirements and the power characteristic information of each region, the structure, type, and characteristics of power resources in different regions are analyzed to determine the construction goals of the power resource pool. Then, according to the construction goals, the virtual power plant resources of each region are logically aggregated, and the aggregation results are tagged according to the power resource tag library to establish a cross-regional virtual power plant resource pool. This cross-regional virtual power plant resource pool covers different power resources from multiple regions and has the ability to dynamically adjust and optimize resource allocation, which can make cross-regional power dispatching more flexible and efficient, and provides a solid foundation for subsequent power resource optimization dispatching and autonomous negotiation.

[0016] Furthermore, such as Figure 2 As shown, the resource pool creation module 11 includes:

[0017] Based on the power system dispatch requirements and the power characteristic information of the multiple regions, the construction goals of the power resource pool are determined; the virtual power plant resources of the multiple regions are logically aggregated according to the construction goals of the power resource pool to obtain multi-regional virtual power plant resources; a power resource tag library is constructed, and the multi-regional virtual power plant resources are tagged based on the power resource tag library to establish the cross-regional virtual power plant resource pool.

[0018] Preferably, by collecting and analyzing information such as power demand, power supply capacity, load variation patterns, and grid operation constraints in various regions, the power dispatch needs between regions are clarified, such as dispatch flexibility, load balancing capacity, and emergency reserve capacity. Then, power characteristic information for each region is collected, including energy production methods (e.g., thermal power, wind power, solar power, nuclear power), power load fluctuation characteristics, types and capabilities of dispatchable resources (e.g., wind power, photovoltaic power generation, energy storage batteries, flexible loads), and the spatiotemporal distribution of power resources in each region. These characteristics help to rationally plan the construction of the power resource pool, ensuring its dispatch flexibility and reliability. After obtaining the power system dispatch needs and power characteristic information from multiple regions, construction goals for the power resource pool are set based on this information. These goals may include improving cross-regional power dispatch efficiency, optimizing the absorption capacity of renewable energy, increasing resource redundancy to cope with emergency needs, and reducing the overall system operating costs. Subsequently, based on the characteristics of power resources in each region, relevant virtual power plant resources are connected through standardized access interfaces or protocols according to the construction goals of the power resource pool. These virtual power plant resources can be different types of power production, storage, or consumption equipment, such as wind turbines, photovoltaic cells, energy storage devices, and demand response loads. Then, based on the characteristics, dispatchability, and operating rules of the power resources, the resources in each region are categorized and aggregated. Aggregation can be based on resource type (such as renewable energy resources, energy storage resources, etc.) or on resource dispatch priority, geographical location, etc., thus forming multi-regional virtual power plant resources. Afterwards, based on the types, functions, and dispatchability of the virtual power plant resources, a power resource tag library is constructed. This power resource tag library includes classification information for different power resources, such as resource type tags (such as photovoltaic, wind power, energy storage, electric vehicle charging stations, etc.), dispatchability tags (such as dispatchable, non-dispatchable, partially dispatchable, etc.), capacity tags (such as the capacity and power output range of each resource), and efficiency tags (such as high efficiency, low efficiency, etc.). Based on this power resource tag library, virtual power plant resources in multiple regions are managed using tags. This involves assigning multiple tags to each resource to ensure that the characteristics of each resource are clearly defined, supporting subsequent scheduling strategies. After tagging is completed, a cross-regional virtual power plant resource pool is formed. This pool not only contains virtual power plant resources from multiple regions but also, through tagging and logical aggregation, enables more efficient resource management and scheduling, improving the stability and responsiveness of the power system.

[0019] The dynamic prediction module 12 is used to monitor multiple power change data streams in the multiple regions in real time, and map the multiple power change data streams to the cross-regional virtual power plant resource pool for dynamic prediction, so as to obtain the virtual power plant operation status parameters and cross-regional power demand prediction parameters.

[0020] In one embodiment, the dynamic prediction module 12 monitors power change data in multiple regions in real time using sensors and data acquisition devices installed on power equipment, obtaining multiple power change data streams for these regions. These power change data streams include power load data (real-time power load changes in each region), power generation data (including output power changes of various power sources), power storage status (battery charging and discharging status, storage capacity, and discharge time), power transmission data (load status of cross-regional power transmission lines), and environmental data (wind speed, temperature, solar radiation intensity, etc.). Subsequently, the collected multiple power change data streams are standardized to ensure data accuracy and consistency. The reprocessed power change data streams are then mapped to cross-regional virtual power plant resource pools. For example, data related to wind power generation is mapped to a wind power resource pool, and data related to photovoltaic power generation is mapped to a photovoltaic resource pool. Subsequently, a predictive model is used to perform predictive analysis on the cross-regional virtual power plant resource pool, generating virtual power plant operating status parameters and cross-regional power demand prediction parameters. The virtual power plant operating status parameters include the virtual power plant's generation capacity, energy storage status, and power load, reflecting the current operating status of the virtual power plant. The cross-regional power demand prediction parameters include load demand, peak-valley differences, and power supply gaps, providing predictive support for cross-regional power dispatch. Through this dynamic prediction mechanism, changes in power demand can be responded to in real time and accurately, ensuring the stable and efficient operation of the power system.

