Virtual power plant whole-process trusted aggregation method and system based on hierarchical trust chain

Abstract

The application belongs to the technical field of novel power system operation control and trust management, and specifically discloses a virtual power plant whole-process credible aggregation method and system based on hierarchical trust chains, which comprises the following steps: based on the characteristic requirements and trust transmission rules of different business links of the virtual power plant, differentiating hierarchical trust chain models of data acquisition links, dispatching control links and market transaction links are respectively constructed; through real-time trust degree evaluation and adaptive weight adjustment, the credibility calculation of multi-agent collaborative decision is realized. The application constructs a trust network composed of multiple efficient, safe and transparent virtual power plant trust chains, provides solid technical support for the fair competition, intelligent dispatching and reliable operation of the power market, and ensures the efficient interaction and stable operation of the power system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new power system operation control and trust management, and particularly relates to a virtual power plant full-process trusted aggregation method and system based on a hierarchical trust chain. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute the prior art.

[0003] As an important technical means of integrating distributed energy resources, virtual power plants play a key role in building new power systems dominated by new energy. However, with the continuous expansion of the scale of distributed energy access, virtual power plants involve multiple business links and multiple participating subjects such as data collection, dispatching control, market trading, and there are complex information interaction and trust transmission relationships between links. Due to the diversity of participating subjects, the wide geographical distribution and the openness of the communication network, there is a serious lack of trust, especially the trust fault problem in the process of integrating heterogeneous resources, which has become an important factor restricting the safe and stable operation of virtual power plants. Due to the lack of a unified trust management mechanism, it is difficult for each participating subject to establish an effective trust relationship, resulting in problems such as difficulty in guaranteeing data authenticity, poor execution effect of dispatching instructions, and fraud risk in market transactions.

[0004] Traditional virtual power plant trust management methods usually focus on single-point verification or simple identity authentication, and pay less attention to the continuity and consistency of cross-link trust transmission, resulting in incomplete trust chains. Although existing technologies propose some trust verification methods based on blockchains and Internet of Things, these trust verification methods often fail to fully consider the differentiated needs of different business links of virtual power plants, and it is difficult for a unified trust verification mechanism to adapt to complex business scenarios. Moreover, a single verification method often fails to cover the full-stack trust needs from hardware devices to application services, resulting in trust fault problems. Moreover, most existing trust models are based on static verification, which is difficult to adapt to the differentiated needs of different business links of virtual power plants, lacks targeted trust transmission mechanism design, and cannot realize the effective combination of real-time trust evaluation and long-term trust management. In addition, existing methods lack real-time trust degree evaluation and adaptive adjustment capabilities when facing network attacks, device failures and other abnormal situations. The trust management of each business link is relatively independent, and there is a lack of unified trust transmission and coordination mechanism. SUMMARY

[0005] In order to solve the above problems, the application provides a virtual power plant full-process trusted aggregation method and system based on a hierarchical trust chain, which can construct a differentiated trust transmission mechanism according to the characteristic requirements of different business links, establish a complete trust verification system from hardware to application, realize dynamic trust transmission across links and trusted security of multi-agent collaborative decision-making, and effectively solve the trust fault problem in the integration of heterogeneous resources.

[0006] In some embodiments, the following technical solutions are adopted:

[0007] A virtual power plant full-process trusted aggregation method based on a hierarchical trust chain, comprising:

[0008] Based on the characteristic requirements and trust transmission rules of different business links of the virtual power plant, differentiated hierarchical trust chain models of the data acquisition link, the scheduling control link and the market transaction link are constructed respectively;

[0009] In the data acquisition link, the original data of the terminal device is collected through the edge gateway, and the device identity authentication and data integrity check are combined to ensure the trustworthiness of the bottom layer device;

[0010] In the scheduling control link, the data stream collected from the edge gateway is received, photovoltaic and load are predicted, and the optimal scheduling scheme is generated; the optimization objective is to minimize the interaction cost with the power grid to maximize the virtual power plant revenue; the power balance constraint compliance and the energy balance degree are calculated respectively, and then the scheduling scheme credibility is calculated to ensure the trustworthiness of the intermediate layer service;

[0011] In the market transaction link, buy and sell orders are generated according to the scheduling scheme, and a hash value is added to each transaction; a blockchain smart contract verification mechanism is adopted to realize the trusted execution of the top layer business;

[0012] Through real-time trust evaluation and adaptive weight adjustment, the credibility calculation of multi-agent collaborative decision-making is realized.

[0013] In some other embodiments, the following technical solutions are adopted:

[0014] A virtual power plant full-process trusted aggregation system based on a hierarchical trust chain, comprising:

[0015] The model construction module is configured to construct differentiated hierarchical trust chain models of the data acquisition link, the scheduling control link and the market transaction link based on the characteristic requirements and trust transmission rules of different business links of the virtual power plant;

[0016] The data acquisition trusted verification module is configured to collect the original data of the terminal device through the edge gateway in the data acquisition link, and combine the device identity authentication and data integrity check to ensure the trustworthiness of the bottom layer device;

[0017] The scheduling control trusted verification module is configured to receive data streams collected from the edge gateway at a scheduling control link, predict photovoltaic and load, and generate an optimal scheduling scheme; and calculate power balance constraint compliance and energy balance degree respectively to calculate scheduling scheme trusted degree to guarantee the trustworthiness of the intermediate layer service, with the optimization target of minimizing the interaction cost with the power grid.

[0018] The market transaction trusted verification module is configured to generate buy / sell orders according to the scheduling scheme at a market transaction link, add a hash value to each transaction, and use a blockchain smart contract verification mechanism to realize trusted execution of the top-level business.

[0019] The collaborative decision trusted degree calculation module is configured to realize trusted degree calculation of multi-agent collaborative decision through real-time trust degree evaluation and adaptive weight adjustment.

[0020] In some other embodiments, the following technical solutions are adopted:

[0021] A terminal device includes a processor and a memory, the processor is used to implement instructions; the memory is used to store a plurality of instructions, the instructions are suitable for being loaded and executed by the processor to implement the virtual power plant full-process trusted aggregation method based on the hierarchical trust chain.

[0022] In some other embodiments, the following technical solutions are adopted:

[0023] A computer readable storage medium, wherein a plurality of instructions are stored, the instructions are suitable for being loaded and executed by the processor of the terminal device to implement the virtual power plant full-process trusted aggregation method based on the hierarchical trust chain.

[0024] Compared with the prior art, the beneficial effects of the present application are:

[0025] (1) The virtual power plant aggregation operation trusted verification system is designed, the virtual power plant can not only realize efficient monitoring and resource optimization configuration of the power grid operation, but also can ensure the safety, transparency and non-tamperability of information flow through the blockchain technology, thereby solving the trust problem between the virtual power plant and the power grid dispatching system and in the power market. Finally, a trust network composed of multiple efficient, safe and transparent virtual power plant trust chains is constructed, which provides solid technical support for fair competition, intelligent scheduling and reliable operation of the power market, and ensures efficient interaction and stable operation of the power system.

