Comprehensive evaluation method and system for hierarchical optimization scheduling of virtual power plant

Abstract

The invention provides a comprehensive evaluation method and system for hierarchical optimization scheduling of a virtual power plant, and relates to the technical field of smart power grids, and the method comprises the steps: constructing a diversified evaluation index set corresponding to the virtual power plant; constructing a hierarchical optimization model corresponding to the virtual power plant and formulating a plurality of hierarchical optimization scheduling strategies; constructing a comprehensive evaluation model, calculating a comprehensive index score of each hierarchical optimization scheduling strategy based on the diversified evaluation index set, and determining a target hierarchical optimization scheduling strategy by comparing the comprehensive index scores; and the target hierarchical optimization scheduling strategy is adjusted based on an intelligent scheduling algorithm, so that balanced optimization of economic benefits, environmental protection influences and social benefits can be realized, the overall benefits of different scheduling strategies are comprehensively evaluated, and the calculation efficiency and robustness of the comprehensive evaluation method are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and particularly to a comprehensive evaluation method, system, electronic device and storage medium for hierarchical optimization scheduling of virtual power plants. Background Art

[0002] With the widespread access of distributed power sources, virtual power plants play an important role in improving the flexibility and economy of power systems. However, the operating characteristics of virtual power plants are complex, and their optimization scheduling is a multi-objective and multi-level problem, which requires comprehensive consideration of factors such as economic benefits, environmental protection indicators and social welfare.

[0003] Existing virtual power plant optimization scheduling methods usually focus on the optimization of a single objective function, such as minimizing cost or maximizing revenue, and cannot comprehensively evaluate the effects of different scheduling strategies. Therefore, it is impossible to achieve the balanced optimization of resource utilization and overall benefits, and it is difficult to meet the diversified needs of the modern power market.

[0004] Therefore, it is necessary to provide a comprehensive evaluation method, system, electronic device and storage medium for hierarchical optimization scheduling of virtual power plants to solve the above technical problems. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a comprehensive evaluation method, system, electronic device and storage medium for hierarchical optimization scheduling of virtual power plants, which are used to solve the problems that the existing virtual power plant scheduling methods are difficult to achieve the balanced optimization of economic benefits, environmental impacts and social benefits, lack an effective evaluation framework to quantitatively analyze the overall benefits of different scheduling strategies, and the calculation efficiency and robustness of the method need to be improved when facing complex operating conditions of virtual power plants.

[0006] The comprehensive evaluation method for hierarchical optimization scheduling of virtual power plants of the present invention includes: Constructing a diversified evaluation index set corresponding to the virtual power plant; Constructing a hierarchical optimization model corresponding to the virtual power plant and formulating multiple hierarchical optimization scheduling strategies; Constructing a comprehensive evaluation model and calculating the comprehensive index scores of each hierarchical optimization scheduling strategy based on the diversified evaluation index set, and determining the target hierarchical optimization scheduling strategy by comparing each comprehensive index score; Adjusting the target hierarchical optimization scheduling strategy based on an intelligent scheduling algorithm.

[0007] Preferably, the diversified evaluation index set includes a cost index, an emission index and a power index.

[0008] Preferably, the hierarchical optimization model includes a high-level scheduling model and a low-level scheduling model; Based on the high-level scheduling model, according to the cost index and the emission index, combined with the real-time power generation power of the power generation units of the virtual power plant, formulate a high-level scheduling strategy; Based on the low-level scheduling model, according to the electricity quantity index, combined with the real-time electricity price of the virtual power plant, formulate a low-level scheduling strategy; Based on the high-low level interaction mechanism, coordinate the high-level scheduling strategy and the low-level scheduling strategy through a data interaction channel to obtain the hierarchical optimal scheduling strategy.

[0009] Preferably, the step of formulating a high-level scheduling strategy based on the high-level scheduling model, according to the cost index and the emission index, and combined with the real-time power generation power of the power generation units of the virtual power plant, specifically includes: Based on the high-level scheduling model, construct a high-level scheduling objective function according to the cost index and the emission index, and the corresponding calculation formula is as follows: In the formula, Z represents the high-level scheduling target value; represents the weight parameter corresponding to the cost index; C represents the cost index; R represents the emission index; I represents the number of types of costs; represents the i-th type of cost; J represents the number of types of emissions; represents the emission amount of the j-th type of emission; min represents the operation of taking the minimum value; Construct the power generation power constraint condition corresponding to the real-time power generation power, and the corresponding calculation formula is as follows: In the formula, represents the real-time power generation power of the m-th power generation unit of the virtual power plant; respectively represent the preset lower limit and upper limit of the power generation power of the m-th power generation unit of the virtual power plant; M represents the total number of power generation units of the virtual power plant; Q represents the real-time power load demand of the virtual power plant; When the high-level scheduling target value is the smallest and the real-time power generation power satisfies the power generation power constraint condition, determine the corresponding cost index, emission index and real-time power generation power, and formulate the high-level scheduling strategy.

