Energy scheduling method and device based on virtual power plant and electronic equipment

Abstract

The invention provides an energy scheduling method and device based on a virtual power plant and electronic equipment, and relates to the technical field of virtual power plant coordination control, and the method comprises the steps: generating a first scheduling plan based on target power data collected by a target virtual power plant and a business constraint condition analyzed from a target response contract, inputting the first scheduling plan into a parallel verification model to obtain a second scheduling plan; issuing the first scheduling plan to the target energy storage device, and receiving device response data fed back by the target energy storage device; and storing the equipment response data and the second scheduling plan in a block chain distributed account book in an associated manner so as to form a double-track certificate. The energy scheduling method and device based on the virtual power plant and the electronic equipment provided by the invention are used for solving the problems of lack of a trust mechanism and insufficient scheduling execution traceability when multiple interest subjects participate in energy aggregation transaction, and improving the credibility of market transaction.

Description

Technical Field

[0001] This application relates to the field of virtual power plant coordination and control technology, and in particular to an energy dispatching method, device and electronic equipment based on virtual power plants. Background Technology

[0002] Virtual power plants aggregate distributed energy resources, including photovoltaic power generation devices, wind turbine generators, battery energy storage units, and controllable load equipment, to form a unified and coordinated system. They utilize information and communication networks to transmit real-time data and combine optimization algorithms to regulate power output or demand response. Logically, when analyzing fluctuations in power supply and demand, they proactively adjust resource output plans or reduce peak loads to balance grid stability and improve power system dispatch efficiency, thereby achieving efficient utilization and economical operation of renewable energy.

[0003] In actual operation, centralized control systems in power plants cannot provide real-time, cross-verified dispatch execution records from multiple parties. The lack of a multi-party synchronous verification mechanism for key information such as control commands, execution feedback, and metering data under a centralized architecture results in a lack of cross-verifiable objective evidence when disputes arise among trading entities regarding dispatch actions. This directly undermines the credibility of market interactions and leads to a lack of trust mechanisms when multiple stakeholders participate in energy aggregation trading. Summary of the Invention

[0004] The purpose of this application is to provide an energy dispatching method, device, and electronic equipment based on a virtual power plant, which can solve the problems of lack of trust mechanism and insufficient traceability of dispatching execution when multiple stakeholders participate in energy aggregation transactions, thereby improving the credibility of market transactions.

[0005] This application provides an energy dispatching method based on a virtual power plant, including: Based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract, a first scheduling plan is generated. This first scheduling plan is then input into a parallel verification model to obtain a second scheduling plan. The target virtual power plant is obtained by aggregating distributed energy resources. The parallel verification model is used to simulate wind and solar power fluctuations or equipment failure scenarios to generate a backup scheduling plan for extreme scenarios. The first scheduling plan is sent to the target energy storage device, and the device response data fed back by the target energy storage device is received. The device response data is associated with the second scheduling plan and stored in a blockchain distributed ledger to form a dual-track notarization. The blockchain notarization data on the blockchain distributed ledger is used by both parties to the target response contract to audit the energy transaction.

[0006] Optionally, generating a first scheduling plan based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract includes: acquiring the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract of the power trading platform; the target power data includes at least the following: photovoltaic output curve, wind turbine status, energy storage load status, and user load metering value; inputting the target power data and the business constraints into the main scheduling model to generate the first scheduling plan.

[0007] Optionally, acquiring the target power data collected from the target virtual power plant includes: performing standardized timestamp processing on the power data collected from the target virtual power plant, unifying the second-level device data to millisecond-level precision, and converting the processed device data into binary format data; establishing an association between the binary format data and the target response contract based on the device identifier, and outputting the target power data.

[0008] Optionally, the business constraints parsed from the target response contract include: parsing the discharge threshold field and the compensation ratio field in the target response contract to obtain multiple discharge thresholds and multiple compensation allocation ratios; binding the multiple discharge thresholds and the multiple compensation allocation ratios to the corresponding energy storage devices to obtain the business constraints of the target response contract.

[0009] Optionally, the second scheduling plan includes: a backup scheduling plan for extreme scenarios, and a compensation allocation scheme when the extreme scenarios cause losses; the step of inputting the first scheduling plan into the parallel verification model to obtain the second scheduling plan includes: generating quantum annealing input parameters corresponding to the second scheduling plan based on the wind and solar fluctuation probability model, and encoding the quantum annealing input parameters into Hamiltonians to obtain the backup scheduling plan; and calculating the compensation allocation scheme of the backup scheduling plan using the Shapley value game model.

[0010] Optionally, the step of associating the device response data with the second scheduling plan and storing it in the blockchain distributed ledger includes: obtaining the device response data generated by the target energy storage device executing the first scheduling plan, encrypting the second scheduling plan using an encryption algorithm to generate a preliminary plan data digest; binding the device response data with the preliminary plan data digest to generate a data verification pair, and storing the data verification pair in the blockchain distributed ledger to complete dual-track notarization.

[0011] Optionally, after associating the device response data with the second scheduling plan and storing it in the blockchain distributed ledger, the method further includes: receiving a target verification instruction triggered by a target user and executing a verification strategy corresponding to the target verification instruction; wherein the target user includes any one of the following: a first user, a second user, and a third user; the target verification instruction includes any one of the following: a first verification instruction triggered by the first user, a second verification instruction triggered by the second user, and a third verification instruction triggered by the third user; the first verification instruction is used to retrieve the actual discharge sequence on the chain through an audit interface and perform a visual comparison with the contractually agreed value; the second verification instruction is used to retrieve the quantum annealing model input parameters and compensation allocation scheme for that period through an audit interface; the third verification instruction is used to: output the user marginal contribution calculation log in the Shapley value model through an audit interface.

[0012] Optionally, the execution of the verification strategy corresponding to the target verification instruction includes: when a data contradiction is detected, activating the arbitration contract deployed on the chain, calling the zero-knowledge proof protocol to verify the source of the contradictory data, and feeding back the output verification result to the target user.