[0021] Furthermore, the dynamic prediction module 12 includes:

[0022] Multiple power change data streams are standardized according to data application standards to obtain multiple standard power change data streams; these multiple standard power change data streams are mapped and matched to the cross-regional virtual power plant resource pool to obtain a virtual power plant update resource pool; the virtual power plant update resource pool is dynamically predicted to obtain virtual power plant operating status parameters and cross-regional power demand prediction parameters.

[0023] Preferably, after obtaining multiple power change data streams, these data streams are processed according to data application standards. During this process, all input data streams are standardized to the same data format. For example, all power data is uniformly converted to kilowatt-hours (kWh) and timestamps are standardized to UTC standard time for unified management across regions and time zones. Standard deviation and mean are used to clean the power change data streams, removing outliers and noise to ensure the accuracy of the processing results. Maximum-minimum normalization is used to process the power change data streams, mapping data of different magnitudes to a unified scale for effective comparison and analysis. After standardization, multiple standard power change data streams are obtained. Subsequently, according to the tags in the cross-regional virtual power plant resource pool, these standard power change data streams are mapped to the resources of the corresponding regions, forming a virtual power plant update resource pool. This allows the power data of each region or resource to be effectively associated with the resource status of the virtual power plant. Subsequently, the data from the updated resource pool of the virtual power plant is input into the power plant operation status assessment model and the power demand forecasting model. The power plant operation status assessment model predicts the power generation capacity, energy storage status, and other operating parameters of each virtual power plant resource in future periods, generating virtual power plant operation status parameters. The power demand forecasting model predicts future power demand, generating cross-regional power demand forecasting parameters. This provides accurate support for the intelligent scheduling and resource optimization of the power system, and helps to improve the stability, flexibility, and cost-effectiveness of power supply.

[0024] Furthermore, the dynamic prediction module 12 includes:

[0025] Historical virtual power plant operation datasets are collected. Based on these datasets, a power plant operation status assessment model and a power demand forecasting model are trained and generated. The power plant operation status assessment model is used to predict the status of the virtual power plant's updated resource pool to obtain virtual power plant operation status parameters. Based on the power demand forecasting model, the power demand forecasting model is used to predict the demand of the virtual power plant's updated resource pool to obtain cross-regional power demand forecasting parameters.

[0026] Optionally, historical operational data of the virtual power plant is first collected from multiple sources. This data includes the operational status of each power generation unit (such as wind power, photovoltaic, and energy storage equipment) within the virtual power plant, real-time power generation, the charging and discharging status of energy storage batteries, external power load, meteorological information, and electricity market data. By collecting this data, the platform can comprehensively understand the operation of the virtual power plant and fluctuations in power demand, while ensuring accurate predictions using multiple factors during subsequent model training. During data collection, sensor data is cleaned, handling missing and outlier values ​​to guarantee data quality. Subsequently, the collected historical virtual power plant operational dataset is used to train a pre-set time series analysis network, generating a power plant operational status assessment model and a power demand prediction model. Then, using the power plant operational status assessment model, based on the power generation data, energy storage status, and external environmental factors (such as meteorological data) in the virtual power plant's updated resource pool, the operational status of the virtual power plant is predicted, determining the virtual power plant's operational status parameters. These parameters represent the current operational status of the virtual power plant's resource pool, providing crucial reference for subsequent power dispatching. At the same time, the power demand forecasting model will be used to analyze the power load data, meteorological information and time series data in the virtual power plant update resource pool to predict the power demand in the future period, obtain cross-regional power demand forecasting parameters, and ensure that the virtual power plant can meet the power demand, so as to achieve power supply and demand balance and improve the efficiency of power resource utilization.

[0027] Furthermore, the dynamic prediction module 12 includes:

[0028] Based on the predicted demand from the virtual power plant, a time series analysis network structure is selected; the historical virtual power plant operation dataset is proportionally divided and labeled to obtain a virtual power plant operation sample set; the time series analysis network structure is used to perform prediction training and optimization on the virtual power plant operation sample set to generate a power plant operation status assessment model and a power demand prediction model.