[0010] Preferably, the step of formulating a low-level scheduling strategy based on the low-level scheduling model, according to the electricity quantity index, and combined with the real-time electricity price of the virtual power plant, specifically includes: Based on the low-level scheduling model, construct a low-level scheduling objective function and the corresponding power balance constraint condition according to the electricity quantity index and the real-time electricity price, and the corresponding calculation formula is as follows: In the formula, FX represents the short-term trading risk value, that is, the low-level scheduling target value; L represents the number of scheduling periods; Represents the power generation at time l; Represents the discharge at time l; Represents the real-time electricity price at time l; min represents the minimum value operation; When the low-level scheduling target value is the smallest and the low-level scheduling target function satisfies the power balance constraint condition, determine the corresponding electricity quantity index and the real-time electricity price, and formulate the low-level scheduling strategy.

[0011] Preferably, constructing a comprehensive evaluation model and calculating the comprehensive index score of each hierarchical optimization scheduling strategy based on the diversified evaluation index set, and determining the target hierarchical optimization scheduling strategy by comparing each comprehensive index score, specifically including: Set the evaluation index matrix corresponding to the diversified evaluation index set as , where Represents the importance degree of the u-th evaluation index relative to the v-th evaluation index, and , , ; Obtain the maximum eigenvalue of the evaluation index matrix ZBJZ, and the maximum eigenvalue satisfies the following equation: In the formula, ZBJZ represents the evaluation index matrix; W represents the eigenvector corresponding to the evaluation index matrix; Represents the maximum eigenvalue; Solve the above equation to obtain the eigenvector W, perform normalization processing on the eigenvector W to obtain the weight vector corresponding to each evaluation index, and the sum of the weight vectors corresponding to all evaluation indexes in the diversified evaluation index set is 1; Obtain the independent index score of the u-th evaluation index under the k-th hierarchical optimization scheduling strategy, and combine with the weight vector corresponding to the u-th evaluation index to calculate the comprehensive index score of the k-th hierarchical optimization scheduling strategy as follows: In the formula, Represents the comprehensive index score of the k-th hierarchical optimization scheduling strategy; Represents the weight vector corresponding to the u-th evaluation index; Represents the independent index score of the u-th evaluation index under the k-th hierarchical optimization scheduling strategy; If the comprehensive index score of the -th hierarchical optimization scheduling strategy is the largest, then the -th hierarchical optimization scheduling strategy is the target hierarchical optimization scheduling strategy.

[0012] Preferably, adjusting the target hierarchical optimization scheduling strategy based on the intelligent scheduling algorithm specifically includes: Constructing a scheduling operation prediction model based on the intelligent scheduling algorithm, obtaining the current scheduling status information of the virtual power plant and inputting it into the scheduling operation prediction model to obtain a scheduling operation instruction. The corresponding calculation formula is as follows: In the formula, represents the f-th neuron in the middle layer of the scheduling operation prediction model; represents the activation function; E represents the number of neurons in the input layer of the scheduling operation prediction model; represents the connection weight between the e-th neuron in the input layer and the f-th neuron in the middle layer of the scheduling operation prediction model; represents the input of the e-th neuron in the input layer of the scheduling operation prediction model, that is, the e-th current scheduling status information; represents the bias of the f-th neuron in the middle layer of the scheduling operation prediction model; represents the output of the output layer of the scheduling operation prediction model, that is, the scheduling operation instruction; F represents the number of neurons in the middle layer of the scheduling operation prediction model; represents the connection weight between the f-th neuron in the middle layer and the output layer of the scheduling operation prediction model; represents the bias of the output layer of the scheduling operation prediction model; Adjusting the target hierarchical optimization scheduling strategy according to the scheduling operation instruction.

[0013] The comprehensive evaluation system for hierarchical optimization scheduling of the virtual power plant of the present invention includes: An index construction model for constructing a diversified evaluation index set corresponding to the virtual power plant; A strategy formulation module for constructing a hierarchical optimization model corresponding to the virtual power plant and formulating multiple hierarchical optimization scheduling strategies; A strategy comparison module for constructing a comprehensive evaluation model and calculating the comprehensive index scores of each hierarchical optimization scheduling strategy based on the diversified evaluation index set, and determining the target hierarchical optimization scheduling strategy by comparing each comprehensive index score; A strategy adjustment module for adjusting the target hierarchical optimization scheduling strategy based on the intelligent scheduling algorithm.

[0014] An electronic device includes a memory and a processor. A computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes the steps of the comprehensive evaluation method for hierarchical optimization scheduling of the virtual power plant as described in any one of the above.

[0015] A readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the steps of the comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant as described in any one of the above.

[0016] Compared with the related technologies, the comprehensive evaluation method, system, electronic device and storage medium for hierarchical optimization scheduling of a virtual power plant provided by the present invention have the following beneficial effects: The present invention can construct a diversified evaluation index set corresponding to the virtual power plant; construct a hierarchical optimization model corresponding to the virtual power plant and formulate multiple hierarchical optimization scheduling strategies; construct a comprehensive evaluation model and calculate the comprehensive index scores of each hierarchical optimization scheduling strategy based on the diversified evaluation index set, and determine the target hierarchical optimization scheduling strategy by comparing each comprehensive index score; adjust the target hierarchical optimization scheduling strategy based on the intelligent scheduling algorithm, so as to achieve the balanced optimization of economic benefits, environmental impacts and social benefits, comprehensively evaluate the overall benefits of different scheduling strategies, and improve the calculation efficiency and robustness of the comprehensive evaluation method.