[0013] This application also provides an energy dispatching device based on a virtual power plant, comprising: The plan generation module is used to generate a first scheduling plan based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract, and input the first scheduling plan into a parallel verification model to obtain a second scheduling plan; the target virtual power plant is obtained by aggregating distributed energy resources; the parallel verification model is used to simulate wind and solar fluctuations or equipment failure scenarios to generate a backup scheduling plan under extreme scenarios; the data acquisition module is used to send the first scheduling plan to the target energy storage device and receive the equipment response data fed back by the target energy storage device; the blockchain evidence storage module is used to associate the equipment response data with the second scheduling plan and store it in a blockchain distributed ledger to form a dual-track evidence storage; wherein, the blockchain evidence storage data on the blockchain distributed ledger is used by both parties to the target response contract to audit the energy transaction.

[0014] Optionally, the data acquisition module is further configured to acquire the target power data collected from the target virtual power plant, and the business constraints parsed from the target response contract of the power trading platform; the target power data includes at least the following: photovoltaic output curve, wind turbine status, energy storage load status, and user load metering value; the plan generation module is specifically configured to input the target power data and the business constraints into the main scheduling model to generate the first scheduling plan.

[0015] Optionally, the data acquisition module is further configured to perform standardized timestamp processing on the power data collected from the target virtual power plant, unify the second-level device data to the millisecond-level precision, and convert the processed device data into binary format data; the data acquisition module is further configured to establish the association between the binary format data and the target response contract based on the device identifier, and output the target power data.

[0016] Optionally, the data acquisition module is further configured to parse the discharge threshold field and compensation ratio field in the target response contract to obtain multiple discharge thresholds and multiple compensation allocation ratios; the data acquisition module is further configured to bind the multiple discharge thresholds and the multiple compensation allocation ratios with the corresponding energy storage devices to obtain the business constraints of the target response contract.

[0017] Optionally, the second scheduling plan includes: a backup scheduling plan for extreme scenarios, and a compensation allocation scheme when the extreme scenarios cause losses; the plan generation module is specifically used to generate quantum annealing input parameters corresponding to the second scheduling plan based on the wind and solar fluctuation probability model, and encode the quantum annealing input parameters into Hamiltonians to obtain the backup scheduling plan; the plan generation module is also specifically used to calculate the compensation allocation scheme of the backup scheduling plan using a Shapley value game model.

[0018] Optionally, the blockchain evidence storage module is specifically used to obtain the device response data generated by the target energy storage device executing the first scheduling plan, and to encrypt the second scheduling plan using an encryption algorithm to generate a preliminary plan data digest; the blockchain evidence storage module is also specifically used to bind the device response data with the preliminary plan data digest to generate a data verification pair, and to store the data verification pair in the blockchain distributed ledger to complete dual-track evidence storage.

[0019] Optionally, the device further includes: an audit module; the audit module is configured to receive a target verification instruction triggered by a target user and execute a verification strategy corresponding to the target verification instruction; wherein the target user includes any one of the following: a first user, a second user, and a third user; the target verification instruction includes any one of the following: a first verification instruction triggered by the first user, a second verification instruction triggered by the second user, and a third verification instruction triggered by the third user; the first verification instruction is configured to retrieve the actual discharge quantity sequence on the chain through the audit interface and perform a visual comparison with the contractually agreed value; the second verification instruction is configured to retrieve the quantum annealing model input parameters and compensation allocation scheme for that period through the audit interface; the third verification instruction is configured to: output the user marginal contribution calculation log in the Shapley value model through the audit interface.

[0020] Optionally, the audit module is specifically used to activate the on-chain arbitration contract when a data contradiction is detected, call the zero-knowledge proof protocol to verify the source of the contradictory data, and feed back the output verification result to the target user.

[0021] This application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the energy dispatching method based on a virtual power plant as described above.

[0022] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the above-described virtual power plant-based energy dispatching methods.

[0023] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the energy dispatching method based on a virtual power plant as described above.

[0024] The energy dispatching method, apparatus, and electronic equipment based on virtual power plants provided in this application firstly generate a first dispatching plan based on target power data collected from the target virtual power plant and business constraints parsed from the target response contract. This first dispatching plan is then input into a parallel verification model to obtain a second dispatching plan. The target virtual power plant is obtained by aggregating distributed energy resources. The parallel verification model is used to simulate wind and solar power fluctuations or equipment failure scenarios to generate a backup dispatching plan for extreme scenarios. Next, the first dispatching plan is distributed to the target energy storage device, and the device response data fed back by the target energy storage device is received. Finally, the device response data and the second dispatching plan are associated and stored in a blockchain distributed ledger to form dual-track notarization. The blockchain notarization data on the distributed ledger is used by both parties to the target response contract to audit the energy transaction. This approach solves the problems of insufficient trust mechanisms and traceability of dispatching execution when multiple stakeholders participate in energy aggregation transactions, thereby improving the credibility of market transactions. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are 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 flowchart illustrating the energy dispatching method based on a virtual power plant provided in this application; Figure 2 This is a schematic diagram of the structure of the energy dispatching device based on a virtual power plant provided in this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions 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, 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] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0029] In related technologies, if an industrial user signs an agreement with a virtual power plant operator requiring the cluster energy storage equipment to discharge 200kWh during peak electricity price periods, the collaborative control process relies on a single central platform to issue instructions and record equipment responses. When the user questions whether only 150kWh was actually discharged, the operator can only provide a one-sided discharge curve log from its own backend database. The industrial user refuses to settle the payment because it cannot independently verify the authenticity of the operation.