[0029] Optionally, in the electricity demand forecasting of virtual power plants, due to the obvious time dependence and periodicity of electricity data, a time series analysis network structure is first constructed using a Long Short-Term Memory (LSTM) network to capture the regularity and trend of electricity load changes over time. Subsequently, the collected historical virtual power plant operation dataset is divided into training, validation, and test sets according to a preset ratio (usually 6:2:2) to ensure the scientific nature and generalization ability of the model training. The training set is used for model parameter learning, the validation set for model tuning, and the test set for evaluating model performance. During the partitioning process, each data point generates continuous time segment samples in chronological order, forming a virtual power plant operation sample set that can be used for network training, enabling the model to capture the regularity of electricity load changes over time. Then, the training set of equipment operating status from the virtual power plant operation sample set is input into the time series analysis network structure, and iterative training is performed through steps such as forward propagation, loss calculation, backpropagation, and parameter optimization. During training, a validation set of data related to equipment operating status from the simulated power plant operation sample set is used periodically for validation. This evaluates the prediction accuracy on unseen data, and network parameters and hyperparameters, such as the number of network layers, nodes, and learning rate, are adjusted based on the loss and metrics of the validation set to optimize model performance. After training, a test set is used for final performance validation to ensure the model has good generalization ability and prediction accuracy. Once the test is passed, the current time series analysis network structure is used as the power plant operation status assessment model. Furthermore, using the same approach, another time series analysis network structure is trained using the training, validation, and test sets of data related to electricity load from the virtual power plant operation sample set to construct an electricity demand forecasting model. These two models can accurately predict the future operating status of the virtual power plant and cross-regional electricity demand with real-time data input, providing reliable data support for scheduling and resource management.

[0030] The scheduling strategy construction module 13 is used to construct a virtual power plant power scheduling strategy, which includes an autonomous negotiation mechanism, power scheduling rules, and a power backup mechanism.

[0031] In one embodiment, within the dispatch strategy construction module 13, to achieve efficient and intelligent power management, the platform constructs and stores virtual power plant dispatch strategies based on actual business needs. These strategies include three mechanisms: an autonomous negotiation mechanism, power dispatch rules, and a power backup mechanism. The autonomous negotiation mechanism establishes a communication and decision-making negotiation framework among multiple virtual power plants, enabling resources in each region to participate autonomously in dispatch decisions. The power dispatch rules clarify the priority ordering, safety constraints, and economic dispatch principles during the dispatch process, including equipment start-up and shutdown sequences, load response requirements, minimization of generation costs, and power supply stability guarantees. The power backup mechanism allows virtual power plants in different regions to quickly assist each other in the event of power shortages or equipment failures, enabling the dispatch and regulation of backup power. The combination of these three mechanisms provides a complete operational framework and decision-making basis for cross-regional resource optimization, autonomous negotiation dispatch, and power backup.

[0032] Furthermore, this application provides that the autonomous negotiation mechanism specifically includes negotiation rules and negotiation algorithms, the power dispatch rules specifically include dispatch priority rules, security constraint rules and economic dispatch rules, and the power mutual backup mechanism specifically includes mutual backup protocols, mutual backup communication and coordination algorithms.

[0033] Preferably, the autonomous negotiation mechanism, by defining negotiation rules and algorithms, enables multiple virtual power plants to share resources and allocate loads without relying on central control. The negotiation rules include the rights and obligations of each virtual power plant participating in dispatch, resource availability declarations, and decision priority settings. The negotiation algorithm, based on these rules, performs iterative calculations and information exchange to achieve conflict detection, scheme selection, and dispatch optimization, ensuring that each region achieves the optimal dispatch scheme under the premise of autonomy. The power dispatch rules clarify the operational principles of power resource dispatch, including dispatch priority rules, safety constraint rules, and economic dispatch rules. Dispatch priority rules determine the priority order of various resources; safety constraint rules ensure equipment operates within allowable load and temperature ranges to prevent overload or failure; and economic dispatch rules minimize generation costs and maximize energy efficiency while ensuring safety. The power backup mechanism, through the establishment of backup protocols, backup communication channels, and coordination algorithms, enables cross-regional backup power dispatch. When a region experiences power shortages or sudden power outages, the mutual backup protocol specifies the conditions and allocation methods for dispatching backup power. Mutual backup communication ensures rapid and accurate information transmission, while the coordination algorithm calculates the available power capacity and priority of each virtual power plant in real time, ensuring that backup power meets demand quickly, safely, and efficiently. Through the synergistic effect of these three mechanisms, the platform enables autonomous, reliable, and economical cross-regional power dispatch, providing a complete execution plan for the efficient operation of virtual power plants.

