Virtual power plant scheduling method based on Genethink shark optimization algorithm

Abstract

The invention discloses a virtual power plant scheduling method based on a Genethink shark optimization algorithm, and relates to the technical field of virtual power plant scheduling, and the method comprises the steps: obtaining each piece of cost data generated in the scheduling process of a virtual power plant, and carrying out the limitation of an enforceable numerical range of each piece of cost data; substituting the cost data into a scheme optimization algorithm, initializing to generate a group of scheduling schemes, and calculating the minimum operation cost of the virtual power plant under the current group of scheduling schemes; continuously simulating a scheduling scheme corresponding to the minimum operation cost of the current virtual power plant through a scheme optimization algorithm, and exploring other scheduling schemes similar to the current scheduling scheme to obtain a current optimal scheduling scheme; a self-protection mechanism is added in the scheme optimization algorithm to prevent the scheme optimization algorithm from falling into a local optimum condition; the method has the beneficial effects that the optimization algorithm is effectively prevented from falling into local optimum, and meanwhile, complex nonlinear, non-convex and multi-target optimization problems can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual power plant dispatching, and in particular to a virtual power plant dispatching method based on Genghis Khan shark optimization algorithm. Background Art

[0002] In today's power system, the widespread access to distributed energy sources such as wind power and photovoltaics has brought about scheduling complexity and stability challenges. The instability and uncertainty of these energy resources make traditional grid scheduling methods seem inadequate. In order to meet this challenge, virtual power plants, as an emerging energy management concept, provide an integrated resource scheduling and optimization management method by integrating distributed energy, energy storage systems and adjustable loads. This approach not only improves the flexibility and economy of the power system, but also promotes the efficient use of renewable energy, which is of great significance for building a more intelligent and stable modern power network.

[0003] However, existing research on virtual power plant optimization scheduling mainly relies on the application of solvers, which perform well when dealing with scheduling problems with clear structures. However, the performance of these solvers is limited in the face of complex situations such as nonlinearity, non-convexity, multi-objective, uncertainty and dynamic changes. They are usually applicable to linear and mixed integer linear programming problems, but their capabilities are limited when dealing with nonlinear and non-convex problems, and they often need to be processed by linearization, which not only increases the complexity of the model but also may sacrifice accuracy. In the processing of multi-objective optimization problems, solvers usually need to synthesize multiple objectives into a single objective, which may not fully reflect the trade-offs between different objectives. In addition, for the uncertainty and dynamic characteristics in virtual power plants, the performance of solvers is not ideal, and usually requires detailed environmental analysis or robust optimization, which not only consumes a lot of computing resources, but also seems to be unable to cope with dynamic environments. In particular, when dealing with multi-peak objective functions commonly used in virtual power plant optimization scheduling, solvers are prone to fall into local optimality and lack comprehensive search capabilities, resulting in unsatisfactory results. Summary of the invention

[0004] In view of the above problems or problems existing in the prior art, the present invention is proposed.

[0005] Therefore, the purpose of the present invention is to provide a virtual power plant scheduling method based on the Genghis Khan shark optimization algorithm, which effectively avoids the optimization algorithm from falling into local optimality by introducing a self-protection mechanism. At the same time, it can handle complex nonlinear, non-convex and multi-objective optimization problems, thereby improving the optimization efficiency and practical application value of the virtual power plant scheduling scheme.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm, which includes obtaining various cost data generated by the virtual power plant during the scheduling process;

[0007] Substitute each cost data into the scheme optimization algorithm, initialize and generate a set of scheduling schemes, and calculate the minimum operating cost of the virtual power plant under the current set of scheduling schemes;

[0008] Through the scheme optimization algorithm, the scheduling scheme corresponding to the minimum operating cost of the current virtual power plant is continuously imitated and other scheduling schemes similar to the current scheduling scheme are explored to obtain the current optimal scheduling scheme.

[0009] As a preferred solution of the virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm of the present invention, a self-protection mechanism is added to the scheme optimization algorithm to prevent the scheme optimization algorithm from falling into a local optimal situation.

[0010] As a preferred solution of the virtual power plant scheduling method based on the Genghis Khan shark optimization algorithm of the present invention, the cost data includes the power generation cost, power purchase and sale cost, demand response cost, carbon emission cost, green certificate transaction cost and penalty cost at each moment, and each cost data is generated according to the constraint rules of the implementable numerical range.