[0017] Through the hierarchical optimization model, the present invention can formulate multiple hierarchical optimization scheduling strategies, thereby improving the resource utilization efficiency, ensuring the balance of overall benefits, and significantly reducing the operating costs of the virtual power plant; through the comprehensive evaluation model, the present invention can comprehensively evaluate the overall benefits of different scheduling strategies based on multiple evaluation indexes, significantly improving the decision-making transparency and fairness; by introducing the intelligent scheduling algorithm, the present invention can optimize and adjust the scheduling strategy, improve the calculation efficiency and robustness of the comprehensive evaluation method, enhance the stability and intelligent level of the comprehensive evaluation system, and thus achieve the efficient utilization of resources and the balanced optimization of overall benefits, meeting the diversified needs of the modern power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of the comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of data transmission in a data interaction channel provided by an embodiment of the present invention; Figure 3 It is a system block diagram of the comprehensive evaluation system for hierarchical optimization scheduling of a virtual power plant provided by an embodiment of the present invention; Figure 4 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0020] As Figure 1 shown, it is a flowchart of a comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant provided by an embodiment of the present invention. Figure 1 The execution subject of the method shown can be a software and / or hardware device. The execution subject of the present application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. Among them, the user equipment can include, but is not limited to, a computer, a smart phone, a personal digital assistant (Personal Digital Assistant, abbreviated as: PDA), and the above-mentioned electronic devices, etc. The network equipment can include, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of computers or network servers based on cloud computing. Among them, cloud computing is a type of distributed computing, which is composed of a group of loosely coupled computers to form a super virtual computer. This embodiment does not make any restrictions on this. It includes steps S1 to S4, specifically as follows: S1, construct a diversified evaluation index set corresponding to the virtual power plant; Among them, a comprehensive evaluation index system, that is, a diversified evaluation index set, can be constructed from multiple dimensions such as the economic benefits, environmental impacts, and social benefits of the virtual power plant.

[0021] For example, the economic benefit dimension involves aspects such as power generation cost and operation cost, which are used to measure the economic feasibility of the scheduling strategy of the virtual power plant; the environmental impact dimension involves aspects such as pollutant emissions, which are used to evaluate the impact degree of the virtual power plant on the environment; the social benefit dimension includes aspects such as power generation and power consumption, which are used to ensure the power stability of the virtual power plant.

[0022] S2, construct a hierarchical optimization model corresponding to the virtual power plant and formulate multiple hierarchical optimization scheduling strategies; It should be noted that the hierarchical optimization model includes a high-level scheduling model and a low-level scheduling model. The high-level scheduling model is used to formulate an overall strategy plan, such as a long-term power generation plan, etc., according to the cost, emissions, and power generation power of the power generation units of the virtual power plant to balance the cost and carbon emissions of the virtual power plant. The low-level scheduling model is used to minimize the short-term trading risk and maintain power balance according to the power situation and real-time electricity price of the virtual power plant. Through this hierarchical mode, a variety of different hierarchical optimization scheduling strategies can be formulated.

[0023] S3. Construct a comprehensive evaluation model and calculate the comprehensive index scores of each of the hierarchical optimization scheduling strategies based on the diversified evaluation index set, and determine the target hierarchical optimization scheduling strategy by comparing each of the comprehensive index scores; Among them, the weight vector of each evaluation index can be calculated in combination with the evaluation index matrix of the diversified evaluation index set.

[0024] Further, the analytic hierarchy process can be used to construct a comprehensive evaluation model, and the comprehensive index scores of each hierarchical optimization scheduling strategy can be quantified based on the diversified evaluation index set. By comparing these comprehensive index scores, the hierarchical optimization scheduling strategy with the highest comprehensive index score can be determined, that is, the target hierarchical optimization scheduling strategy.

[0025] S4. Adjust the target hierarchical optimization scheduling strategy based on the intelligent scheduling algorithm.

[0026] In practical applications, the input layer of the intelligent scheduling algorithm can receive the current state information of the virtual power plant. The middle layer can use multi-layer perceptron technology to perform non-linear transformation on the output of the input layer to extract deep features, and its output layer can output the final scheduling operation instructions.

[0027] In the above way, the target hierarchical optimization scheduling strategy can be adjusted to improve the scheduling efficiency and robustness of the strategy, so that it can better adapt to complex working conditions.

[0028] In the specific implementation process, the diversified evaluation index set includes cost indicators, emission indicators, and power quantity indicators.

[0029] Among them, the cost indicator is an indicator used to measure the economic operation status of the virtual power plant, which covers the power generation cost, that is, the costs such as fuel, equipment loss, and manpower invested in the power generation process, and the operation cost, that is, the costs such as equipment maintenance and management fees. By considering the cost indicator, the feasibility of the scheduling strategy at the economic level can be intuitively judged, and while ensuring power supply, the cost can be reasonably controlled and the economic benefits can be improved.

[0030] The emission indicator is an indicator used to measure the environmental impact of the virtual power plant, which mainly involves the emissions of various pollutants, such as carbon dioxide, sulfur dioxide, etc. This indicator can clearly reflect the environmental impact of the power plant under different scheduling strategies.

[0031] The power quantity indicator is an indicator used to measure the power supply and distribution of the virtual power plant, which mainly includes indicators such as power generation and power consumption. Power generation can reflect the production capacity of the power plant, and power consumption reflects market demand. Based on the power quantity indicator, the power supply and demand dynamics can be monitored in real time, and then the power balance can be ensured and the power supply reliability can be guaranteed.