[0030] To address the aforementioned technical problems in related technologies, this application provides an energy dispatching method based on a virtual power plant. This method mainly includes the following steps: ① Collecting physical system layer data through an industrial Internet of Things (IIoT) network to obtain photovoltaic output curves, wind turbine status, energy storage charge status, and user load metering values; ② Extracting user demand response contracts from a power trading platform and parsing them to obtain power constraints and settlement rules; ③ Integrating the physical system layer data and the power constraints into a main dispatching model to generate a first dispatching plan; ④ Inputting the first dispatching plan into a parallel verification model to simulate extreme scenarios such as wind and solar power fluctuations or equipment failures, and outputting robust dispatching strategies and compensation allocation schemes; ⑤ Distributing a second dispatching plan to the energy storage device controller to execute physical actions, while simultaneously collecting device response data; ⑥ Binding the device response data to the pre-plan hash value output by the parallel verification model and storing it in a blockchain distributed ledger to form dual-track evidence storage; ⑦ Calling an audit interface to extract on-chain physical execution data and pre-plan hash values, generating an audit report that can be independently verified by multiple entities; ⑧ The main dispatching system and the parallel verification system respectively obtain on-chain execution deviation data, update model parameters, and complete closed-loop iteration.

[0031] Thus, by simulating extreme scenarios through a parallel verification system, robust strategies optimized by quantum annealing and Shapley value game compensation schemes are output, which are cross-verified with the second scheduling plan to form a decision-making mutual verification mechanism; based on blockchain dual-track evidence storage, the physical execution data of the equipment is bound and stored with the pre-plan hash value, and a timestamp-aligned verification pair is constructed to achieve full-link traceability of operations; a multi-entity audit interface is deployed to support industrial users to verify discharge volume, aggregators to retrieve quantum annealing parameters, and regulators to view game logs, with disputed data triggering on-chain zero-knowledge proof arbitration; execution deviation data drives the federated learning framework to encrypt and exchange the main system's Bayesian optimization parameters and the parallel system's adversarial network parameters, continuously improving the accuracy and credibility of scheduling decisions, fundamentally solving the problems of evidence silos and trust deficiencies in multi-entity collaborative scenarios.

[0032] The energy dispatching method based on virtual power plants provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0033] like Figure 1 As shown in the embodiment of this application, an energy dispatching method based on a virtual power plant is provided, which may include the following steps 101 to 103: Step 101: Based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract, generate a first scheduling plan and input the first scheduling plan into the parallel verification model to obtain a second scheduling plan.

[0034] The target virtual power plant is obtained by aggregating distributed energy resources; the parallel verification model is used to simulate wind and solar fluctuations or equipment failure scenarios to generate backup scheduling plans under extreme scenarios.

[0035] For example, in this application embodiment, physical system layer data is collected through an industrial Internet of Things network to obtain photovoltaic output curves, wind turbine status, energy storage charge status and user load metering values; and user demand response contracts are extracted from the power trading platform and the power constraints and settlement rules are parsed to obtain them.

[0036] Specifically, step 101 above may also include the following steps 101a and 101b: Step 101a: Obtain the target power data collected from the target virtual power plant, and the business constraints parsed from the target response contract of the power trading platform.

[0037] The target power data includes at least the following: photovoltaic output curve, wind turbine status, energy storage status of charge, and user load metering values.

[0038] Step 101b: Input the target power data and the business constraints into the main scheduling model to generate the first scheduling plan.

[0039] For example, the aforementioned physical system layer data acquisition is accomplished through industrial standard Internet of Things (IoT) networks. This refers to sensors and metering devices deployed in photovoltaic power plants, wind farms, energy storage units, and on the user side, monitoring the real-time operating status and energy flow of the physical equipment. The photovoltaic output curve reflects the change in photovoltaic module power generation over time; the wind turbine status includes information such as pitch angle and rotational speed, indicating the turbine's operating condition; the energy storage state of charge indicates the current level of electricity stored in the energy storage device; and the user load metering value is the user's real-time energy consumption or feedback data. These data collectively constitute the basic information for the operation of the virtual power plant's physical layer.

[0040] Specifically, step 101a above, the step of acquiring the target power data collected from the target virtual power plant, may further include the following steps 101a1 and 101a2: Step 101a1: Perform standardized timestamp processing on the power data collected from the target virtual power plant, unify the second-level device data to the millisecond-level precision, and convert the processed device data into binary format data.

[0041] Step 101a2: Establish the association between the binary format data and the target response contract based on the device identifier, and output the target power data.

[0042] For example, in this embodiment of the application, standardized timestamp processing is performed by a microservice component to unify second-level device data to millisecond-level precision; the processed device data is converted into a unified binary format; the association between the binary format data and the response contract terms is established based on the device identifier, and standardized physical system layer data, namely the aforementioned target power data, is output.

[0043] Specifically, step 101a above, the step of parsing the business constraints from the target response contract, may further include steps 101a3 and 101a4: Step 101a3: Parse the discharge threshold field and compensation ratio field in the target response contract to obtain multiple discharge thresholds and multiple compensation allocation ratios.

[0044] Step 101a4: Bind the multiple discharge thresholds and the multiple compensation allocation ratios to the corresponding energy storage devices to obtain the business constraints of the target response contract.

[0045] For example, in the embodiments of this application, the step of defining response contract terms may include: parsing the discharge threshold field and the compensation ratio field in the demand response contract; dynamically binding the parsed discharge threshold to the corresponding energy storage device identifier to generate a scheduling constraint rule base; and outputting the power constraint conditions including the scheduling constraint rules to the main scheduling model.

[0046] For example, defining response contract terms refers to obtaining signed user contract data from the power trading platform. These contracts exist in the form of structured data and typically contain key business constraints, such as the discharge quota that users must provide or accept during specific peak periods, as well as the conditions for triggering compensation mechanisms and specific settlement rules. In this embodiment of the application, these structured contract documents are parsed, and the terms therein are transformed into power constraint rules that the dispatching system can directly use.

[0047] For example, the aforementioned master scheduling model is responsible for generating the core scheduling plan. This model typically uses reinforcement learning algorithms (such as DQN deep Q-networks) as its decision-making core. Its working principle involves using the real-time physical system state data obtained in step 1 (such as power generation, energy storage status, and load demand) and the contractual electricity constraint rules parsed in step 2 as input information for the model. The model calculates based on a preset objective function (e.g., maximizing revenue, minimizing volatility, or complying with the contract) and outputs charging and discharging instructions for various controllable resources (especially energy storage devices), i.e., the aforementioned first scheduling plan. This step is the core decision for resource allocation.