[0011] As a preferred solution of the virtual power plant scheduling method based on the Genghis Khan shark optimization algorithm of the present invention, wherein: the solution optimization algorithm is the Genghis Khan shark optimization algorithm.

[0012] As a preferred solution of the virtual power plant dispatching method based on Genghis Khan Shark Optimization Algorithm of the present invention, a self-protection mechanism is added to the scheme optimization algorithm to prevent the scheme optimization algorithm from falling into a local optimal situation, specifically:

[0013] Detect whether the current optimal scheduling solution falls into a local optimal situation;

[0014] If it is detected that the current optimal scheduling plan falls into a local optimal situation, the current optimal scheduling plan is randomly disturbed to make the current optimal scheduling plan jump out of the local optimal area and continue to explore a better scheduling plan.

[0015] As a preferred solution of the virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm of the present invention, the minimum operating cost of the virtual power plant under the current group of scheduling solutions is calculated as follows:

[0016] Taking the minimum operating cost of the virtual power plant within a cycle as the goal, an objective function is established based on various cost data;

[0017] Substitute the various cost data corresponding to the current group of scheduling plans into the objective function to calculate the minimum operating cost of the virtual power plant under the current group of scheduling plans.

[0018] As a preferred scheme of the virtual power plant scheduling method based on the Genghis Khan shark optimization algorithm of the present invention, wherein: the current optimal scheduling scheme is to substitute each cost data in each group corresponding to each group of scheduling schemes generated by the scheme optimization algorithm into the objective function, calculate the minimum operating cost of the virtual power plant under each group of scheduling schemes, and compare the minimum operating costs of each group of virtual power plants, and set the scheduling scheme corresponding to the smallest minimum operating cost of the virtual power plant as the current optimal scheduling scheme.

[0019] In order to further solve the above technical problems, the present invention provides the following technical solutions: Data acquisition module: collects various cost data in the virtual power plant scheduling process.

[0020] Data limitation module: limits the feasible numerical range of each collected cost data.

[0021] Initialization module: Initializes and generates a set of scheduling plans based on a set of cost data.

[0022] Optimization module: simulates the current scheduling plan and explores the optimal scheduling plan in the area close to the current scheduling plan.

[0023] Self-protection mechanism module: detects and prevents the optimization module from falling into local optimal situations, implements random disturbance to change areas and continues to explore better scheduling solutions.

[0024] Objective function module: establishes an objective function based on various cost data, takes minimizing the operating cost within a scheduling cycle as the goal, and calculates the minimum operating cost of each group of virtual power plants under each group of scheduling schemes.

[0025] Scheme comparison module: compares the minimum operating costs of each group of virtual power plants, and determines that the scheduling scheme corresponding to the minimum operating cost of the smallest virtual power plant is the better scheduling scheme.

[0026] System control unit: coordinates the operation of the above modules and ensures the implementation of the scheduling method.

[0027] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the industrial data priority calculation method based on correlation relationship and sequence processing are implemented as described above.

[0028] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the industrial data priority calculation method based on correlation relationship and sequence processing as described above are implemented.

[0029] Beneficial effects of the present invention: The present invention adopts a scheme optimization algorithm, especially the Genghis Khan shark optimization algorithm, to solve the virtual power plant optimization scheduling problem. It can not only directly deal with complex nonlinear and non-convex problems without linearization processing, maintaining the accuracy of the model, but also can adaptively adjust its search strategy according to changes in the search environment, and balance the global search and local search during the search process, which helps to avoid premature convergence to the local optimal solution. At the same time, it can explore other areas of the solution space to find better solutions. It performs better when dealing with uncertainty and dynamic environments, and can flexibly respond to dynamic constraints and multi-objective optimization requirements in virtual power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 The Genghis Khan shark optimization algorithm of the present invention is used to solve the power balance diagram of the virtual power plant.

[0032] Figure 2 Solve the virtual power plant power balance diagram for the cplex of the present invention.

[0033] Figure 3 This is a diagram of the virtual power plant optimization scheduling model of the present invention. DETAILED DESCRIPTION

[0034] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0035] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0036] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0037] Example 1

[0038] This is the first embodiment of the present invention, which provides a virtual power plant scheduling method based on Genghis Khan shark optimization algorithm, which includes:

[0039] S1: Obtain various cost data generated by the virtual power plant during the scheduling process.