[0032] It should be noted that these three evaluation indicators are interrelated and provide a comprehensive and accurate basis for evaluating the dispatching strategy of the virtual power plant from multiple dimensions such as economy, environment, and power supply.

[0033] The hierarchical optimization model includes a high-level dispatching model and a low-level dispatching model; Based on the high-level dispatching model, according to the cost index and the emission index, combined with the real-time power generation power of the power generation units of the virtual power plant, a high-level dispatching strategy is formulated; Based on the low-level dispatching model, according to the power quantity index, combined with the real-time electricity price of the virtual power plant, a low-level dispatching strategy is formulated; Based on the high-low level interaction mechanism, the high-level dispatching strategy and the low-level dispatching strategy are coordinated through a data interaction channel to obtain the hierarchical optimization dispatching strategy.

[0034] Among them, through the high-level dispatching model, according to the cost index and the emission index, combined with the real-time power generation power of the power generation units of the virtual power plant, the cost and carbon emissions can be balanced from a macro level, and then the optimal allocation of overall resources can be realized.

[0035] Furthermore, through the low-level dispatching model, based on the power quantity index, combined with the real-time electricity price, the short-term trading risk can be reduced and the power balance can be maintained, and a low-level dispatching strategy suitable for the real-time working conditions can be formulated.

[0036] It should be noted that the high-low level interaction mechanism refers to the mechanism of coordinating the high-level and low-level dispatching strategies by using a data interaction channel. As Figure 2 shown, it is a schematic diagram of data transmission in the data interaction channel provided by the embodiment of the present invention. The high-level dispatching model can transmit the high-level dispatching strategy to the low-level dispatching model through the data interaction channel, while the low-level dispatching model can feedback the low-level dispatching strategy to the high-level dispatching model through the data interaction channel.

[0037] Through this interaction mechanism, the mutual cooperation of the upper and lower layer strategies can be ensured, and finally a comprehensive and coordinated hierarchical optimization dispatching strategy can be obtained, ensuring the efficient and stable operation of the virtual power plant.

[0038] The step of formulating a high-level dispatching strategy based on the high-level dispatching model, according to the cost index and the emission index, combined with the real-time power generation power of the power generation units of the virtual power plant, specifically includes: Based on the high-level dispatching model, a high-level dispatching objective function is constructed according to the cost index and the emission index, and the corresponding calculation formula is as follows: In the formula, Z represents the high-level dispatching target value; denote the weight parameters corresponding to the cost indicators; C denotes the cost indicator; R denotes the emission indicator; I denotes the number of types of costs; denote the i-th type of cost; J denotes the number of types of emissions; denote the emissions of the j-th type of emission; min denotes the operation of taking the minimum value; Construct the power generation power constraint condition corresponding to the real-time power generation power, and the corresponding calculation formula is as follows: In the formula, denote the real-time power generation power of the m-th power generation unit of the virtual power plant; respectively denote the preset lower limit of the power generation power and the preset upper limit of the power generation power of the m-th power generation unit of the virtual power plant; M denotes the total number of power generation units of the virtual power plant; Q denotes the real-time power load demand of the virtual power plant; When the high-level scheduling target value is the smallest and the real-time power generation power satisfies the power generation power constraint condition, determine the corresponding cost indicator, emission indicator and real-time power generation power, and formulate the high-level scheduling strategy.

[0039] In practical applications, based on the cost indicator and the emission indicator, comprehensively consider the economic and environmental factors, and minimize the target value of the high-level scheduling objective function.

[0040] In addition, the real-time power generation power of the power generation unit needs to satisfy the power generation power constraint condition, that is, the real-time power generation power of each power generation unit needs to be between the preset lower limit of the power generation power and the preset upper limit of the power generation power, and the sum of the power generation powers of all power generation units needs to satisfy the real-time power load demand of the virtual power plant.

[0041] When the high-level scheduling target value reaches the minimum value and the real-time power generation power satisfies the power generation power constraint condition, the corresponding cost indicator, emission indicator and real-time power generation power are in the ideal state. Further, the high-level scheduling strategy can be formulated according to these data, so as to achieve the balance of cost and carbon emissions.

[0042] Based on the low-level scheduling model, according to the electricity quantity indicator, combined with the real-time electricity price of the virtual power plant, formulate the low-level scheduling strategy, which specifically includes: Based on the low-level scheduling model, according to the electricity quantity indicator and the real-time electricity price, construct the low-level scheduling objective function and the corresponding power balance constraint condition, and the corresponding calculation formula is as follows: In the formula, FX represents the short-term trading risk value, that is, the low-level scheduling target value; L represents the number of scheduling periods; denote the power generation quantity at time l; denote the discharge quantity at time l; represents the real-time electricity price at time l; min represents the operation of taking the minimum value; When the low-level scheduling target value is the smallest and the low-level scheduling target function satisfies the power balance constraint condition, determine the corresponding electricity quantity index and the real-time electricity price, and formulate the low-level scheduling strategy.

[0043] In different scheduling periods, by analyzing the relationship between the power generation, the discharge amount and the real-time electricity price, a low-level scheduling target function can be constructed to minimize the low-level scheduling target value, where the low-level scheduling target value is the short-term trading risk value.