[0026] (2) Firstly, the application constructs a differentiated hierarchical trust chain model based on the characteristic requirements of different business links of a virtual power plant, respectively adopts tree type, star type and distributed P2P structure to realize accurate matching of trust transmission mechanism and business process; then, designs a three-level trusted verification system integrating Internet of Things device authentication, cloud computing dynamic optimization and blockchain smart contract, establishes a complete trust chain from the hardware trust root to the application layer; finally, through a cross-link dynamic trust transmission mechanism, combined with real-time trust degree evaluation and adaptive weight adjustment, realizes trusted security of multi-agent collaborative decision-making, and constructs a whole-process trusted aggregation optimization model of a virtual power plant.

[0027] (3) The method of the application can effectively solve the trust fault problem in the integration of heterogeneous resources, significantly improve the trust degree and economic benefit of a virtual power plant in a network attack scenario, and realize safe and trusted aggregation of distributed energy resources through a dynamic trust management mechanism. In addition, the method of the application has good adaptability and expansibility, can adapt to the operation scenarios and security requirements of virtual power plants of different scales, and provides important technical support for building a new power system mainly based on new energy.

[0028] Other features and advantages of the present application will be in part apparent and in part pointed out hereinafter in the description of the application. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 a schematic diagram of a whole-process trusted aggregation method of a virtual power plant based on a hierarchical trust chain in an embodiment of the application;

[0030] Figure 2 a schematic diagram of a future 24-hour scheduling plan generation in an embodiment of the application;

[0031] Figure 3 a schematic diagram of an IEEE30 node network attack topology in an embodiment of the application;

[0032] Figure 4 a schematic diagram of a trust degree improvement effect comparison in an embodiment of the application;

[0033] Figure 5 a schematic diagram of a problem that can be optimally solved in a virtual power plant by using a whole-link trust chain in an embodiment of the application. DETAILED DESCRIPTION

[0034] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless otherwise indicated, all technical and scientific terms used in the application have the same meaning as generally understood by those skilled in the art to which the application belongs.

[0035] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0036] Embodiment One

[0037] In one or more embodiments, a virtual power plant full-process trusted aggregation method based on hierarchical trust chain is disclosed, which specifically includes the following processes:

[0038] S101: Based on the characteristic requirements and trust transmission rules of different business links of the virtual power plant, differential hierarchical trust chain models are respectively constructed for the data acquisition link, the scheduling control link and the market transaction link;

[0039] S102: In the data acquisition link, the original data of the terminal equipment is collected through the edge gateway, and the device identity authentication and data integrity check are combined to ensure the trustworthiness of the bottom layer equipment;

[0040] S103: In the scheduling control link, the data stream collected from the edge gateway is received, the photovoltaic and load are predicted, and the optimal scheduling scheme is generated; the optimization objective is to minimize the interaction cost with the power grid to maximize the virtual power plant revenue; the power balance constraint compliance and the energy balance degree are calculated, and then the scheduling scheme trustworthiness is calculated to ensure the trustworthiness of the middle layer service;

[0041] S104: In the market transaction link, buy and sell orders are generated according to the scheduling scheme, and a hash value is added to each transaction; a blockchain smart contract verification mechanism is adopted to realize the trusted execution of the top layer business;

[0042] S105: Through real-time trust degree evaluation and adaptive weight adjustment, the trustworthiness calculation of multi-agent collaborative decision is realized.

[0043] In this embodiment, the virtual power plant full-process trusted aggregation method based on hierarchical trust chain mainly includes three core links of differential hierarchical trust chain construction, three-level trusted verification system design and cross-link dynamic trust transmission mechanism. First, based on the characteristic requirements and trust transmission rules of different business links of the virtual power plant, differential hierarchical trust chain models are constructed to accurately match the business processes and trust requirements of each link. Combined with the Figure 1For the characteristics of massive device access in the data acquisition link, a tree-type hierarchical cascade structure is used to realize the trusted access of Internet of Things devices; for the centralized management needs of the scheduling control link, a star structure is used to establish a trust management mechanism with the scheduling center as the core; for the multi-party negotiation characteristics of the market transaction link, a distributed P2P structure is used to realize decentralized trust verification.

[0044] In this embodiment, a three-level trusted verification system is designed to establish a complete trust chain from the hardware trust root to the application layer. Specifically, a hardware trust root verification mechanism is constructed at the device layer, combined with device identity authentication and data integrity verification to ensure the trustworthiness of the underlying devices; a cloud computing dynamic optimization verification mechanism is established at the platform layer to ensure the trustworthiness of the intermediate layer services using real-time performance monitoring and anomaly detection algorithms; a blockchain smart contract verification mechanism is constructed at the application layer to realize the trusted execution of the top-level business using distributed ledger technology. Finally, a cross-link dynamic trust transfer mechanism is constructed to realize the trusted guarantee of multi-agent collaborative decision-making through real-time trust evaluation and adaptive weight adjustment.

[0045] As a specific implementation, the process of constructing a differentiated hierarchical trust chain model is as follows:

[0046] Starting from the characteristic requirements and trust transfer rules of different business links of virtual power plants, through analysis of the business characteristics of the three links of data acquisition, scheduling control, and market transaction, as well as the trust transfer structures of tree type, star type, and distributed P2P, a differentiated hierarchical trust chain model for virtual power plants is constructed.

[0047] Combined with Figure 1 , the specific process includes:

[0048] (1) Overall architecture design of trust transfer mechanism:

[0049] The trust transfer mechanism is analyzed and constructed for the three parts of trust in data acquisition, scheduling instructions, and market transactions in virtual power plants.

[0050] Trust root: The Trusted Platform Module (TPM) is used as the hardware trust root and is set up in the central control area of the virtual power plant. The central control area is the core hub of the virtual power plant, not only bearing the unified scheduling function of distributed resources, but also being the center node of security policy formulation and execution. Establishing a trust root in this area can ensure the in-depth defense of system security from the architecture design level, while improving management efficiency and standardization, and building a reliable security foundation for the entire virtual power plant system.

[0051] Transmission mode: At the implementation level, the data acquisition chain adopts a tree structure design, which fully utilizes the scalability feature of the tree trust chain. By dynamically adjusting the acquisition range, combined with the hierarchical management mechanism, efficient data aggregation and hierarchical filtering are realized. This structure supports the strategy of collecting and preprocessing data nearby, significantly reducing the risk of network congestion by optimizing the transmission path. The deployment of multi-level data acquisition nodes further enhances the real-time performance and reliability of the system, effectively meeting the core technical requirements of the data acquisition link.