[0040] Furthermore, the cost data includes the power generation cost, power purchase and sales cost, demand response cost, carbon emission cost, green certificate trading cost and penalty cost at each moment. Each cost data is generated based on the constraint rules of the implementable numerical range.

[0041] It should be noted that the power generation cost includes the operating costs of wind power, photovoltaics, energy storage and gas turbines.

[0042] Among them, the total operating cost of wind power, photovoltaic power and energy storage is C op The expression is as follows:

[0043]

[0044] Where: w ,ω s ,ω d They are the operating costs of wind, solar and energy storage;

[0045] P wind (t), P sol (t), P dis (t) are the discharge amounts of wind, solar and energy storage at time t respectively;

[0046] The constraint condition is that the SOC of the energy storage system must be kept within the specified range, and its expression is:

[0047] SOC min ≤SOC(t)≤SOC max ,

[0048] SOC min , SOC max are the minimum state of charge and the maximum state of charge respectively.

[0049] Gas turbine operating costs C gs Depending on its power generation and fuel cost, its expression is:

[0050]

[0051] Where: a, b, c are fuel cost coefficients; P G i(t) is the electrical energy generated by the i-th gas turbine at time t;

[0052] The constraint condition is to limit the power generated by the gas turbine to the minimum and maximum power, which is expressed as:

[0053] P gs，min ≤P Gi (t)≤P gs，max ,

[0054] The ramp constraint is used to limit the rate of change of the electric energy generated by the gas turbine to avoid drastic changes in the generated electric energy in a short period of time and ensure the stable operation of the equipment. Its expression is:

[0055] |P Gi (t)-P Gi (t-1)|≤P limit ,

[0056] Where: P limit It is the climbing constraint of the gas turbine.

[0057] Cost of electricity purchase and sale C bs is the difference cost of the virtual power plant in purchasing or selling electricity in the power market, and its expression is:

[0058] C bs =P buy (t)ω buy (t)-P sell (t)ω sell (t)

[0059] In the formula, ω buy (t) and ω sell (t) are the market prices for electricity purchase and electricity sales respectively; P buy (t) and P sell (t) are the electricity purchased and sold at time t;

[0060] The constraint condition is power balance, specifically, the amount of electricity purchased and sold by the virtual power plant in each period must meet the actual power demand and power generation constraints, and its expression is:

[0061] P wind +P sol +P Gi +P dr +P buy =P sell +P load

[0062] Where: P dr for demand response;

[0063] Demand response cost C dr Based on the incentive mechanism, the user response is encouraged by the incentive price λ, and the response load is calculated, which is expressed as:

[0064] C dr =λP dr

[0065] The constraint condition is the response interval, specifically the response coefficient of the demand response is in the interval (ρ down , ρ up ), determined according to the incentive price, and its expression is:

[0066] ρ down ≤ρ(t)≤ρ up

[0067] The load reduction is to meet the upper limit of the load that can be reduced and the load participation ratio constraints.

[0068] Carbon trading costs C ce It refers to the step-by-step carbon price model, in which the carbon price rises in a step-by-step manner as the carbon trading volume increases;

[0069] The constraint is the carbon emission quota. Specifically, within the specified quota range, the upper limit of carbon trading costs is subject to regional carbon policy restrictions to ensure that total emissions do not exceed the quota.

[0070] Green certificate transaction cost C tgc Based on the inverse demand function of the Cournot model, the price of green certificates is inversely proportional to the quantity sold;

[0071] The constraint is the sales volume limit, specifically the number of green certificates sold cannot exceed the total number of green certificates stipulated by the market, and must meet the renewable energy consumption ratio.

[0072] It should be noted that, referring to Figure 3 , and further construct an optimal scheduling model for virtual power plants participating in the electricity-carbon-green certificate market that takes into account the uncertainty of wind and solar power. The operating costs of virtual power plants are decomposed into wind, solar and energy storage operating costs, gas turbine operating costs, electricity purchase and sales costs, demand response costs, carbon trading costs and green certificate trading costs, and an objective function is established. The model comprehensively considers the uncertainty of electricity generated by renewable energy such as wind power and photovoltaics in virtual power plants, and introduces demand response, carbon trading and green certificate trading mechanisms.