[0044] When the low-level scheduling target value is the smallest and the low-level scheduling target function satisfies the power balance constraint condition, the low-level scheduling strategy can be formulated based on the corresponding electricity quantity index and the real-time electricity price, thereby reducing the short-term trading risk and maintaining the power balance.

[0045] By formulating the above hierarchical scheduling strategy, the virtual power plant can achieve the optimal allocation of resources and efficient operation at different levels.

[0046] In practical applications, by adjusting the weight parameters corresponding to the cost indicators, as well as the number of statistical cost types, the number of emission types and the number of scheduling periods, multiple hierarchical optimal scheduling strategies can be obtained.

[0047] Constructing the comprehensive evaluation model and calculating the comprehensive index score of each hierarchical optimal scheduling strategy based on the diversified evaluation index set, and determining the target hierarchical optimal scheduling strategy by comparing each comprehensive index score, specifically including: Set the evaluation index matrix corresponding to the diversified evaluation index set as , where represents the importance degree of the u-th evaluation index relative to the v-th evaluation index, and , , ; Obtain the maximum eigenvalue of the evaluation index matrix ZBJZ, and the maximum eigenvalue satisfies the following equation: In the formula, ZBJZ represents the evaluation index matrix; W represents the eigenvector corresponding to the evaluation index matrix; represents the maximum eigenvalue; Solve the above equation to obtain the eigenvector W, and perform normalization processing on the eigenvector W to obtain the weight vector corresponding to each evaluation index, and the sum of the weight vectors corresponding to all evaluation indexes in the diversified evaluation index set is 1; Obtain the independent index score of the u-th evaluation index under the k-th hierarchical optimal scheduling strategy , combined with the weight vector corresponding to the \(u\)-th evaluation index, the comprehensive index score of the \(k\)-th hierarchical optimization scheduling strategy is calculated as follows: In the formula, represents the comprehensive index score of the \(k\)-th hierarchical optimization scheduling strategy; represents the weight vector corresponding to the \(u\)-th evaluation index; represents the independent index score of the \(u\)-th evaluation index under the \(k\)-th hierarchical optimization scheduling strategy; If the comprehensive index score of the -th hierarchical optimization scheduling strategy is the largest, then the -th hierarchical optimization scheduling strategy is the target hierarchical optimization scheduling strategy.

[0048] Among them, the elements in the evaluation index matrix corresponding to the diversified evaluation index set represent the relative importance between different evaluation indexes. For example, the importance degree of the cost index compared with the power quantity index, etc. These importance degrees are determined through expert scoring or other evaluation methods.

[0049] Furthermore, the maximum eigenvalue of the evaluation index matrix can be obtained, and then the relationship equation between the evaluation index matrix, the eigenvector and the maximum eigenvalue can be constructed. By solving this equation, the value of the eigenvector can be obtained. After normalizing it, the weight vector corresponding to each evaluation index can be obtained. And the sum of the weight vectors corresponding to all evaluation indexes is 1, and each weight vector can accurately reflect the relative importance of the corresponding evaluation index.

[0050] Then, the independent index score of each evaluation index under each hierarchical optimization scheduling strategy can be obtained, and combined with the weight vector of each evaluation index, the comprehensive index score of each hierarchical optimization scheduling strategy can be calculated.

[0051] Finally, the comprehensive index scores of all hierarchical optimization scheduling strategies can be compared, and the hierarchical optimization scheduling strategy with the highest comprehensive index score is the target hierarchical optimization scheduling strategy, that is, the optimization scheduling scheme with the best comprehensive performance.

[0052] Adjusting the target hierarchical optimization scheduling strategy based on the intelligent scheduling algorithm specifically includes: Based on the intelligent scheduling algorithm, a scheduling operation prediction model is constructed, and the current scheduling state information of the virtual power plant is obtained and input into the scheduling operation prediction model to obtain a scheduling operation instruction. The corresponding calculation formula is as follows: In the formula, represents the \(f\)-th neuron in the middle layer of the scheduling operation prediction model; represents an activation function; E represents the number of neurons in the input layer of the scheduling operation prediction model; represents the connection weight between the e-th neuron in the input layer and the f-th neuron in the middle layer of the scheduling operation prediction model; represents the input of the e-th neuron in the input layer of the scheduling operation prediction model, that is, the e-th current scheduling state information; represents the bias of the f-th neuron in the middle layer of the scheduling operation prediction model; represents the output of the output layer of the scheduling operation prediction model, that is, the scheduling operation instruction; F represents the number of neurons in the middle layer of the scheduling operation prediction model; represents the connection weight between the f-th neuron in the middle layer and the output layer of the scheduling operation prediction model; represents the bias of the output layer of the scheduling operation prediction model; Adjust the target hierarchical optimization scheduling strategy according to the scheduling operation instruction.

[0053] It can be understood that the scheduling operation prediction model is composed of an input layer, a middle layer, and an output layer, and is used to adjust the target hierarchical optimization scheduling strategy.

[0054] First, the current scheduling state information of the virtual power plant can be collected, such as the electricity inventory situation, real-time electricity price fluctuations, real-time power generation power of each power generation unit, etc. Then, this information can be input into the input layer of the scheduling operation prediction model. Among them, each neuron in the input layer corresponds to a current scheduling state information.