[0048] For example, the second scheduling plan mentioned above includes: a backup scheduling plan for extreme scenarios, and a compensation allocation scheme when the extreme scenario causes losses. Step 101b may further include steps 101b1 and 101b2: Step 101b1: Generate quantum annealing input parameters corresponding to the second scheduling plan based on the wind and solar fluctuation probability model, and encode the quantum annealing input parameters as Hamiltonians to obtain the backup scheduling plan.

[0049] Step 101b2: Calculate the compensation allocation scheme of the backup scheduling plan using the Shapley value game model.

[0050] For example, the parallel verification model described above is a verification and supplementary system that operates independently of the main scheduling model, used to simulate potential risks and assess the robustness of the main plan. This model receives a first scheduling plan generated by the main scheduling model as a starting point. It first uses simulation tools or probabilistic models to generate a set of input parameters representing extreme scenarios (such as a sudden drop in wind power generation, drastic fluctuations in photovoltaic output, or sudden failures of critical equipment). Then, the quantum annealing strategy, as one of the core solvers, is used to handle these high-dimensional, complex optimization problems, calculating alternative scheduling strategies that remain feasible under such extreme scenarios. Simultaneously, the game theory strategy (typically using a Shapley value theory model) is applied to calculate how to fairly allocate compensation amounts and responsibilities among different entities such as users and aggregators when losses occur due to extreme scenarios. The model ultimately outputs the second scheduling plan described above, which includes a robust scheduling strategy for crisis backup and a compensation allocation scheme to provide a basis for subsequent disputes.

[0051] It should be noted that the confidence assessment module compares the deviation rate between the first scheduling plan and the second scheduling plan, and activates the manual review process when the deviation rate exceeds the threshold.

[0052] Step 102: Send the first scheduling plan to the target energy storage device and receive the device response data fed back by the target energy storage device.

[0053] For example, the execution of scheduling instructions is issued by the main scheduling system to the device control layer. For instance, the controller of an energy storage system receives and executes specific charging and discharging instructions. Simultaneously, the system collects real-time data on the actual response status of the devices after their actions via the Internet of Things (IoT) network, such as the actual discharge power curve of the energy storage unit. This step is crucial for translating the scheduling plan into physical world actions and obtaining execution feedback.

[0054] Step 103: Associate the device response data with the second scheduling plan and store it in the blockchain distributed ledger to form a dual-track evidence storage.

[0055] The blockchain-stored data on the distributed ledger is used by both parties to the target response contract to audit the energy transaction.

[0056] For example, the dual-track evidence storage mechanism in this application establishes a reliable association between physical world execution data and virtual world verification logic.

[0057] Specifically, step 103 above may also include the following steps 103a1 and 103a2: Step 103a1: Obtain the device response data generated by the target energy storage device executing the first scheduling plan, and encrypt the second scheduling plan using an encryption algorithm to generate a plan data digest.

[0058] Step 103a2: Bind the device response data with the plan data digest to generate a data verification pair, and store the data verification pair in the blockchain distributed ledger to complete dual-track evidence storage.

[0059] For example, the device controller executes the discharge command of the second scheduling plan and transmits the actual discharge power curve back to the evidence storage system through the industrial Internet of Things network; it calls the encryption algorithm to process the robust scheduling strategy output by the parallel verification model and generates a contingency plan data digest; it binds the actual discharge power curve and the contingency plan data digest to form a verification pair and stores them in the blockchain distributed ledger to complete dual-track evidence storage.

[0060] For example, the actual response data of the collected equipment (such as the discharge power curve) and the key information of the contingency plan output by the parallel verification model (processed by a hash algorithm to form immutable summary data) are bound together by timestamps or other unique identifiers and jointly recorded on the blockchain distributed ledger. This method of evidence storage forms two mutually corroborating data chains: the physical execution chain records what happened in the real world, while the simulation verification chain explains why such scheduling is reasonable or has a backup plan.

[0061] In one possible implementation, the blockchain network configuration smart contract is configured as follows: the smart contract receives the scheduling instruction timestamp and electricity price period data, and automatically matches the scheduling timestamp and peak electricity price period; when the matching result is a peak period, the associated user's pre-deposited margin account is locked; the cumulative value of the discharge is recorded in real time to the on-chain storage, and the user's pre-deposited margin account is released when the cumulative value reaches the threshold agreed in the contract.

[0062] Optionally, in this embodiment, the system also provides a channel for independent verification by multiple parties through an audit interface. Different participants access the stored evidence data on the blockchain through their respective authorized interfaces.

[0063] For example, after step 103 above, the energy dispatching method based on a virtual power plant provided in this application embodiment may further include the following step 104: Step 104: Receive the target verification instruction triggered by the target user and execute the verification strategy corresponding to the target verification instruction.

[0064] The target user includes any one of the following: a first user, a second user, and a third user; the target verification instruction includes any one of the following: a first verification instruction triggered by the first user, a second verification instruction triggered by the second user, and a third verification instruction triggered by the third user; the first verification instruction is used to retrieve the actual discharge sequence on the chain through the audit interface and compare it with the contractually agreed value; the second verification instruction is used to retrieve the quantum annealing model input parameters and compensation allocation scheme for that period through the audit interface; the third verification instruction is used to output the user marginal contribution calculation log in the Shapley value model through the audit interface.

[0065] For example, industrial users (i.e., the first user mentioned above) can retrieve historical actual discharge data of their own equipment and compare it with the contractually agreed values ​​for verification; aggregators (i.e., the second user mentioned above) can consult the operating parameters and basis (such as the input constraints of quantum annealing) recorded by the parallel verification system during a specific period in case of disputes, to prove the rationality of the scheduling behavior; and regulatory agencies (i.e., the third user mentioned above) can obtain the calculation process and result logs of compensation allocation in the game model. This design achieves transparency of execution data and multi-party auditability.