[0052] The dispatching control chain adopts a star structure to achieve this topology, which enables the central node of the star trust chain to establish direct connections with each execution node. The characteristics of the shortest communication path and the lowest transmission delay ensure the rapid transmission of control instructions. In addition, the convenient fault diagnosis capability and fast response mechanism brought by its centralized management mode significantly improve the reliability of the control system, fully meeting the strict requirements of low delay, scalability and flexibility of dispatching control.

[0053] The market transaction chain selects a distributed P2P structure, which is a typical implementation of a hybrid dynamic model. This design fully embodies the pursuit of transaction transparency. The decentralized nature of the P2P structure effectively eliminates the risk of single-point failure, improving system availability while enhancing transaction fairness. This structure has significant advantages such as data multi-point backup and high fault tolerance, ensuring stable operation of the system. More importantly, its mechanism characteristics of equal participation and information sharing provide an ideal platform for the implementation of consensus mechanisms, fundamentally guaranteeing the transparency and reliability of transactions, which meets the core technical demands of modern transaction platforms.

[0054] (2) Virtual power plant full-chain trusted aggregation operation system design:

[0055] Based on the aforementioned trust chain theoretical framework, a complete virtual power plant aggregation operation trusted verification scheme is designed. This scheme combines edge computing, distributed storage, and blockchain technology to achieve efficient access and trusted management of large-scale distributed energy, as shown in Figure 1 .

[0056] (2-1) Data acquisition trusted verification subsystem:

[0057] The data acquisition trusted verification subsystem is mainly responsible for the access and edge computing of devices, including smart meters, energy storage PCS, photovoltaic inverters, and load controllers. These devices are connected to the system through edge gateways, which can preprocess and analyze raw data in real time, and implement local storage and management of data. This improves the real-time performance and reliability of the system.

[0058] (2-2) Dispatching control trusted verification subsystem:

[0059] As the data processing hub of the system, the data collection service uniformly receives data streams from the edge layer and stores them in the InfluxDB distributed time series database cluster. Predictions of photovoltaic and load are made to provide decision-making basis for the dispatch optimization module. The dispatch optimization module considers multiple factors such as load prediction results, grid constraints, and economy to generate the optimal dispatch scheme, realizing intelligent operation of the virtual power plant.

[0060] (2-3) Market transaction trusted verification subsystem:

[0061] A trusted management platform is built using blockchain technology to ensure the non-tamperability and full traceability of transaction data through distributed ledger technology. The system integrates energy order management, automated matching engine, and blockchain confirmation mechanism to realize transparent trading and settlement of energy assets. The energy blockchain adapter connects traditional energy dispatching and blockchain network to ensure consistency and security of the transaction process. It provides an efficient, fair, and trusted trading environment for distributed energy market participants, supporting efficient decision-making and system maintenance.

[0062] In this embodiment, the trust chain has the following important characteristics:

[0063] 1) Verifiability: any entity can verify the identity legitimacy and behavior compliance of associated entities through digital signature, hash verification, etc., to meet:

[0064] (1)

[0065] 2) Transitivity: if entity trusts , trusts , then can also trust . This transitivity allows trust relationships to be extended to a wider network.

[0066] 3) Traceability: the system needs to record the establishment process of trust relationships completely to ensure that any trust decision can be traced back to the trusted root through audit logs :

[0067] (2)

[0068] In this embodiment, the original data of terminal devices is collected through edge gateways at the data collection link, and device identity authentication and data integrity verification are combined to ensure the trustworthiness of the underlying devices. The specific implementation is as follows:

[0069] (1) Device identity authentication and data integrity verification:

[0070] Device identity authentication is to determine whether the device is correctly connected by comparing the device id.

[0071] Data integrity is verified by calculating the comprehensive integrity score, wherein the comprehensive integrity score is obtained by calculating the average value of the field integrity score and the data length score.

[0072] The field integrity score is:

[0073] (3)

[0074] wherein, is the set of mandatory fields, is the set of actually existing fields, is the current timestamp, is the device identity id, is the original data collected by the device.

[0075] The data length score is:

[0076] (4)

[0077] wherein, is the actual length of the decompressed data, (byte) is the reference length.

[0078] The comprehensive integrity score is:

[0079] (5)

[0080] The threshold value can be set to determine whether the data integrity is qualified, or the credibility of the data collection part can be determined by the integrity score, so as to trace back and check whether there is a problem in the data collection part.

[0081] (2) Data anomaly alarm:

[0082] The mean and variance of the data sequence in the time window are calculated respectively, and then the Z-score of each data point is calculated, and the Z-score method is used to determine whether the data point is an abnormal data point; for example: when the value of Z-score satisfies , it is determined that the device data change is in an abnormal state, triggering an alarm.

[0083] In this embodiment, the data stream collected from the edge gateway is received at the scheduling control link, and photovoltaic and load are predicted. The prediction method can use existing methods, such as: using LSTM neural network and random forest model respectively to perform 24-hour rolling prediction on photovoltaic power generation and load power.

[0084] The optimal scheduling scheme is generated by comprehensively considering multiple factors such as load prediction results, power grid constraints and economy, and intelligent operation of the virtual power plant is realized; wherein, the optimal scheduling scheme is mainly obtained by adjusting the energy storage, the energy storage is discharged preferentially in the valley period, the energy storage is charged preferentially in the peak period, the net power is calculated in the flat electricity price period, and the optimization objective is to minimize the interaction cost with the power grid, and the final energy storage output adjustment result and the actual exchange power with the power grid are obtained by optimizing and solving the objective function, so as to generate the scheduling scheme.

[0085] The power balance constraint compliance and the energy balance degree are calculated respectively, and then the scheduling scheme reliability is calculated, so as to guarantee the reliability of the intermediate layer service. The specific implementation process is as follows:

[0086] (1) The peak-valley electricity price strategy of the embodiment is as follows:

[0087] (6)

[0088] Wherein, represents the electricity price in different periods, represents the peak electricity price, represents the valley electricity price, represents the flat electricity price in the non-peak-valley period. , are the peak period set and the valley period set respectively.

[0089] The system adopts different optimization strategies according to different periods. The energy storage is discharged preferentially in the valley period, and the energy storage is charged preferentially in the peak period. The net power is calculated in the flat electricity price period:

[0090] (7)

[0091] If , then:

[0092] (8)

[0093] (9)

[0094] Wherein, is the net power, i.e. the surplus / deficiency of photovoltaic power generation minus load power consumption, which is used to adjust the energy storage charging / discharging plan; is the rated capacity of the energy storage system, is the maximum charging / discharging power of the energy storage system, is the maximum charging capacity, is the charging efficiency, represents the output power of the photovoltaic system at time t, represents the power demand of the load at time t, represents the charging / discharging power of the energy storage system at time t, the positive value represents charging, and the negative value represents discharging; SoS(t) is the state of charge of the energy storage system at time t, SoS(t-1) is the state of charge of the energy storage system at the previous time, SoS(t-1) is the state of charge of the energy storage system at the previous time, SoSmax is the maximum state of charge allowed for the energy storage system.