[0073] In order to accurately predict the output of wind power and photovoltaic power generation, the Frank-Copula function is used to describe their correlation, and a typical scenario is generated through scenario generation and reduction methods. This method can better reflect the actual output of wind power and photovoltaic power generation in the same area. The construction process of the wind and solar uncertainty model is as follows:

[0074] Nonparametric kernel density estimation: Using historical data, the probability density functions of wind power and photovoltaic power are generated through Gaussian kernel function;

[0075]

[0076] Where: t = 1, 2, ..., 24, which is 24 time periods; x and y are the wind turbine and photovoltaic outputs in time period t respectively; Xd , Y d are the wind turbine and photovoltaic outputs at time period t on day d, respectively; h is the bandwidth.

[0077] Frank-Copula connection function: The joint distribution of wind power and photovoltaic power is established through the Frank-Copula function to obtain their joint probability distribution;

[0078] F(x,y)=C(F(x),F(y))

[0079]

[0080] Where: F(X) and F(Y) are the cumulative distribution functions of wind and light, respectively; C is the two-dimensional Frank-Copula function; λ is the correlation parameter, λ greater than 0 indicates that u and v are positively correlated; λ approaching 0 indicates that u and v tend to be independent; λ less than 0 indicates that u and v are negatively correlated.

[0081] Scenario generation and reduction: The joint distribution function is sampled, and the wind and solar output is solved using the cubic spline interpolation method. Finally, the scene reduction is performed through the k-means clustering method to generate a typical wind and solar output scenario. The cubic spline polynomial is:

[0082]

[0083] Where: d = 1, 2, ..., n; a d , b d 、c d , l d are cubic polynomial coefficients respectively.

[0084] The energy storage system adjusts the balance of power supply and demand through charging and discharging to ensure the stable operation of the virtual power plant under different load conditions. The energy storage system model describes the power limit and charge state change of the energy storage. The specific process is as follows:

[0085]

[0086] Where: Soc(t) is the battery state of charge at time t; Ebat(t) is the battery power at time t; Emax is the maximum capacity of the power plant.

[0087] The demand response model uses the uncertainty interval method to describe the randomness of demand response and adjusts the user's enthusiasm for participating in the response through incentive prices. This method provides more flexibility for virtual power plant scheduling. The specific process is as follows:

[0088]

[0089] ρ down ≤ρ≤ρ up

[0090] Where: x represents the incentive price; ρ represents the demand response coefficient.

[0091] As the incentive price increases from zero to a certain threshold, users' enthusiasm and responsiveness to participation increase accordingly.

[0092] The trading price of carbon emission rights increases with the increase of trading volume. The step-by-step carbon price model is used to describe the changes in carbon prices. The carbon emission rights trading model can effectively describe the dynamic changes in the carbon market. The specific process is as follows:

[0093]

[0094] Where: car 0 is the basic carbon price; Q car is the carbon emission rights trading volume, Q car To sell carbon emission rights in time, Q car When it is negative, purchase carbon emission rights; μ is the carbon price growth rate; l is the length of carbon trading volume.

[0095] In the green certificate market, green certificates can be used for trading as a commodity. The green certificate trading model uses the inverse demand function based on the Cournot model to describe the relationship between the price of green certificates and the quantity sold:

[0096]

[0097] Where: TGC is the green certificate price in the market; α TGC and β TGC are the two positive parameters of the inverse price function of the Cournot model; Q sell,d is the number of green certificates that can be sold today; θ0 TGC is the green certificate transaction price ratio coefficient calculated based on historical data; Ρ0 TCG is the renewable energy consumption ratio in this region; Q0 D It is the total number of green certificates in one day.

[0098] S2: Substitute each cost data into the scheme optimization algorithm, initialize and generate a set of scheduling schemes, and calculate the minimum operating cost of the virtual power plant under the current set of scheduling schemes.

[0099] Furthermore, the solution optimization algorithm is the Genghis Khan Shark Optimization Algorithm.

[0100] Furthermore, the minimum operating cost of the virtual power plant under the current group of scheduling schemes is calculated as:

[0101] Taking the minimum operating cost of the virtual power plant within a dispatch cycle as the goal, an objective function is established based on various cost data;

[0102] Substitute the various cost data corresponding to the current group of scheduling plans into the objective function to calculate the minimum operating cost of the virtual power plant under the current group of scheduling plans.

[0103] It should be noted that a scheduling cycle is 24 hours a day.