[0055] The neurons in the middle layer of the model can process the information transmitted from the input layer and extract the deep features therein. The output layer can receive the information processed by the middle layer and process it to obtain the final scheduling operation instruction. These instructions include the indication of specific operations such as power generation adjustment and energy storage charge and discharge rate adjustment.

[0056] Finally, the target hierarchical optimization scheduling strategy can be adjusted accordingly according to the scheduling operation instruction, so that the scheduling operation of the virtual power plant can adapt to the real-time operating conditions, and then the efficiency and robustness of the scheduling operation can be improved, and a better operating effect can be achieved.

[0057] Such as Figure 3 shown, is the system block diagram of the comprehensive evaluation system for hierarchical optimization scheduling of the virtual power plant provided by the embodiment of the present invention. The comprehensive evaluation system includes: An index construction model for constructing a diversified evaluation index set corresponding to the virtual power plant; A strategy formulation module for constructing the corresponding hierarchical optimization model of the virtual power plant and formulating multiple hierarchical optimization scheduling strategies; A strategy comparison module, configured to build a comprehensive evaluation model and calculate the comprehensive index scores of each of the hierarchical optimization scheduling strategies based on the diversified evaluation index set, and determine the target hierarchical optimization scheduling strategy by comparing each of the comprehensive index scores; A strategy adjustment module, configured to adjust the target hierarchical optimization scheduling strategy based on an intelligent scheduling algorithm.

[0058] Figure 3 The device in the illustrated embodiment can correspondingly be used to execute Figure 1 the steps in the method embodiment shown, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0059] An electronic device includes a memory and a processor. A computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes the steps of the comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant as described in any one of the above.

[0060] As Figure 4 shown, it is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present invention. The electronic device 40 includes: a processor 41, a memory 42, and a computer program; wherein The memory 42 is used to store the computer program, and the memory can also be a flash memory. The computer program is, for example, an application program, a functional module, etc. for implementing the above method.

[0061] The processor 41 is used to execute the computer program stored in the memory to implement each step executed by the device in the above method. Specifically, reference can be made to the relevant descriptions in the foregoing method embodiments.

[0062] Optionally, the memory 42 can be either independent or integrated with the processor 41.

[0063] When the memory 42 is a device independent of the processor 41, the device may further include: A bus 43, used to connect the memory 42 and the processor 41.

[0064] A readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the steps of the comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant as described in any one of the above.

[0065] Among them, the readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium accessible by a general or special-purpose computer. For example, the readable storage medium is coupled to the processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). Additionally, the ASIC can be located in the user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in the communication device. The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0066] The present invention also provides a program product, which includes execution instructions stored in a readable storage medium. At least one processor of the device can read the execution instructions from the readable storage medium, and the execution of the execution instructions by at least one processor enables the device to implement the methods provided by the above various embodiments.

[0067] In the above embodiments of the device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the present invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0068] Exemplarily, assume that a virtual power plant is established in a large industrial park, and the virtual power plant realizes efficient dispatching management by applying the integrated dispatching method of the present invention.

[0069] When constructing a diversified evaluation index system, the unique nature of industrial parks needs to be fully considered. For cost indicators, the cost of power generation covers the direct inputs of raw materials, manpower, etc. for power generation of various types of energy. The cost of purchasing electricity reflects the cost of purchasing electricity from the external power grid, and the cost of equipment depreciation reflects the economic impact of equipment loss in long-term operation. For emission indicators, the focus is on the emissions of carbon dioxide and nitrogen oxides, which have a significant impact on air quality and environmental sustainability. The power indicators pay more attention to the real-time power situation of enterprises in the park, which directly affects the stability of the production and operation of enterprises. In order to obtain these key data, an efficient data docking mechanism can be established to interact with the energy management system of the park in real time to exchange energy production and consumption data, obtain pollutant emission data from environmental monitoring equipment, and obtain power-related information from the power supply system to ensure the real-time and accuracy of the data.

[0070] In the process of building a hierarchical optimization model, the high-level scheduling model can deeply integrate the historical electricity consumption data accumulated in the park for a long time, and formulate a one-week power generation plan based on the electricity price forecast and accurate weather forecast information for the next week. For example, during the daytime when the electricity price is low and the light resources are abundant, the distributed photovoltaic power station can be reasonably arranged to generate power at full load, which not only reduces the power generation cost, but also reduces carbon emissions, and improves economic and environmental benefits.

[0071] The low-level dispatch model manages the output of distributed energy in a refined manner based on real-time electricity price fluctuations and the dynamically changing electricity demand in various areas of the park. For example, when the electricity load in a certain area suddenly increases due to increased production activities, the model can quickly adjust the discharge process of nearby energy storage equipment to ensure the stability of power supply and effectively reduce short-term trading risks.

[0072] In addition, the weight vector of each evaluation index can be determined with the help of the hierarchical analysis method, and the scores of various evaluation indicators of the virtual power plant under different scheduling strategies can be comprehensively collected, and then the comprehensive scores of each scheduling strategy can be obtained through the comprehensive evaluation model. By comparing the comprehensive scores of different strategies, the best scheduling strategy can be screened out and fed back to the operation and management personnel of the virtual power plant in a timely manner, providing strong support for scientific decision-making.