[0095] The above formula represents the calculation of the maximum chargeable power when there is energy surplus, taking the minimum value of the three limiting factors of the charge power limit of the energy storage system, the current available net power, and the acceptable charge of the battery (considering the charging efficiency ).

[0096] If , then:

[0097] (10)

[0098] (11)

[0099] where, Pmaxdis the maximum discharge power of the energy storage system, ηdis the discharge efficiency.

[0100] The above formula represents the calculation of the maximum dischargeable power when there is energy deficit, taking the minimum value of the three limiting factors of the charge power limit of the energy storage system, the current required power gap, and the dischargeable power of the battery (considering the discharge efficiency ).

[0101] (2) To minimize the interaction cost with the grid as the optimization objective, a target function is established, and the final output adjustment result of the energy storage and the actual exchange power with the grid are obtained by optimizing the target function, so that the virtual power plant revenue is maximized, that is, the transaction volume is adjusted according to the price change to obtain the maximum profit.

[0102] The target function is specifically:

[0103] (12)

[0104] Constraints:

[0105] (13)

[0106] (14)

[0107] (15)

[0108] (16)

[0109] where, ​Ppv(t) represents the output power of the photovoltaic system at time t, Pgrid(t) represents the exchange power of the grid at time t, positive value represents buying power from the grid, and vice versa; Pload(t) represents the power demand of the load at time t, Pstorage(t) represents the charging and discharging power of the energy storage system at time t, positive value represents charging, and negative value represents discharging, Pmax represents the maximum allowed grid interaction power, both in kw.

[0110] Equation (13) is the power balance constraint, equation (14) is the energy storage state of charge constraint, equation (15) is the energy storage charging and discharging constraint, and equation (16) is the grid interaction constraint. These constraints are considered to ensure the service life of the energy storage system and the stability of the grid.

[0111] (3) Calculate the power balance constraint compliance and energy balance degree respectively, and then calculate the scheduling scheme credibility to ensure the credibility of the intermediate layer service; The credibility of the scheduling scheme can ensure that the scheduling plan meets the power balance and energy balance constraints, and can be transmitted to the market transaction module for correct execution. For example: a credibility threshold can be set, when the credibility of the scheduling scheme reaches the credibility threshold, it is considered that the scheme is credible, otherwise, an alarm is output, at this time, it can be checked whether the system is affected by network attack to cause the scheduling plan to be received incorrectly.

[0112] Specifically, the power balance constraint compliance is determined based on the ratio of the number of constraint violations to the total number of checks; The energy balance degree is determined based on the output power of the photovoltaic system at time t, the grid exchange power, the charging and discharging power of the energy storage system, and the load demand power; The credibility of the scheduling scheme is the weighted sum of the power balance constraint compliance and the energy balance degree.

[0113] As a specific example, the calculation method of the power balance constraint compliance is:

[0114] (17)

[0115] The calculation method of the energy balance degree is:

[0116] (18)

[0117] The calculation method of the scheduling scheme credibility is:

[0118] (19)

[0119] Wherein, represents the power balance constraint compliance, is the number of constraint violations, is the total number of checks. is the energy balance degree, is the comprehensive credibility score, and respectively, and the sum of the two is 1.

[0120] In this embodiment, buy and sell orders are generated according to the dispatch scheme in the market transaction link, and a hash value is added to each transaction. The blockchain smart contract verification mechanism is used to realize the trusted execution of the top-level business by using the distributed ledger technology.

[0121] (1) In the market transaction link, the order generation model is used to simulate the actual operation process to generate buy and sell orders for transactions. The matching model is used to match the buy and sell orders according to the matching logic. If the matching is successful, the transaction is successful. The revenue calculation model is used to obtain the revenue after the transaction of the orders generated by the dispatch plan is completed.

[0122] The logic of the order generation model in this embodiment can be: when the exchange power of the power grid at time t is , a sell order is generated; when , a buy order is generated.

[0123] The basic electricity price based on the peak-valley electricity price strategy is as follows:

[0124] (20)

[0125] wherein, is the peak-time electricity price considering market depth, is the valley-time electricity price considering market depth, is the electricity price of other periods considering market depth.

[0126] The above formula is used for price generation in market transactions. The final transaction price is generated in combination with the weight parameter, which is used to simulate real market transactions. For example: it can be assumed that the basic peak-time electricity price = 1 yuan / kwh, and the current market price = 1.2 yuan / kwh. Then, the optimal offer can be calculated by the buyer and the seller according to formula (21) and (22).

[0127] The optimal price generation model considering market depth information is as follows:

[0128] (21)

[0129] (22)

[0130] wherein, is the optimal offer of the seller considering market depth information, is the optimal offer of the buyer considering market depth information; is the highest buy order price with market depth, The minimum sell order price for adding market depth. , , , are weight coefficients, which can adjust the buy and sell order price strategy according to actual needs.

[0131] This embodiment first obtains the real-time market price based on formula (20), and then generates buy and sell order prices based on formulas (21) and (22). Then, according to the order matching condition, it is judged whether the two sides of the offer can be transacted, and the transaction volume is calculated according to formula (25).

[0132] The matching model is specifically:

[0133] (23)

[0134] (24)

[0135] (25)

[0136] The requirement for order matching is that the buy order price is greater than 90% of the sell order price , and a price tolerance of 5% is set to make more orders match. The transaction price is the average of the successful buy order price and the sell order price, and the quantity is defined as the minimum value of the buy order electricity quantity and the sell order electricity quantity .

[0137] The revenue calculation model is specifically:

[0138] (26)

[0139] (27)

[0140] (28)

[0141] (29)

[0142] wherein, is the energy storage arbitrage revenue, formulas (27-29) are constraint conditions that need to be met for maximizing the revenue, wherein is the charging power, is the discharging power, formula (27) describes the change rule of the state of charge of the energy storage system between adjacent time nodes, and formula (29) restricts that the energy storage system cannot charge and discharge at the same time.

[0143] (30)

[0144] (31)

[0145] wherein, is the net benefit of grid transaction, is the total benefit calculation; is the basic electricity price at time t, is the sell order price at time t, is the buy order price at time t.

[0146] (2) The blockchain smart contract verification mechanism is adopted to realize the trusted execution of the top-level business by using the distributed ledger technology.