[0104] Furthermore, the current optimal scheduling plan is to substitute the cost data of each group corresponding to each group of scheduling plans generated by the scheme optimization algorithm into the objective function, calculate the minimum operating cost of the virtual power plant under each group of scheduling plans, and compare the minimum operating costs of each group of virtual power plants, and set the scheduling plan corresponding to the smallest minimum operating cost of the virtual power plant as the current optimal scheduling plan.

[0105] It should be noted that the minimum operating cost of the virtual power plant minC vpp The expression is:

[0106] min C VPP =C op +C gs +C bs +C dr +C ce +C tgc

[0107] Where: C vpp represents the total operating cost of the virtual power plant in a dispatch cycle; C op represents the total operating cost of wind power, photovoltaic power and energy storage; C gs represents the gas turbine operating cost; C bs Represents the cost of purchasing and selling electricity; C dr represents the demand response cost; C ce represents the carbon trading cost; C tgc Represents the transaction cost of green certificates.

[0108] S3: Through the scheme optimization algorithm, the scheduling scheme corresponding to the minimum operating cost of the current virtual power plant is continuously imitated and other scheduling schemes similar to the current scheduling scheme are explored to obtain the current optimal scheduling scheme.

[0109] S4: Add a self-protection mechanism to the solution optimization algorithm to prevent the solution optimization algorithm from falling into a local optimal situation.

[0110] Furthermore, a self-protection mechanism is added to the solution optimization algorithm to prevent the solution optimization algorithm from falling into a local optimal situation. Specifically:

[0111] Detect whether the current optimal scheduling solution falls into a local optimal situation;

[0112] If it is detected that the current optimal scheduling plan falls into a local optimal situation, the current optimal scheduling plan is randomly disturbed to make the current optimal scheduling plan jump out of the local optimal area and continue to explore a better scheduling plan.

[0113] It should be noted that the Genghis Khan Shark Optimization Algorithm (GKSO) is a new optimization algorithm inspired by the hunting and survival behavior of Genghis Khan sharks. The algorithm simulates shark behavior in four key stages: exploration, exploitation, foraging conversion, and self-protection mechanism; specifically:

[0114] (1) Exploration phase

[0115] During the exploration phase, the Genghis Khan shark swims randomly in the water to ensure the safety of the area and find the best prey location. This behavior calculates the random position by the upper and lower limits of the search space to expand the search range; the position update formula is as follows:

[0116]

[0117] Where: represents the new position of the i-th individual in the j-th dimension; ub j and lb j They represent the upper and lower boundaries of the jth dimension respectively; r1 is a random number in the range [0,1]; it is the current iteration number;

[0118] The goal of this phase is to have the shark navigate the entire search space to find a potential prey location.

[0119] (2) Development stage

[0120] During the development phase, the Genghis Khan Shark will rely on its keen sense of smell to move to the optimal prey location to capture higher quality prey. Its position update formula is as follows:

[0121]

[0122] S=m·I·r

[0123]

[0124] Where: is the best position currently known; s represents the shark's sense of smell, which is controlled by the concentration of the odor emitted by the prey; r is a random number in the range [0,1]; I is the fitness value of the individual; m is a constant (usually 1.5);

[0125] When r = 0, it means that the shark cannot perceive the smell and the searcher re-enters the exploration phase; when r = 1, the shark completely absorbs the smell and may find a local optimal solution.

[0126] (3) Foraging stage

[0127] During the foraging phase, the Genghis Khan shark will use a parabolic trajectory to move quickly after approaching the optimal prey location. This behavior enables the algorithm to dynamically switch between global search and local development, thereby improving the optimization effect; the specific update formula is as follows:

[0128]

[0129]

[0130] Where r2 is a random number in the range of [0,1]; λ is a random symbol with a value of 1 or -1, which is used to control the direction; p is a nonlinear convergence factor, whose value gradually decreases with the number of iterations; |ω(t+1)| is the weight coefficient at iteration t+1, which is used to adjust the amplitude of the parabola path; T is the total number of iterations.

[0131] (4) Self-protection mechanism

[0132] When a shark encounters a threat or falls into a local optimum, its body color will become lighter to escape the predator. This behavior is simulated in the algorithm as a process of jumping out of the local optimum. The specific mathematical model is as follows:

[0133]

[0134] ρ=α·(2·rand-1)

[0135]

[0136] Where: k1 is a random number uniformly distributed in the range [-1,1], used for perturbation; α, β, ρ are adaptability coefficients; β min and β max are 0.2 and 1.2 respectively; rand is a random number in [0,1]; X1 and X2 are two random solutions used to increase the randomness of the search.