[0073] When designing an intelligent scheduling algorithm, a powerful neural network model can be built. Specifically, through the input nodes of the model, multi-dimensional information such as power inventory, real-time electricity price, and the status of various distributed energy devices can be widely received. The middle layer of the model can use multi-layer perceptron technology for complex non-linear transformation, and then deeply analyze the key features of the data. Finally, the output layer of the model outputs the power generation adjustment instructions for each distributed energy and the charge-discharge rate adjustment instructions for energy storage devices, and then the scheduling strategy can be adjusted to enable it to quickly and accurately respond to various complex operating conditions, significantly improving the scheduling efficiency and robustness of the virtual power plant, and ensuring the efficient and stable operation of the virtual power plant.

[0074] Through the introduction of the above embodiments, the present invention can construct a diversified evaluation index set corresponding to the virtual power plant through the comprehensive evaluation method, system, electronic device and storage medium for hierarchical optimization scheduling of the virtual power plant; construct a hierarchical optimization model corresponding to the virtual power plant and formulate multiple hierarchical optimization scheduling strategies; construct a comprehensive evaluation model and calculate the comprehensive index scores of each hierarchical optimization scheduling strategy based on the diversified evaluation index set, and determine the target hierarchical optimization scheduling strategy by comparing each comprehensive index score; adjust the target hierarchical optimization scheduling strategy based on the intelligent scheduling algorithm, so as to achieve the balanced optimization of economic benefits, environmental impacts and social benefits, comprehensively evaluate the overall benefits of different scheduling strategies, and improve the calculation efficiency and robustness of the comprehensive evaluation method.

[0075] Through the hierarchical optimization model of the present invention, multiple hierarchical optimization scheduling strategies can be formulated, thereby improving the resource utilization efficiency, ensuring the balance of overall benefits, and significantly reducing the operating costs of the virtual power plant; through the comprehensive evaluation model of the present invention, the overall benefits of different scheduling strategies can be comprehensively evaluated based on multiple evaluation indicators, significantly improving the decision-making transparency and fairness; through the introduction of the intelligent scheduling algorithm, the present invention can optimize and adjust the scheduling strategy, improve the calculation efficiency and robustness of the comprehensive evaluation method, enhance the stability and intelligent level of the comprehensive evaluation system, and then achieve the efficient utilization of resources and the balanced optimization of overall benefits, meeting the diversified needs of the modern power market.

[0076] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the process Figure 1means for the functions specified in one or more processes and / or blocks Figure 1 or in one or more blocks.

[0077] Those of ordinary skill in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium, which includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memory, magnetic disc memory, tape memory, or any other medium that can be used to carry or store data and is computer-readable.

[0078] It should also be noted that the term "comprises", "comprising", or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a series of elements includes not only those elements but also other elements not expressly listed, or elements that are inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

Claims

1. A comprehensive evaluation method for hierarchical optimal scheduling of virtual power plants, characterized in that Including: Constructing a diversified evaluation index set corresponding to the virtual power plant; Constructing a hierarchical optimization model corresponding to the virtual power plant and formulating multiple hierarchical optimal dispatching strategies; Constructing a comprehensive evaluation model and calculating the comprehensive index scores of each hierarchical optimal dispatching strategy based on the diversified evaluation index set, and determining the target hierarchical optimal dispatching strategy by comparing each comprehensive index score; Adjusting the target hierarchical optimal dispatching strategy based on an intelligent dispatching algorithm.

2. The comprehensive evaluation method for hierarchical optimal scheduling of a virtual power plant according to claim 1, characterized in that The diversified evaluation index set includes a cost index, an emission index, and a power quantity index.

3. The comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant according to claim 2, characterized in that The hierarchical optimization model includes a high-level dispatching model and a low-level dispatching model; Based on the high-level dispatching model, according to the cost index and the emission index, combined with the real-time power generation power of the power generation units of the virtual power plant, formulating a high-level dispatching strategy; Based on the low-level dispatching model, according to the power quantity index, combined with the real-time electricity price of the virtual power plant, formulating a low-level dispatching strategy; Based on the high-low level interaction mechanism, coordinating the high-level dispatching strategy and the low-level dispatching strategy through a data interaction channel to obtain the hierarchical optimal dispatching strategy.

4. The comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant according to claim 3, wherein The formulating of the high-level dispatching strategy based on the high-level dispatching model, according to the cost index and the emission index, combined with the real-time power generation power of the power generation units of the virtual power plant, specifically includes: Based on the high-level dispatching model, constructing a high-level dispatching objective function according to the cost index and the emission index, and the corresponding calculation formula is as follows: Wherein, Z represents the high-level scheduling target value; represents the weight parameter corresponding to the cost index; C represents the cost index; R represents the emission index; I represents the number of cost types; represents the i-th type of cost; J represents the number of emission types; represents the emission amount of the j-th type of emission; min represents the operation of taking the minimum value; Constructing a power generation power constraint condition corresponding to the real-time power generation power, and the corresponding calculation formula is as follows: In the formula, represents the real-time power generation of the m-th power generation unit of the virtual power plant; respectively represent the preset lower limit and upper limit of the power generation of the m-th power generation unit of the virtual power plant; M represents the total number of power generation units of the virtual power plant; Q represents the real-time power load demand of the virtual power plant; When the high-level dispatching target value is the smallest and the real-time power generation power meets the power generation power constraint condition, determining the corresponding cost index, emission index, and real-time power generation power, and formulating the high-level dispatching strategy.