[0066] For example, an industrial user inputting a contract number triggers the first verification path: the audit interface retrieves the actual discharge sequence on the chain and compares it visually with the contractually agreed value; an aggregator submitting a dispute timestamp triggers the second verification path: the audit interface retrieves the quantum annealing model input parameters and compensation allocation scheme for that period; a regulatory agency inputting permission instructions triggers the third verification path: the audit interface outputs the user's marginal contribution calculation log in the Shapley value model.

[0067] For example, when the audit interface detects a data inconsistency in either path, it can also activate an on-chain arbitration contract.

[0068] Specifically, step 104 above may also include step 104a: Step 104a: When a data contradiction is detected, activate the arbitration contract deployed on the chain, call the zero-knowledge proof protocol to verify the source of the contradictory data, and feed back the output verification result to the target user.

[0069] For example, when the audit interface detects a data contradiction in any path: the on-chain deployed arbitration contract is activated, and the zero-knowledge proof protocol is invoked to verify the source of the contradictory data; the arbitration contract outputs the privacy-protected verification result and pushes it to the terminal device display interface of the disputing party.

[0070] For example, in this embodiment, the closed-loop iterative update mechanism ensures the model's self-evolution. The main scheduling system and the parallel verification system analyze the deviation between the execution result data stored on the blockchain and the original plan. The Bayesian optimization strategy is used by the main scheduling system to adjust the parameters (e.g., exploration factors) of its reinforcement learning model to reduce decision bias in similar scenarios. The parallel verification system utilizes the generative adversarial network strategy, particularly the training of the discriminator, to enhance its ability to identify potential false or unreasonable dispute patterns. To achieve model co-evolution while protecting the data privacy of all parties, a federated learning framework is adopted, allowing the main system model and the verification system model to securely exchange some parameter update information without sharing original sensitive data. This continuous learning and parameter update process enables the entire scheduling system to continuously adapt to new environments, improving scheduling accuracy and reliability.

[0071] The energy dispatching method based on virtual power plants provided in this application provides a reliable, traceable and continuously optimized operating environment for multi-entity participation in virtual power plants through physical data acquisition and contract rule parsing, main dispatching decision generation, independent parallel verification based on quantum and game theory strategies, establishing mutual trust evidence through dual-track blockchain storage, multi-party auditable interfaces, and a complete closed loop driven by federation.

[0072] The standardized processing flow for acquiring physical system layer data in this application aims to solve the problems of heterogeneous data protocols and time asynchrony in industrial equipment. The microservice component first performs timestamp alignment: synchronizing the clocks of devices such as photovoltaic inverters and wind turbine controllers via the NTP network time protocol, unifying the second-level sampled raw data to millisecond-level time accuracy, and eliminating time drift errors across device data. Next, a protocol conversion operation is performed: the raw data transmitted via industrial protocols such as Modbus and IEC60870 is converted into the standardized Avro binary format, achieving cross-platform data compatibility. Finally, a data association operation is performed: based on the device's unique identifier (such as the energy storage device ID), physical measurement data (such as the energy storage SOC value) is dynamically bound to the constraint clauses in the response contract (such as the discharge threshold), forming a standardized data stream that can be directly input into the scheduling model.

[0073] The parsing and binding mechanism for response contract terms in this embodiment focuses on solving the real-time matching problem between scheduling plans and contractual constraints. The system first parses key contract fields: extracting structured data such as discharge thresholds (e.g., 200kWh required during peak hours) and compensation ratios (e.g., 80% settlement if targets are not met) from the JSON-formatted demand response contract. Then, dynamic rule binding is performed: the parsed discharge thresholds are associated with specific energy storage device identifiers (e.g., device ID_123 bound to a threshold of 200kWh), generating a device-level scheduling constraint rule base. This rule base serves as input to the main scheduling model, ensuring the scheduling plan automatically conforms to the contractual agreement.

[0074] The parallel verification model in this application improves the robustness of the scheduling plan through dual verification: Quantum annealing strategy: Generate input parameters (such as a 30% probability of a sudden drop in wind speed) based on the wind and solar fluctuation probability model, encode extreme scenarios as Hamiltonians of the Ising model, and solve for the optimal robust strategy (such as running with a 20% reduction) through the quantum annealing algorithm.

[0075] Shapley value game strategy: Calculate the marginal contribution of each participant in extreme scenarios and fairly allocate compensation amounts (e.g., user A bears 60% of the loss due to high historical call frequency).

[0076] Confidence assessment mechanism: compare the deviation rate between the second scheduling plan and the quantum annealing backup strategy (e.g., deviation > 5%). If the deviation exceeds the threshold, it will be transferred to manual review to prevent the algorithm from failing.

[0077] The dual-track evidence preservation process in this embodiment constructs a mutual verification chain of physical execution and virtual verification: After the device controller executes the discharge command, it transmits the actual discharge power curve back via the OPC UA protocol (physical execution chain); the robust strategy (such as a derating scheme) output by the parallel verification system generates an immutable plan digest using the SHA-3 algorithm (simulated verification chain). The two are then bound together as a verification pair using timestamps (e.g., the discharge curve and plan digest bound to timestamp T1 are written into the blockchain to form traceable evidence. Any data tampering will result in a change in the hash value, ensuring the credibility of the evidence preservation.

[0078] The blockchain smart contract in this embodiment enables automatic contract fulfillment: the contract automatically matches the scheduling instruction timestamp with the peak electricity price period database (e.g., 14:00-16:00). When a match is successful, the associated user's margin account is immediately locked (e.g., freezing the amount corresponding to 200kWh in the account). During instruction execution, the discharge value recorded on the chain is accumulated in real time. When the accumulated value reaches the contract threshold (e.g., the accumulated discharge reaches 200kWh), the margin is automatically released to complete the settlement.

[0079] The audit interface in this application provides differentiated verification paths: Industrial user path: After entering the contract number, it automatically retrieves the actual discharge sequence on the chain (e.g., [150kWh, 180kWh]) and generates a comparative line chart with the contract threshold (200kWh). Aggregator path: After submitting the dispute timestamp (e.g., T1), it obtains the quantum annealing model input parameters (e.g., wind speed drop data) and compensation plan (user A compensates 120 yuan). Regulatory path: View the marginal contribution log calculated by the Shapley value model (user B's contribution = 0.35).