[0147] The blockchain model is the basis for ensuring the credibility of the market transaction module. A corresponding hash value is generated through the blockchain for each order generated, and a corresponding hash value is generated for each order matched. The accepted dispatch plan also has a corresponding hash value. The credibility of the transaction is ensured through hash value comparison.

[0148] The blockchain is composed of a series of blocks (Block), each block contains a number of transactions, and the hash value of the previous block, forming a chain structure.

[0149] (32)

[0150] (33)

[0151] (34)

[0152] (35)

[0153] Equation (32) defines the block, is the block index, is the transaction set contained in the block, is the timestamp, is the hash value of the previous block, is the random number adjusted in the proof of work, the proof of work mechanism adjusts the value of so that the hash value of the block meets certain difficulty conditions, ensuring the security and non-tamperability of the blockchain.

[0154] The blockchain validity verification is set, which needs to meet equation (34): the pre-hash of each block is correct; and equation (35): the proof of work of each block is valid.

[0155] (36)

[0156] (37)

[0157] (38)

[0158] wherein, is an unconfirmed transaction pool, and the unconfirmed transactions are added to a new block , a legitimate is found by proof of work, and the new block is added to the blockchain; represents the last transaction in the transaction pool; represents the index number of the last block in the current blockchain, which is used to determine the index number of the new block (new block index = last block index + 1); is the current timestamp, which records the specific time when the new block is created, and ensures the time sequence of the blockchain, facilitating the tracking of the block creation time; represents the hash value of the last block.

[0159] In this embodiment, the trustworthiness in a specified network attack environment is calculated through real-time trust assessment and adaptive weight adjustment, to verify the trust chain's ability to improve the trustworthiness of the virtual power plant, and to assist the multi-agent collaborative decision-making of the virtual power plant in a trusted environment in data acquisition, dispatching control and market transactions.

[0160] The real-time trust calculation framework of this embodiment includes three trust calculation dimensions and introduces a dynamic parameter updating mechanism, building a complete trust evaluation chain from abstract power system nodes to specific industrial equipment and finally to network attack targets, forming a complete conversion of trust evaluation subjects. In the final result, it can be seen that the introduction of the trust chain in the virtual power plant greatly improves the trustworthiness of the system, so that the multi-agent in the entire virtual power plant can make trusted decisions in a more trusted environment.

[0161] In this embodiment, the subjective trustworthiness is determined based on the direct trust value and the recommended trust value; the objective trustworthiness is determined based on the attack success rate, the security event impact and the vulnerability impact; the subjective trustworthiness and the objective trustworthiness are weighted and summed to obtain the comprehensive trustworthiness; wherein the weight coefficient is dynamically adjusted based on the number of interaction history; the comprehensive trustworthiness is adjusted by a trust evolution factor; the value of the trust evolution factor is determined based on the trust change trend.

[0162] Specifically, the subjective trust calculation is:

[0163] (39)

[0164] wherein, is the subjective trustworthiness, is the direct trust weight, is the direct trust value, To recommend trust weights, To recommend trust values.

[0165] Objective trust calculation is:

[0166] (40)

[0167] In the formula, Objective trust degree, Attack success rate, SuccessfulAttacks is the number of attacks that successfully broke through the defense, and TotalAttacks is the total number of attacks executed, both of which are parameter results statistically obtained during actual system operation. Security event impact is calculated by assessing the severity of each security event and mapping it to a specific impact weight; specifically, the system classifies security events into four levels of severity, assigning different weight values: low risk (0.02), medium risk (0.05), high risk (0.10), and severe risk (0.15). For a set of security events, the overall impact value is the average of all event weights, with 0.3 set as the upper limit to avoid excessive impact. Mathematically expressed as: ; where The weight of the i-th event, n is the total number of security events; a security event refers to a specific event that affects system security (such as unauthorized login, configuration error, suspicious access, detection of malicious software, continuous attack attempt, data leakage, successful intrusion, etc.), which is classified into low, medium, high, and severe levels according to severity in the system. Vulnerability impact is calculated based on the CVSS (directly calling the cvss library in Python) score; the system first calculates the average CVSS score of all vulnerabilities, then divides this average by 50 for scaling to a range suitable for trust degree calculation, and sets 0.2 as the upper limit to ensure that the vulnerability impact is within a controllable range. This calculation process can be represented by the following mathematical formula: , where is the CVSS score of the i-th vulnerability, and n is the total number of vulnerabilities. By scaling the CVSS value by dividing by 50, the influence of a single factor on trust degree is avoided.

[0168] Comprehensive trust degree calculation is:

[0169] (41)

[0170] where , respectively, the subjective trust weight and the objective trust weight, a dynamic weight adjustment mechanism is adopted, when the system lacks interaction history, the subjective trust weight is set to 0, and the objective trust weight is set to 1.0; when there is enough interaction data, the configured weights are used: for example, the subjective trust weight can be set to 0.6, and the objective trust weight can be set to 0.4 for weighted average.

[0171] The final trust degree is calculated by comprehensive trust, and is adjusted by the trust evolution factor E:

[0172] (42)

[0173] (43)

[0174] The trust evolution factor E of the embodiment is based on the change trend of the comprehensive trust The calculation is that when the trust is stable, it is 1.0, when the trust rises, it is increased by 20% at most, and when the trust decreases, it is reduced by 30% at most, ensuring that the trust degree is in the range of [0, 1] and can reflect the real security state of the system. Finally, the comprehensive trust degree score and the security report are generated.

[0175] Application example:

[0176] In order to verify the effect of the method of the embodiment, a simulation environment is built based on Python 3.12 platform, a virtual power plant simulation system with a 24-hour operation cycle is designed, a complete trust chain covering data collection, dispatching control and market transaction is constructed, and an attack is carried out on the IEEE30 node network introduced into the trust chain and the standard IEEE30 node network, and a mutual trust calculation analysis method based on mobile agent is used as an evaluation tool.

[0177] Data collection link: the system introduces four types of core equipment, including smart meters, photovoltaic inverters, energy storage converters and load controllers, generates a historical data set covering a two-year time span, and updates every 5 minutes. The edge layer constructs a complete edge computing architecture, including edge gateways supporting Modbus and MQTT protocols, edge computing modules for real-time data analysis, and anomaly detection algorithms and data integrity verification models based on Z-score, ensuring data quality while storing encrypted data in InfluxDB time series database.

[0178] Dispatch control link: The dispatch core uses asynchronous thread mode to pull the latest data from the InfluxDB database every 5 minutes to ensure that the main dispatch process is not blocked. The system uses LSTM neural network and random forest model to predict photovoltaic power generation and load power for 24 hours. The dispatch optimization takes minimizing the grid interaction cost as the objective function, implements the peak-valley electricity price response strategy, and strictly follows the power balance constraint, the energy storage SOC and the charge-discharge power limit, the grid interaction power constraint and other operating constraints. The system finally outputs the energy storage power, grid power, load power and photovoltaic power per hour, generates the basic dispatch plan every hour, and updates it every 5 minutes.