5. The comprehensive evaluation method for hierarchical optimal scheduling of a virtual power plant according to claim 3, wherein The formulating of the low-level dispatching strategy based on the low-level dispatching model, according to the power quantity index, combined with the real-time electricity price of the virtual power plant, specifically includes: Based on the low-level dispatching model, constructing a low-level dispatching objective function and the corresponding power balance constraint condition according to the power quantity index and the real-time electricity price, and the corresponding calculation formula is as follows: In the formula, FX represents the short-term trading risk value, i.e., the low-level scheduling target value; L represents the number of scheduling periods; represents the power generation at time l; represents the discharge at time l; represents the real-time electricity price at time l; min represents the operation of taking the minimum value; When the low-level dispatching target value is the smallest and the low-level dispatching objective function meets the power balance constraint condition, determining the corresponding power quantity index and real-time electricity price, and formulating the low-level dispatching strategy.

6. The comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant according to claim 1, wherein The constructing of the comprehensive evaluation model and calculating the comprehensive index scores of each hierarchical optimal dispatching strategy based on the diversified evaluation index set, and determining the target hierarchical optimal dispatching strategy by comparing each comprehensive index score, specifically includes: Set the evaluation index matrix corresponding to the diversified evaluation index set as , where represents the importance degree of the \(u\)th evaluation index relative to the \(v\)th evaluation index, and , , ; Obtain the maximum eigenvalue of the evaluation index matrix ZBJZ , and the maximum eigenvalue satisfies the following equation: Wherein, ZBJZ represents the evaluation index matrix; W represents the eigenvector corresponding to the evaluation index matrix; represents the maximum eigenvalue; Solving the above equation to obtain the eigenvector W, normalizing the eigenvector W to obtain the weight vector corresponding to each evaluation index, and the sum of the weight vectors corresponding to all evaluation indexes in the diversified evaluation index set is 1; Obtain the independent index score of the \(u\)-th evaluation index under the \(k\)-th hierarchical optimization scheduling strategy , combined with the weight vector corresponding to the \(u\)-th evaluation index, calculate the comprehensive index score of the \(k\)-th hierarchical optimization scheduling strategy as follows: In the formula, represents the comprehensive index score of the k-th hierarchical optimization scheduling strategy; represents the weight vector corresponding to the u-th evaluation index; represents the independent index score of the u-th evaluation index under the k-th hierarchical optimization scheduling strategy; If the comprehensive index score of the th hierarchical optimization scheduling strategy is the largest, then the th hierarchical optimization scheduling strategy is the target hierarchical optimization scheduling strategy.

7. The comprehensive evaluation method for hierarchical optimization scheduling of a virtual power plant according to claim 1, characterized in that The adjusting of the target hierarchical optimal dispatching strategy based on the intelligent dispatching algorithm, specifically includes: Based on the intelligent scheduling algorithm, a scheduling operation prediction model is constructed. The current scheduling status information of the virtual power plant is obtained and input into the scheduling operation prediction model to obtain a scheduling operation instruction. The corresponding calculation formula is as follows: In the formula, represents the f-th neuron in the middle layer of the scheduling operation prediction model; represents the activation function; E represents the number of neurons in the input layer of the scheduling operation prediction model; represents the connection weight between the e-th neuron in the input layer and the f-th neuron in the middle layer of the scheduling operation prediction model; represents the input of the e-th neuron in the input layer of the scheduling operation prediction model, that is, the e-th current scheduling status information; represents the bias of the f-th neuron in the middle layer of the scheduling operation prediction model; represents the output of the output layer of the scheduling operation prediction model, that is, the scheduling operation instruction; F represents the number of neurons in the middle layer of the scheduling operation prediction model; represents the connection weight between the f-th neuron in the middle layer and the output layer of the scheduling operation prediction model; represents the bias of the output layer of the scheduling operation prediction model; Adjust the target hierarchical optimization scheduling strategy according to the scheduling operation instruction.

8. The comprehensive evaluation system for the hierarchical optimization scheduling of a virtual power plant according to the comprehensive evaluation method as claimed in any one of claims 1-7, characterized in that, Including: An index construction model for constructing a diversified evaluation index set corresponding to the virtual power plant; A strategy formulation module for constructing a hierarchical optimization model corresponding to the virtual power plant and formulating multiple hierarchical optimization scheduling strategies; A strategy comparison module for constructing a comprehensive evaluation model and calculating the comprehensive index score of each hierarchical optimization scheduling strategy based on the diversified evaluation index set, and determining the target hierarchical optimization scheduling strategy by comparing each comprehensive index score; A strategy adjustment module for adjusting the target hierarchical optimization scheduling strategy based on the intelligent scheduling algorithm.

9. An electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, characterized in that, When the processor runs the computer program stored in the memory, the processor executes the steps of the comprehensive evaluation method for hierarchical optimization scheduling of the virtual power plant as described in any one of claims 1-7.

10. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the steps of the comprehensive evaluation method for hierarchical optimization scheduling of the virtual power plant as described in any one of claims 1-7.

Images