[0080] The on-chain arbitration mechanism in this embodiment handles data conflicts: when the audit interface detects a logical conflict (such as insufficient actual discharge but no compensation record), it automatically activates the arbitration smart contract. The contract calls a zero-knowledge proof protocol to verify the authenticity of the data source (such as proving that the discharge data comes from a trusted meter), generates a privacy-protected verification report (only displaying the verification conclusion), and pushes it to the terminal display interface of the disputing party.

[0081] The federated learning architecture in this application implements model co-evolution: Main scheduling model optimization: Bayesian optimization algorithm is used to analyze execution biases (such as the difference between predicted and actual output) and adjust the exploration factor parameters of the reinforcement learning model (reducing the probability of random actions). Parallel model optimization: A discriminator is trained through a generative adversarial network to identify false dispute features (such as abnormal discharge fluctuation patterns). Secure parameter exchange: The federated server encrypts and transmits the main model parameters and discriminator parameters, updating shared model weights without leaking the original data.

[0082] The specific optimization path of the federated learning architecture in this application embodiment is as follows: The main scheduling system collects on-chain execution deviation data to train a Gaussian process regression model, outputting the error distribution probability (e.g., ±5% error probability of 80%), and optimizes the action selection weights of the DQN algorithm accordingly (e.g., reducing the probability of high-risk actions). The parallel verification system inputs arbitration cases into the generative adversarial network to generate adversarial examples (e.g., simulating malicious user complaint patterns) to train the quantum annealing model, improving its adaptability to complex game scenarios (e.g., multi-user joint claims).

[0083] The energy dispatching method based on virtual power plants provided in this application addresses the trust and traceability issues among multiple stakeholders through a triple mutual verification mechanism. First, a dual-system collaborative pre-simulation mechanism is established: after the main dispatching model generates the first dispatching plan, the parallel verification model receives the plan and simulates extreme scenarios such as sudden changes in wind and solar power, and equipment failures, outputting a robust dispatching strategy optimized by the quantum annealing algorithm and a compensation allocation scheme calculated by the Shapley value game model. The outputs of the two systems are cross-validated by a confidence assessment module, and execution is triggered only when the deviation rate is below a threshold, preventing disputes arising from inappropriate dispatching decisions from the outset.

[0084] Secondly, a dual-track blockchain evidence storage chain is constructed: the device controller executes the second scheduling plan, generating physical response data (such as the discharge power curve) and transmitting it back in real time. Simultaneously, the pre-plan data output by the parallel verification model is hashed to generate an immutable digest. The physical execution data and the pre-plan digest are bound as verification pairs and written into the distributed ledger, forming a timestamp-aligned evidence storage between the physical execution chain and the simulated verification chain. Every execution result is associated with verifiable decision-making basis, achieving full-chain transparency in operations.

[0085] Finally, a multi-dimensional audit interface and federated evolution mechanism are deployed: industrial users call smart contracts to verify the actual on-chain discharge amount and contract threshold; aggregators retrieve the input parameters of the quantum annealing model to verify the rationality of extreme scenario handling; regulatory agencies view the marginal contribution log of the Shapley value model. Disputed data triggers an on-chain arbitration contract for zero-knowledge proof verification. Execution deviation data drives the federated learning framework to update the exploration factors of the main scheduling model and the discriminator parameters of the parallel verification model, continuously improving the decision-making accuracy and credibility of the dual system.

[0086] The energy dispatching method based on virtual power plants provided in this application first generates a first dispatching plan based on target power data collected from the target virtual power plant and business constraints parsed from the target response contract. This first dispatching plan is then input into a parallel verification model to obtain a second dispatching plan. The target virtual power plant is obtained by aggregating distributed energy resources. The parallel verification model is used to simulate wind and solar power fluctuations or equipment failure scenarios to generate a backup dispatching plan for extreme scenarios. Next, the first dispatching plan is sent to the target energy storage device, and the device response data fed back by the target energy storage device is received. Finally, the device response data and the second dispatching plan are associated and stored in a blockchain distributed ledger to form dual-track notarization. The blockchain notarization data on the blockchain distributed ledger is used by both parties to the target response contract to audit the energy transaction. This approach solves the problems of insufficient trust mechanisms and traceability of dispatching execution when multiple stakeholders participate in energy aggregation transactions, thereby improving the credibility of market transactions.

[0087] It should be noted that the energy dispatching method based on a virtual power plant provided in this application can be executed by an energy dispatching device based on a virtual power plant, or by a control module within that device for executing the energy dispatching method based on a virtual power plant. This application uses the execution of the energy dispatching method based on a virtual power plant by the energy dispatching device as an example to illustrate the energy dispatching device based on a virtual power plant provided in this application.

[0088] It should be noted that the energy dispatching methods based on virtual power plants shown in the accompanying drawings of the embodiments of this application are all illustrated by way of example with reference to one of the accompanying drawings of the embodiments of this application. In specific implementation, the energy dispatching methods based on virtual power plants shown in the accompanying drawings of the above methods can also be implemented in conjunction with any other accompanying drawings shown in the above embodiments, which will not be elaborated here.

[0089] The energy dispatching device based on a virtual power plant provided in this application is described below. The energy dispatching method based on a virtual power plant described below can be referred to in correspondence with the energy dispatching method based on a virtual power plant described above.

[0090] Figure 2 A schematic diagram of the structure of the energy dispatching device based on a virtual power plant provided in the embodiments of this application is shown below. Figure 2 As shown, it specifically includes: The plan generation module 201 is used to generate a first scheduling plan based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract, and input the first scheduling plan into a parallel verification model to obtain a second scheduling plan; the target virtual power plant is obtained by aggregating distributed energy resources; the parallel verification model is used to simulate wind and solar fluctuations or equipment failure scenarios to generate a backup scheduling plan under extreme scenarios; the data acquisition module 202 is used to send the first scheduling plan to the target energy storage device and receive the equipment response data fed back by the target energy storage device; the blockchain evidence storage module 203 is used to associate the equipment response data with the second scheduling plan and store it in a blockchain distributed ledger to form a dual-track evidence storage; wherein, the blockchain evidence storage data on the blockchain distributed ledger is used by both parties to the target response contract to audit the energy transaction.