[0179] Transaction platform link: The system constructs a blockchain P2P transaction environment based on the SHA-256 hash algorithm and the proof of work consensus mechanism, and adopts a three-layer architecture of the blockchain interface layer, the market transaction layer and the transaction system core layer. The platform sets a time-of-use electricity price system, with a price of 1.5 yuan / kWh during peak hours of 8-11 and 18-21, a price of 0.8 yuan / kWh during flat hours, and a price of 0.3 yuan / kWh during valley hours of 0-6 and 22-24. The transaction mechanism uses a heap data structure to realize the priority sorting of orders, ensures that the optimal price order is matched first, and triggers the intermediate price matching algorithm when the buy order price is not lower than 90% of the sell order price. The system writes the optimized dispatch plan into the blockchain every 5 minutes, records the complete transaction hash value, timestamp, transaction status and other information, and realizes the credible verification and traceability of the whole transaction process.

[0180] Network attack scenarios: Three network attack scenarios are set up, as shown in Table 1. The Tiny scenario attacks six generator nodes (nodes 1, 2, 5, 8, 11, and 13) in the system, which are the core of the power system and control the power supply of the entire system. The attack complexity is set to low level, and the target data types include basic control commands, system state, and power generation data. The Small scenario attack expands the attack range to the generator nodes plus some key load nodes, and the attack complexity is upgraded to medium level. The target data types include power generation data, protection settings, network topology, and load data. The Medium scenario attack is the most comprehensive attack strategy, targeting all important nodes (including all generator nodes and key load nodes), with an attack complexity of high level, trying to obtain all key data of the system, including measurement data, state estimation, security policy, and backup files. The attack system integrates the NASim network attack simulation environment, uses a brute force proxy for single-round intensive attacks, and performs 200 rounds of continuous attacks in the intensive attack multi-round mode and 150 rounds of intelligent attacks in the adaptive attack multi-round mode. A complete node-device mapping mechanism is established, with generator nodes mapping to power-side device combinations, including photovoltaic inverters, energy storage PCS, and smart meters, and load nodes mapping to important power-side devices, including loads and smart meters, achieving complete conversion from abstract power system nodes to specific industrial devices, to network attack targets, and finally to trust evaluation subjects. Figure 3 The network topology of the IEEE 30-node power system.

[0181] Table 1 Network attack scenario settings

[0182]

[0183] First, two years of historical data are initially generated for photovoltaic power generation and load power consumption prediction. Every five minutes, the real-time generated data is written and updated to the historical data. Table 2 shows the real-time abnormal situation monitoring of the device operation, taking photovoltaic equipment as an example.

[0184] Table 2 Device operation live and abnormal monitoring table

[0185]

[0186] At this time, the sun gradually sets, and the photovoltaic output becomes low, and the energy storage begins to discharge. Here, the temperature change of the photovoltaic power generation equipment is abnormal. Due to the weakening of light, the equipment output decreases, the temperature decreases, and the change amplitude exceeds the specified threshold, triggering an alarm.

[0187] Then, the current time prediction module obtains the prediction of the future 24-hour load and photovoltaic power based on historical data, as well as the dispatching plan of the grid exchange power, electricity price, and battery state of charge, as shown in Figure 2As shown, the photovoltaic and load power forecasts are within a reasonable range, and a reasonable dispatch plan can be generated based on the forecast results. At the same time, the visualized dispatch plan generation can more intuitively show whether the dispatch plan is feasible and whether the system is in normal operation.

[0188] Similarly, the dispatch control module also has monitoring and evaluation functions, and Table 3 shows part of the system monitoring data and the dispatch scheme monitoring table.

[0189] Table 3 System data and dispatch scheme monitoring table

[0190]

[0191] Subsequently, the market transaction module receives the operation results of the dispatch module, generates buy and sell orders according to the dispatch plan, and adds a hash value to each transaction to ensure that transaction records can be queried, ensuring transaction transparency and fairness. Table 4 shows an example of a blockchain transaction record:

[0192] Table 4 Example of blockchain transaction record

[0193]

[0194] Table 5 is an economic benefit analysis of the dispatch plan generated by the dispatch control trusted verification subsystem. Here, the benefits of energy storage arbitrage and virtual power plant direct transactions are also included. As can be seen from the table, after adding energy storage optimization dispatch and transactions, the benefits increased significantly, from the original profit of 737.22 yuan to the profit of 1336.19 yuan.

[0195] Table 5 Economic benefit analysis

[0196]

[0197] Finally, the improvement effect of system credibility in three attack scenarios is tested. After a successful attack, the system will evaluate the number of compromised nodes, the key data leaked, and the security vulnerabilities discovered, and calculate the cascading impact through network topology analysis.

[0198] In this embodiment, first, the initial values of the direct trust value and the recommended trust value are set, such as both being set to 0.5; then updated based on the following formula:

[0199] The recommended trust degree is updated as:

[0200] (44)

[0201] The direct trust degree is updated as:

[0202] (45)

[0203] The comprehensive trust degree is updated as:

[0204] (46)

[0205] in, The recommendation trust update coefficient is used to control the system's sensitivity to third-party recommendation information. The direct trust update coefficient is used to adjust the system's learning speed from direct interactive experiences. The overall trust update coefficient is used to manage the dynamic evolution of the overall trust level. For time frames. Let this be the recommended trust value at time n+1. Let n be the recommended trust observation value at time n; Let be the direct trust value at time n+1. For the direct trust observation at time n; This is the overall trust value at time n+1.

[0206] In this embodiment, the calculation logic for trust level is as follows:

[0207] Set initial values ​​for the recommendation trust score and direct trust score at time n, and the overall trust score at time n-1. The initial values ​​are all 0.5; the subjective trust level and objective trust level at time n are calculated using formulas (39) and (40) respectively; the calculation results are substituted into formula (41) to calculate the comprehensive trust level at time n; and the comprehensive trust level is adjusted using formula (42) to obtain the result. The recommendation trust level is updated using formula (44). The direct trust update is obtained by using formula (45). The overall trust level update is obtained by calculating using formula (45). This process of iterative updating continues until the end.

[0208] To avoid the subjectivity issues of traditional parameter allocation, and to evaluate the rationality of parameter selection and the robustness of results, this embodiment performs sensitivity analysis. In a simulation environment, this embodiment tests the coefficients... , , The impact of different combinations in the range [0.1, 0.9] on the trust score calculation results.