[0137] By simulating the complex behavior of sharks in nature, the GKSO algorithm achieves a balance between global search and local optimization, has a strong convergence speed and adaptability, and is suitable for optimization problems with multi-dimensional complex constraints.

[0138] Example 2

[0139] Reference Figure 1 and Figure 2 , which is the second embodiment of the present invention, and is different from the first embodiment in that: a virtual power plant scheduling method based on Genghis Khan shark optimization algorithm is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0140] In this embodiment, the position representation of each Genghis Khan shark in the population is set as a group of 1×72 data (the optimization latitude of the algorithm is set to 72, and the optimization variables include gas turbine output, demand response, energy storage, and electricity purchase and sale), where 1-24 is the gas turbine output for 24 hours a day, 25-48 is the demand response participation data for 24 hours a day, and 49-72 is the output of energy storage for 24 hours a day.

[0141] The amount of electricity purchased and sold every hour of the day is the power balance deficit at the current moment (i.e., gas turbine output + demand response participation data + wind and solar output - load at that moment). Taking into account the actual transmission power limit and other conditions, there are upper and lower limits for the purchase and sale of electricity at each moment. Therefore, a penalty factor is introduced. If the purchase and sale of electricity at the current moment is not enough to balance the power, a large cost penalty factor will be added to the objective function. Then, the iterative results of the objective function in Example 1 are used to compare the minimum operating costs. The position with the lowest cost will be set as the optimal result of this iteration, i.e., the optimal scheduling plan for this iteration. Finally, the maximum number of iterations of the algorithm is set, and the output results are compared after each iteration. The iterative result with the lowest minimum operating cost is taken as the better result, i.e., the better scheduling plan, and the algorithm is finally terminated.

[0142] Taking the time-of-use electricity price in Guizhou Province and the load of a certain area for 24 hours a day as an example, this embodiment compares the optimization results of the Genghis Khan Shark Optimization Algorithm with the results of the CPLEX solver. The specific indicators are shown in the following table:

[0143]

[0144] The comparison results between Genghis Khan Shark Optimization Algorithm (GKSA) and CPLEX solver in virtual power plant scheduling optimization show that GKSA has obvious advantages in total cost, wind, solar and storage operation cost, and power purchase and sales cost.

[0145] Specifically, the total operating cost of GKSA is 96,960.15 yuan, which is significantly lower than CPLEX's 114,305.47 yuan. This is mainly due to its more flexible handling of the uncertainty of distributed energy, which reduces the operating cost of wind, solar and storage to 512.54 yuan (a reduction of more than 95% compared to CPLEX's 10,818.94 yuan).

[0146] In addition, GKSA also shows an advantage in the cost of purchasing and selling electricity, which is only 369.40 yuan, about 1 / 8 of CPLEX. This shows that GKSA can optimize the purchasing and selling strategy more flexibly and reduce the cost impact caused by market fluctuations. In terms of demand response, the cost of GKSA is slightly higher than that of CPLEX, reflecting that the algorithm has more investment in actively motivating users to participate in demand response. Although the short-term cost increases, it will help enhance the system's load regulation ability in the long run.

[0147] Overall, GKSA demonstrates its superiority in dealing with complex constraints and multi-objective optimization tasks due to its global search and multi-peak optimization capabilities.

[0148] Example 3

[0149] This is an embodiment of the present invention, which is the third embodiment of the present invention. It is different from the first embodiment in that: a virtual power plant dispatching system based on Genghis Khan shark optimization algorithm is provided, including a data acquisition module, a data limitation module, an initialization module, an optimization module, a self-protection mechanism module, an objective function module and a system control unit.

[0150] Among them, the data acquisition module is used to collect various cost data in the virtual power plant scheduling process, the data limitation module is used to limit the implementable numerical range of each collected cost data, the initialization module is used to initialize and generate a group of scheduling plans based on a set of cost data, the optimization module is used to imitate the current scheduling plan and explore the optimal scheduling plan in the area similar to the current scheduling plan, the self-protection mechanism module is used to detect and prevent the optimization module from falling into the local optimal situation, implement random disturbance to change the area to continue to explore a better scheduling plan, the objective function module is used to establish an objective function based on various cost data, with the goal of minimizing the operating cost within a scheduling cycle, and calculate the minimum operating cost of each group of virtual power plants under each group of scheduling plans, the scheme comparison module is used to compare the minimum operating cost of each group of virtual power plants, and determine that the scheduling plan corresponding to the minimum operating cost of the minimum virtual power plant is the better scheduling plan, and the system control unit is used to coordinate the operation of the above modules to ensure the implementation of the scheduling method.