[0034] The scheduling control module 14 is used to perform scheduling analysis on the virtual power plant's operating status parameters and cross-regional power demand forecast parameters based on the virtual power plant's power scheduling strategy, determine the target power scheduling strategy parameters, and perform power resource scheduling control through the target power scheduling strategy parameters.

[0035] In one embodiment, within the dispatch control module 14, a comprehensive analysis of the virtual power plant's operating status parameters and cross-regional power demand forecast parameters is first performed using a virtual power plant power dispatch strategy to form the current power dispatch strategy space. Within this power dispatch strategy space, a global optimization is performed using a power dispatch fitness function, and possible dispatch schemes are calculated and evaluated to determine the optimal target power dispatch strategy parameters. These target power dispatch strategy parameters include specific execution content such as the output allocation of each virtual power plant, energy storage charging and discharging plans, backup power call sequence, and cross-regional coordination schemes. After determining the target power dispatch strategy parameters, the platform distributes the strategy parameters to each virtual power plant resource through the dispatch control unit, realizing automated power resource dispatch control, including starting or stopping generator units, adjusting energy storage devices, calling backup power, and coordinating load response, thereby ensuring cross-regional power supply and demand balance, dispatch economy, and system operational safety.

[0036] Furthermore, the scheduling control module 14 includes:

[0037] Based on the virtual power plant power dispatch strategy, the operating status parameters of the virtual power plant and the cross-regional power demand forecast parameters are analyzed to obtain the power dispatch strategy space; according to the power dispatch objective of the virtual power plant, a power dispatch fitness function is designed; based on the power dispatch fitness function, global optimization is performed in the power dispatch strategy space to determine the target power dispatch strategy parameters.

[0038] Preferably, based on the established virtual power plant power dispatch strategy, the operating status parameters of the virtual power plant are comprehensively analyzed with cross-regional power demand forecast parameters to form a power dispatch strategy space covering all feasible dispatch schemes. This strategy space includes various possible dispatch configurations such as different power generation unit output combinations, energy storage charging and discharging plans, mutual backup power dispatch schemes, and load regulation measures. After obtaining the dispatch strategy space, the platform designs a power dispatch fitness function based on the current virtual power plant's dispatch objectives (such as optimal economics, maximizing supply and demand balance, and satisfying security constraints). This function can quantify the merits of each dispatch scheme in achieving the objectives and can comprehensively consider multi-dimensional factors such as generation cost, energy efficiency, stability, and response speed, typically representing a normalized weighted sum of these factors. Subsequently, the platform uses the fitness function to perform global optimization in the policy space. Through iterative search, genetic algorithm, particle swarm optimization or other intelligent optimization methods, it evaluates and selects the scheme with the highest fitness, and finally determines the target power dispatch strategy parameters. These target power dispatch strategy parameters will serve as the specific basis for dispatch execution, guiding subsequent resource allocation and control operations, and ensuring that cross-regional virtual power plants maintain efficient, safe and economical operation under dynamic power demand and operating condition changes.

[0039] Furthermore, the scheduling control module 14 includes:

[0040] The power dispatch fitness function is used to evaluate the strategy parameters in the power dispatch strategy space to obtain a power dispatch fitness set; based on the power dispatch fitness set, an iterative search is performed in the power dispatch strategy space to determine the target power dispatch strategy parameters.

[0041] Optionally, during the scheduling optimization process, multiple strategy parameter combinations are first randomly selected from the power scheduling strategy space, each representing a scheduling scheme. Then, these strategy parameter combinations are simulated in a simulation environment to quantify their performance in terms of economy, security, stability, and supply-demand balance. The power scheduling fitness function is then used to comprehensively calculate these indicators, obtaining the fitness score for each strategy parameter combination, thus forming a power scheduling fitness set. Next, a genetic algorithm is used to perform global optimization in the scheduling strategy space. In the initial stage, a certain number of strategy parameter individuals are selected as the population, and these individuals are sorted and selected based on the scores of the fitness set. The algorithm generates new strategy combinations in the population through selection, crossover, and mutation operations, allowing excellent parameter characteristics to be inherited and recombined, while retaining a certain degree of randomness to explore uncovered strategy spaces. During the iteration process, the same fitness calculation is continuously performed on the newly generated strategy combinations, and the population is updated, gradually improving the overall quality of the scheduling scheme. When the number of iterations reaches a preset upper limit or the population fitness converges to a stable interval, the strategy parameter combination with the highest fitness is determined as the target power dispatch strategy parameter, and the target power dispatch strategy parameter is distributed to achieve optimal allocation and dynamic dispatch of cross-regional power resources. This process not only ensures the global optimality of the dispatch scheme, but also has strong robustness and can adapt to real-time changes in power demand and operating status.