[0209] First, calculate the importance and interaction of the parameters:

[0210] ;

[0211] ;

[0212] ;

[0213] ;

[0214] wherein, is the first order sensitivity index, is the total effect index, is the interaction effect, is the trust score, denotes variance, denotes expectation, denotes all parameters except ; denotes the parameter currently being analyzed, the variable as the main research object in the sensitivity analysis, is a certain parameter except , is used to measure the strength of interaction between two parameters, reflecting the degree of influence of parameter and parameter on the output variable Y together.

[0215] By performing sensitivity analysis and robustness test on the three parameters, the subjective problem of parameter allocation can be avoided, and the result of the credibility calculation is more representative, which can represent the credibility of the virtual power plant of this configuration in this scenario.

[0216] The performance evaluation function calculates the comprehensive score for selecting the optimal parameter combination and calculating the most representative credibility result. Finally, the parameter combination with the highest score is selected to calculate the credibility of the system in this scenario. The performance evaluation function is specifically:

[0217] ;

[0218] wherein, is the comprehensive score, is the stability score, is the robustness score, and represent the weights of stability and robustness respectively, and each baseline weight is set to 0.5, which is adjusted according to the sensitivity analysis result. The adjustment scheme is as follows:

[0219] ;

[0220] ;

[0221] ;

[0222] wherein, , is the baseline weight, is the interaction effect correction factor, is the interaction effect strength between parameters, taking the average of all parameter pairs' interaction, i.e. when performing sensitivity analysis on three update coefficients β(τ), λ(τ), σ(τ), the interaction effect between all possible two-parameter pairs will be calculated, and then the average of all interaction effects is taken. A comprehensive score is obtained by normalization of sensitivity and addition of interaction factor correction.

[0223] The stability score is calculated using the coefficient of variation (CV) and parameter sensitivity:

[0224]

[0225] where the coefficient of variation (CV) is a standardized statistical indicator for measuring the degree of data dispersion (volatility), is the standard deviation of the data, is the average value of the data. For example: when calculating the corresponding trust degree of the generated 1000 groups of parameters, a set of 1000 comprehensive trust degree values will be obtained, and the average value and standard deviation of the set can be calculated to obtain the coefficient of variation. A high CV value means that the trust degree result is very sensitive to parameter changes, and fine-tuning of parameters can cause the trust score to fluctuate greatly, and the system is unstable. A low CV value means that the trust degree result is not sensitive to parameter changes, and even if the parameters change within a certain range, the trust score remains within a stable range, and the system is very stable.

[0226] The robustness score is based on the ratio of parameter change and trust value change:

[0227]

[0228] where, is the change in comprehensive trust degree, i.e. the difference in comprehensive trust degree calculated by different parameter combinations; is the parameter change amount.

[0229] Finally, detect malicious recommenders:

[0230]

[0231] where, represents the recommendation trust value at the current time, represents the direct trust value at the current time; when exceeds the set threshold, the recommendation is marked as malicious, and its recommendation trust weight is reduced to 0.

[0232] ​​​​Through the comprehensive evaluation of system stability and robustness, the complete search space containing 1000 parameter combinations is constructed using Latin hypercube sampling for optimization comparison to find the most representative parameter combination and enhance the persuasiveness of the case study.

[0233] The final comprehensive trust calculation adopts a dynamic weight adjustment mechanism and is finally adjusted by a trust evolution factor to generate a comprehensive trust score and a system security report.

[0234] Figure 4 The results of the comparative analysis of the credibility of the trust chain are shown in the figure. It can be seen that in the three different scale attack scenarios, the trust degree of the system is significantly improved after the introduction of the trust chain mechanism. In the tiny attack scenario, the trust degree is improved from 0.110 to 0.291, with an improvement of 164.2%; in the small attack scenario, the trust degree is greatly improved from 0.264 to 0.829, with an improvement of 213.9%; in the medium attack scenario, the trust degree is improved from 0.372 to 0.847, with an improvement of 127.7%. Overall, the trust chain mechanism has shown good protection effect in all attack scenarios, and the improvement effect of the small scenario is the most prominent, which shows that the proposed trust chain mechanism can effectively enhance the credibility and security of the system in the face of different intensity network attacks.

[0235] Through the virtual power plant aggregation operation trust verification architecture of the embodiment, the virtual power plant can not only realize efficient monitoring and resource optimization configuration of power grid operation, but also ensure the safety, transparency and non-tamperability of information flow through blockchain technology, thereby solving the trust problem between the virtual power plant and the power grid dispatching system and in the power market. Finally, a trust network composed of multiple efficient, safe and transparent virtual power plant trust chains is constructed, which provides solid technical support for the fair competition, intelligent dispatching and reliable operation of the power market, ensures the efficient interaction and stable operation of the power system, and optimizes the problems such as Figure 5 as shown.

[0236] Embodiment Two

[0237] In one or more embodiments, a virtual power plant full-process trusted aggregation system based on hierarchical trust chain is disclosed, comprising:

[0238] The model construction module is configured to construct differentiated hierarchical trust chain models for data acquisition links, dispatching control links and market transaction links based on the feature requirements and trust transmission rules of different business links of the virtual power plant.

[0239] The data collection credible verification module is configured to collect original data of the terminal equipment through the edge gateway at a data collection link, and ensure the credibility of the bottom equipment by combining device identity authentication and data integrity check.

[0240] The scheduling control credible verification module is configured to receive the data stream collected from the edge gateway at a scheduling control link, predict the photovoltaic and load, and generate an optimal scheduling scheme; take minimizing the interaction cost with the power grid as an optimization target, respectively calculate the power balance constraint compliance and the energy balance degree, and then calculate the scheduling scheme credibility to ensure the credibility of the middle layer service;

[0241] The market transaction credible verification module is configured to generate buy and sell orders according to the scheduling scheme at a market transaction link, add a hash value to each transaction, and use a blockchain smart contract verification mechanism to realize the credible execution of the top layer business.

[0242] The collaborative decision-making credibility calculation module is configured to realize the credibility calculation of multi-agent collaborative decision-making through real-time trust evaluation and adaptive weight adjustment.

[0243] In some other embodiments, a terminal device is also disclosed, which includes a processor and a memory, the processor is used to implement instructions; the memory is used to store a plurality of instructions, the instructions are suitable for being loaded and executed by the processor to implement the above-mentioned virtual power plant whole-process credible aggregation method based on the layered trust chain.

[0244] In some other embodiments, a computer readable storage medium is also disclosed, which stores a plurality of instructions, the instructions are suitable for being loaded and executed by the processor of the terminal device to implement the above-mentioned virtual power plant whole-process credible aggregation method based on the layered trust chain.

[0245] The specific implementation process of the above-mentioned module or method is the same as that in the first embodiment, and will not be described in detail.