[0091] Optionally, the data acquisition module 202 is further configured to acquire the target power data collected from the target virtual power plant, and the business constraints parsed from the target response contract of the power trading platform; the target power data includes at least the following: photovoltaic output curve, wind turbine status, energy storage load status, and user load metering value; the plan generation module 201 is specifically configured to input the target power data and the business constraints into the main scheduling model to generate the first scheduling plan.

[0092] Optionally, the data acquisition module 202 is further configured to perform standardized timestamp processing on the power data collected from the target virtual power plant, unify the second-level device data to the millisecond-level precision, and convert the processed device data into binary format data; the data acquisition module 202 is further configured to establish the association between the binary format data and the target response contract based on the device identifier, and output the target power data.

[0093] Optionally, the data acquisition module 202 is further configured to parse the discharge threshold field and the compensation ratio field in the target response contract to obtain multiple discharge thresholds and multiple compensation allocation ratios; the data acquisition module 202 is further configured to bind the multiple discharge thresholds and the multiple compensation allocation ratios with the corresponding energy storage devices to obtain the business constraints of the target response contract.

[0094] Optionally, the second scheduling plan includes: a backup scheduling plan for extreme scenarios, and a compensation allocation scheme when the extreme scenarios cause losses; the plan generation module 201 is specifically used to generate quantum annealing input parameters corresponding to the second scheduling plan according to the wind and solar fluctuation probability model, and encode the quantum annealing input parameters into Hamiltonians to obtain the backup scheduling plan; the plan generation module 201 is also specifically used to calculate the compensation allocation scheme of the backup scheduling plan using a Shapley value game model.

[0095] Optionally, the blockchain evidence storage module 203 is specifically used to obtain the device response data generated by the target energy storage device executing the first scheduling plan, and to encrypt the second scheduling plan using an encryption algorithm to generate a preliminary plan data digest; the blockchain evidence storage module 203 is also specifically used to bind the device response data with the preliminary plan data digest to generate a data verification pair, and to store the data verification pair in the blockchain distributed ledger to complete dual-track evidence storage.

[0096] Optionally, the device further includes: an audit module; the audit module is configured to receive a target verification instruction triggered by a target user and execute a verification strategy corresponding to the target verification instruction; wherein the target user includes any one of the following: a first user, a second user, and a third user; the target verification instruction includes any one of the following: a first verification instruction triggered by the first user, a second verification instruction triggered by the second user, and a third verification instruction triggered by the third user; the first verification instruction is configured to retrieve the actual discharge quantity sequence on the chain through the audit interface and perform a visual comparison with the contractually agreed value; the second verification instruction is configured to retrieve the quantum annealing model input parameters and compensation allocation scheme for that period through the audit interface; the third verification instruction is configured to: output the user marginal contribution calculation log in the Shapley value model through the audit interface.

[0097] Optionally, the audit module is specifically used to activate the on-chain arbitration contract when a data contradiction is detected, call the zero-knowledge proof protocol to verify the source of the contradictory data, and feed back the output verification result to the target user.

[0098] The energy dispatching device based on a virtual power plant provided in this application first generates a first dispatching plan based on target power data collected from the target virtual power plant and business constraints parsed from the target response contract. This first dispatching plan is then input into a parallel verification model to obtain a second dispatching plan. The target virtual power plant is obtained by aggregating distributed energy resources. The parallel verification model is used to simulate wind and solar power fluctuations or equipment failure scenarios to generate a backup dispatching plan for extreme scenarios. Next, the first dispatching plan is distributed to the target energy storage device, and the device response data fed back by the target energy storage device is received. Finally, the device response data and the second dispatching plan are associated and stored in a blockchain distributed ledger to form dual-track notarization. The blockchain notarization data on the distributed ledger is used by both parties to the target response contract to audit the energy transaction. This addresses the problems of insufficient trust mechanisms and traceability of dispatching execution when multiple stakeholders participate in energy aggregation transactions, thereby improving the credibility of market transactions.

[0099] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communications bus 340. The processor 310 can call logic instructions in the memory 330 to execute an energy dispatching method based on a virtual power plant. This method includes: first, generating a first dispatching plan based on target power data collected from the target virtual power plant and business constraints parsed from the target response contract; then inputting the first dispatching plan into a parallel verification model to obtain a second dispatching plan; the target virtual power plant is obtained by aggregating distributed energy resources; the parallel verification model is used to simulate wind and solar power fluctuations or equipment failure scenarios to generate a backup dispatching plan for extreme scenarios; next, the first dispatching plan is sent to the target energy storage device, and the device response data fed back by the target energy storage device is received; finally, the device response data and the second dispatching plan are associated and stored in a blockchain distributed ledger to form dual-track notarization; wherein, the blockchain notarization data on the blockchain distributed ledger is used by both parties to the target response contract to audit the energy transaction. This solves the problems of insufficient trust mechanisms and traceability of dispatching execution when multiple stakeholders participate in energy aggregation transactions, improving the credibility of market transactions.

[0100] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] On the other hand, this application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the energy dispatching method based on a virtual power plant provided by the above methods. The method includes: first, generating a first dispatching plan based on target power data collected from a target virtual power plant and business constraints parsed from a target response contract, and inputting the first dispatching plan into a parallel verification model to obtain a second dispatching plan; the target virtual power plant is obtained by aggregating distributed energy resources; the parallel verification model is used to simulate wind and solar fluctuations or equipment failure scenarios to generate a backup dispatching plan under extreme scenarios; then, the first dispatching plan is sent to a target energy storage device, and the device response data fed back by the target energy storage device is received; finally, the device response data and the second dispatching plan are associated and stored in a blockchain distributed ledger to form dual-track evidence storage; wherein, the blockchain evidence storage data on the blockchain distributed ledger is used by both parties to the target response contract to audit the energy transaction. In this way, the problems of lack of trust mechanisms and insufficient traceability of dispatch execution when multiple stakeholders participate in energy aggregation and trading can be solved, thereby improving the credibility of market transactions.