[0042] The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform according to embodiments of the present invention solves the technical problems of uneven resource allocation and low dispatch efficiency in cross-regional power dispatch. It achieves the technical effect of improving supply and demand matching accuracy through cross-regional resource aggregation and dynamic forecasting, thereby increasing the utilization rate of power resources and dispatch flexibility. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform includes: a resource pool establishment module 11, a dynamic forecasting module 12, a dispatch strategy construction module 13, and a dispatch control module 14.

[0043] Although this application makes various references to certain modules in the platform according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0044] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform, characterized in that: The platform includes: The resource pool creation module is used to aggregate and tag virtual power plant resources from multiple regions to create a cross-regional virtual power plant resource pool. The dynamic prediction module is used to monitor multiple power change data streams in multiple regions in real time, and map the multiple power change data streams to the cross-regional virtual power plant resource pool for dynamic prediction, so as to obtain virtual power plant operation status parameters and cross-regional power demand prediction parameters. The scheduling strategy construction module is used to construct the virtual power plant power scheduling strategy, which includes an autonomous negotiation mechanism, power scheduling rules, and power backup mechanism. The scheduling and control module is used to perform scheduling analysis on the virtual power plant's operating status parameters and cross-regional power demand forecast parameters based on the virtual power plant's power scheduling strategy, determine the target power scheduling strategy parameters, and perform power resource scheduling control through the target power scheduling strategy parameters.

2. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform as described in claim 1, characterized in that, The resource pool creation module includes: Based on the power system dispatch requirements and the power characteristic information of the multiple regions, the construction objectives of the power resource pool are determined; Logically aggregate virtual power plant resources from multiple regions according to the power resource pool construction goals to obtain virtual power plant resources from multiple regions. A power resource tag library is constructed, and the virtual power plant resources in the multi-regional area are tagged and identified based on the power resource tag library to establish the cross-regional virtual power plant resource pool.

3. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform as described in claim 1, characterized in that, The dynamic prediction module includes: Multiple power change data streams are standardized according to data application standards to obtain multiple standard power change data streams. The multiple standard power change data streams are mapped and matched to the cross-regional virtual power plant resource pool to obtain the virtual power plant update resource pool; The virtual power plant's resource pool is dynamically updated to obtain virtual power plant operating status parameters and cross-regional power demand forecast parameters.

4. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform as described in claim 3, characterized in that, The dynamic prediction module includes: Collect historical virtual power plant operation datasets, and train and generate power plant operation status assessment models and power demand prediction models based on the historical virtual power plant operation datasets; The virtual power plant operation status parameters are obtained by predicting the status of the updated resource pool of the virtual power plant through the power plant operation status assessment model. Based on the power demand forecasting model, the virtual power plant update resource pool is used to forecast demand and obtain cross-regional power demand forecasting parameters.

5. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform as described in claim 4, characterized in that, The dynamic prediction module includes: Based on the predicted demand from the virtual power plant, time series analysis was selected to analyze the network structure. The historical virtual power plant operation dataset is divided and labeled proportionally to obtain a virtual power plant operation sample set; The time series analysis network structure is used to predict, train, and optimize the virtual power plant operation sample set to generate a power plant operation status assessment model and a power demand prediction model.

6. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform as described in claim 1, characterized in that, The autonomous negotiation mechanism specifically includes negotiation rules and negotiation algorithms; the power dispatch rules specifically include dispatch priority rules, security constraint rules, and economic dispatch rules; and the power mutual backup mechanism specifically includes mutual backup protocols, mutual backup communication and coordination algorithms.

7. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform as described in claim 1, characterized in that, The scheduling and control module includes: Based on the virtual power plant power dispatch strategy, the operating status parameters of the virtual power plant and the cross-regional power demand forecast parameters are analyzed to obtain the power dispatch strategy space. Design a power dispatch fitness function based on the power dispatch objectives of the virtual power plant; Based on the power dispatch fitness function, global optimization is performed within the power dispatch strategy space to determine the target power dispatch strategy parameters.

8. The cross-regional virtual power plant power redundancy and resource autonomous negotiation dispatch platform as described in claim 7, characterized in that, The scheduling and control module includes: The power dispatch fitness function is used to evaluate the strategy parameters in the power dispatch strategy space to obtain a power dispatch fitness set. Based on the power dispatch fitness set, an iterative search is performed within the power dispatch strategy space to determine the target power dispatch strategy parameters.

Images