[0151] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0152] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0153] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0154] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0155] It is important to note that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A virtual power plant scheduling method based on Genghis Khan shark optimization algorithm, characterized by: include, Obtain various cost data generated by the virtual power plant during the scheduling process; Substitute each cost data into the scheme optimization algorithm, initialize and generate a set of scheduling schemes, and calculate the minimum operating cost of the virtual power plant under the current set of scheduling schemes; Through the scheme optimization algorithm, the scheduling scheme corresponding to the minimum operating cost of the current virtual power plant is continuously imitated and other scheduling schemes similar to the current scheduling scheme are explored to obtain the current optimal scheduling scheme.

2. The virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm according to claim 1 is characterized in that: Also includes, A self-protection mechanism is added to the solution optimization algorithm to prevent the solution optimization algorithm from falling into a local optimal situation.

3. The virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm according to claim 1 is characterized in that: The cost data include power generation cost, power purchase and sale cost, demand response cost, carbon emission cost, green certificate transaction cost and penalty cost at each moment. Each cost data is generated based on constraint rules of an implementable numerical range.

4. The virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm according to any one of claims 1 to 3, characterized in that: The scheme optimization algorithm is the Genghis Khan Shark Optimization Algorithm.

5. The virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm as claimed in claim 2, characterized in that: The self-protection mechanism added to the solution optimization algorithm to prevent the solution optimization algorithm from falling into a local optimal situation is specifically as follows: Detect whether the current optimal scheduling solution falls into a local optimal situation; If it is detected that the current optimal scheduling plan falls into a local optimal situation, the current optimal scheduling plan is randomly disturbed to make the current optimal scheduling plan jump out of the local optimal area and continue to explore a better scheduling plan.

6. The virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm according to any one of claims 1 to 3 and 5, characterized in that: The calculation of the minimum operating cost of the virtual power plant under the current group of scheduling schemes is specifically: Taking the minimum operating cost of the virtual power plant within a dispatch cycle as the goal, an objective function is established based on various cost data; Substitute the various cost data corresponding to the current group of scheduling plans into the objective function to calculate the minimum operating cost of the virtual power plant under the current group of scheduling plans.

7. The virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm according to any one of claims 1 to 3 and 5, characterized in that: The current optimal scheduling plan is to substitute each cost data in each group corresponding to each group of scheduling plans generated by the plan optimization algorithm into the objective function, calculate the minimum operating cost of the virtual power plant under each group of scheduling plans, and compare the minimum operating costs of each group of virtual power plants, and set the scheduling plan corresponding to the smallest minimum operating cost of the virtual power plant as the current optimal scheduling plan.

8. A system using the virtual power plant scheduling method based on Genghis Khan Shark Optimization Algorithm as claimed in claim 1, characterized in that: include: Data acquisition module: collects various cost data in the virtual power plant scheduling process; Data limitation module: limits the feasible numerical range of each collected cost data; Initialization module: Initializes and generates a set of scheduling plans based on a set of cost data; Optimization module: simulates the current scheduling plan and explores the optimal scheduling plan in the area close to the current scheduling plan; Self-protection mechanism module: detects and prevents the optimization module from falling into a local optimal situation, implements random disturbance to change the area and continues to explore a better scheduling solution; Objective function module: establishes an objective function based on various cost data, takes minimizing the operating cost within a scheduling cycle as the goal, and calculates the minimum operating cost of each group of virtual power plants under each group of scheduling schemes; Scheme comparison module: compares the minimum operating costs of each group of virtual power plants, and determines the scheduling scheme corresponding to the minimum operating cost of the smallest virtual power plant as the better scheduling scheme; System control unit: coordinates the operation of the above modules and ensures the implementation of the scheduling method.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for calculating the priority of industrial data based on correlation relationship and sequence processing described in claim 1 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for calculating the priority of industrial data based on correlation relationship and sequence processing described in claim 1 are implemented.

Images