[0102] On another front, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the aforementioned energy dispatching methods based on virtual power plants. This method includes: first, generating a first dispatch plan based on target power data collected from a target virtual power plant and business constraints parsed from a target response contract; then, inputting the first dispatch plan into a parallel verification model to obtain a second dispatch plan; the target virtual power plant is obtained by aggregating distributed energy resources; the parallel verification model is used to simulate wind and solar power fluctuations or equipment failure scenarios to generate a backup dispatch plan for extreme scenarios; subsequently, the first dispatch plan is distributed to a target energy storage device, and equipment response data is received from the target energy storage device; finally, the equipment response data and the second dispatch plan are associated and stored in a blockchain distributed ledger to form dual-track notarization; wherein, the blockchain notarization data on the blockchain distributed ledger is used by both parties to the target response contract to audit the energy transaction. This addresses the problems of insufficient trust mechanisms and traceability of dispatch execution when multiple stakeholders participate in energy aggregation transactions, thereby improving the credibility of market transactions.

[0103] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An energy dispatching method based on a virtual power plant, characterized in that, include: Based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract, a first scheduling plan is generated, and the first scheduling plan is input into the parallel verification model to obtain a second scheduling plan; the target virtual power plant is obtained by aggregating distributed energy resources; The parallel verification model is used to simulate wind and solar fluctuations or equipment failure scenarios to generate backup scheduling plans under extreme scenarios. The first scheduling plan is sent to the target energy storage device, and the device response data fed back by the target energy storage device is received; The device response data is associated with the second scheduling plan and stored in a blockchain distributed ledger to form a dual-track evidence storage system; The blockchain-stored data on the distributed ledger is used by both parties to the target response contract to audit the energy transaction.

2. The method according to claim 1, characterized in that, The first scheduling plan is generated based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract, including: The system acquires the target power data collected from the target virtual power plant, as well as the business constraints parsed from the target response contract of the power trading platform. The target power data includes at least the following: photovoltaic output curve, wind turbine status, energy storage status of charge, and user load metering values. The target power data and the business constraints are input into the main scheduling model to generate the first scheduling plan.

3. The method according to claim 2, characterized in that, The acquisition of the target power data collected from the target virtual power plant includes: The power data collected from the target virtual power plant is subjected to standardized timestamp processing to unify the second-level equipment data to the millisecond-level precision, and the processed equipment data is converted into binary format data; The association between the binary format data and the target response contract is established based on the device identifier, and the target power data is output.

4. The method according to claim 2, characterized in that, The business constraints parsed from the target response contract include: The discharge threshold field and compensation ratio field in the target response contract are parsed to obtain multiple discharge thresholds and multiple compensation allocation ratios; By binding the multiple discharge thresholds and the multiple compensation allocation ratios with the corresponding energy storage devices, the business constraints of the target response contract are obtained.

5. The method according to claim 1, characterized in that, The second scheduling plan includes: a backup scheduling plan for extreme scenarios, and a compensation allocation scheme when losses are incurred due to extreme scenarios; The step of inputting the first scheduling plan into the parallel validation model to obtain the second scheduling plan includes: Based on the wind and solar fluctuation probability model, quantum annealing input parameters corresponding to the second scheduling plan are generated, and the quantum annealing input parameters are encoded as Hamiltonians to obtain the backup scheduling plan. The compensation allocation scheme of the backup scheduling plan is calculated using the Shapley value game model.

6. The method according to claim 1, characterized in that, The step of associating the device response data with the second scheduling plan and storing it in a blockchain distributed ledger includes: Obtain the device response data generated by the target energy storage device executing the first scheduling plan, and encrypt the second scheduling plan using an encryption algorithm to generate a contingency plan data digest; The device response data is bound to the contingency plan data summary to generate a data verification pair, and the data verification pair is stored in the blockchain distributed ledger to complete dual-track evidence storage.

7. The method according to any one of claims 1 to 6, characterized in that, After associating the device response data with the second scheduling plan and storing it in the blockchain distributed ledger, the method further includes: Receive the target verification command triggered by the target user and execute the verification strategy corresponding to the target verification command; The target user includes any one of the following: a first user, a second user, and a third user; the target verification instruction includes any one of the following: a first verification instruction triggered by the first user, a second verification instruction triggered by the second user, and a third verification instruction triggered by the third user; the first verification instruction is used to retrieve the actual discharge sequence on the chain through the audit interface and compare it with the contractually agreed value; the second verification instruction is used to retrieve the quantum annealing model input parameters and compensation allocation scheme for that period through the audit interface; the third verification instruction is used to output the user marginal contribution calculation log in the Shapley value model through the audit interface.

8. The method according to claim 7, characterized in that, The execution of the verification strategy corresponding to the target verification instruction includes: When a data contradiction is detected, the on-chain arbitration contract is activated, a zero-knowledge proof protocol is invoked to verify the source of the contradictory data, and the verification result is fed back to the target user.

9. An energy dispatching device based on a virtual power plant, characterized in that, The device includes: The plan generation module is used to generate a first scheduling plan based on the target power data collected from the target virtual power plant and the business constraints parsed from the target response contract, and input the first scheduling plan into the parallel verification model to obtain a second scheduling plan; the target virtual power plant is obtained by aggregating distributed energy resources; the parallel verification model is used to simulate wind and solar fluctuations or equipment failure scenarios to generate a backup scheduling plan under extreme scenarios; The data acquisition module is used to send the first scheduling plan to the target energy storage device and receive the device response data fed back by the target energy storage device; The blockchain evidence storage module is used to associate the device response data with the second scheduling plan and store it in the blockchain distributed ledger to form a dual-track evidence storage; The blockchain-stored data on the distributed ledger is used by both parties to the target response contract to audit the energy transaction.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the energy dispatching method based on a virtual power plant as described in any one of claims 1 to 8.

Images