[0246] The above describes the specific embodiments of the application in combination with the drawings, but is not a limitation on the protection scope of the application. Those skilled in the art should understand that various modifications or changes made on the basis of the technical solutions of the application without creative labor are still within the protection scope of the application.

Claims

1. A virtual power plant full-process trusted aggregation method based on a hierarchical trust chain, characterized in that, The application relates to a trustable virtual power plant, and relates to a trustable virtual power plant and a trustable multi-agent collaborative decision-making method. The application comprises the following steps: Differentiated hierarchical trust chain models of data acquisition, scheduling control and market transaction are respectively constructed based on the characteristic requirements and trust transmission rules of different business links of the virtual power plant; Raw data of terminal equipment is collected through an edge gateway in the data acquisition link, and device identity authentication and data integrity verification are combined to ensure that the bottom layer equipment is reliable; In the scheduling control link, data streams collected from the edge gateway are received, photovoltaic and load are predicted, and an optimal scheduling scheme is generated; The optimization objective is to minimize the interaction cost with the power grid to maximize the virtual power plant revenue; power balance constraint compliance and energy balance are calculated, and then the scheduling scheme reliability is calculated to ensure the reliability of the intermediate layer service; In the market transaction link, buy and sell orders are generated according to the scheduling scheme, and a hash value is added to each transaction; a blockchain smart contract verification mechanism is used to realize the reliable execution of the top layer business; Through real-time trust evaluation and adaptive weight adjustment, the trust degree of multi-agent collaborative decision-making is calculated, specifically: Subjective trust degree is determined based on direct trust value and recommended trust value; Objective trust degree is determined based on attack success rate, security event influence and vulnerability influence; The subjective trust degree and the objective trust degree are weighted and summed to obtain the comprehensive trust degree; wherein the weight coefficient is dynamically adjusted based on the number of interaction history; The comprehensive trust degree is adjusted by a trust evolution factor; the value of the trust evolution factor is determined based on the trust change trend; 2. The virtual power plant full-process trusted aggregation method based on a hierarchical trust chain according to claim 1, characterized in that, TPM is used as a hardware trust root and is set in the central control area of the virtual power plant; a tree structure is used to build a trust chain in the data acquisition link; a star structure is used to build a trust chain in the scheduling control link, so that the center node of the star trust chain can be directly connected with each execution node; a distributed P2P structure is used to build a trust chain in the market transaction link. Device identity authentication and data integrity verification are combined to ensure that the bottom layer equipment is reliable, specifically: Device identity authentication judges whether the device is correctly connected by comparing the device ID; Data integrity verification calculates field integrity score and data length score, and then calculates the average value of the two to obtain the comprehensive integrity score; 3. The virtual power plant full-process trusted aggregation method based on a hierarchical trust chain according to claim 1, characterized in that, The mean and variance of the data sequence in the time window are calculated, then the Z score of each data point is calculated, and whether the data point is an abnormal data point is judged based on the Z score. ； wherein, Pgrid(t) represents the exchange power of the grid at time t, a positive value indicates electricity purchase from the grid, and vice versa; P(t) represents the electricity price of different time periods, which varies according to different peak and valley periods.

4. The virtual power plant full-process trusted aggregation method based on a hierarchical trust chain of claim 1, wherein, The optimization objective is to minimize the interaction cost with the power grid to maximize the virtual power plant revenue, specifically: Power balance constraint compliance is determined based on the ratio of the number of constraint violations to the total number of checks; Energy balance is determined based on the output power of the photovoltaic system at time t, the power exchange of the power grid, the charging and discharging power of the energy storage system and the load demand power; The scheduling scheme reliability is the weighted sum of the power balance constraint compliance and the energy balance.

5. The virtual power plant full-process trusted aggregation method based on a hierarchical trust chain according to claim 1, characterized in that, In the market transaction link, the buy / sell order for transaction is generated by simulating the actual operation process through the order generation model, the buy / sell order is matched by the matching model according to the matching logic, and the transaction is successful if the matching is successful; the profit after the order transaction generated by the scheduling plan is completed is obtained through the profit calculation model.

6. A virtual power plant whole-process trusted aggregation system based on a hierarchical trust chain, characterized in that, The method comprises the following steps: The model construction module is configured to: based on the feature requirements and trust transmission rules of different business links of the virtual power plant, respectively construct the differentiated hierarchical trust chain model of the data acquisition link, the scheduling control link and the market transaction link; The data acquisition credible verification module is configured to: in the data acquisition link, collect the original data of the terminal equipment through the edge gateway, and ensure the credibility of the bottom equipment by combining device identity authentication and data integrity verification; The scheduling control credible verification module is configured to: in the scheduling control link, receive the data stream collected from the edge gateway, predict the photovoltaic and load, and generate the optimal scheduling scheme; taking minimizing the interaction cost with the power grid as the optimization objective, respectively calculating the power balance constraint compliance and the energy balance degree, and then calculating the scheduling scheme credibility to ensure the credibility of the intermediate layer service; The market transaction credible verification module is configured to: in the market transaction link, generate buy / sell orders according to the scheduling scheme, and add a hash value to each transaction; using the blockchain smart contract verification mechanism, the credible execution of the top-level business is realized; The collaborative decision credibility calculation module is configured to: through real-time trust degree evaluation and adaptive weight adjustment, the credibility calculation of multi-agent collaborative decision is realized, specifically: Determine the subjective trust degree based on the direct trust value and the recommended trust value; Determine the objective trust degree based on the attack success rate, the security event influence and the vulnerability influence; The subjective trust degree and the objective trust degree are weighted and summed to obtain the comprehensive trust degree; wherein the weight coefficient is dynamically adjusted based on the number of interaction history; The comprehensive trust degree is adjusted by the trust evolution factor; the value of the trust evolution factor is determined based on the trust change trend; TPM is used as the hardware trust root and set in the central control area of the virtual power plant; the tree structure is used to construct the trust chain in the data acquisition link; the star structure is used to construct the trust chain in the scheduling control link, so that the center node of the star trust chain can establish a direct connection with each execution node; the distributed P2P structure is used to construct the trust chain in the market transaction link. 7.A terminal device comprising a processor and a memory, the processor configured to implement instructions; the memory configured to store a plurality of instructions, and the terminal device is characterized in that, The instructions are suitable for being loaded and executed by the processor to implement the hierarchical trust chain based virtual power plant whole-process credible aggregation method of any one of claims 1-5.

8. A computer-readable storage medium having stored therein a plurality of instructions, wherein the instructions, when executed by a processor, cause the processor to perform operations comprising: The instructions are suitable for being loaded and executed by the processor of the terminal equipment to implement the hierarchical trust chain based virtual power plant whole-process credible aggregation method of any one of claims 1-5.

Images