Virtual power plant optimization scheduling method based on particle swarm optimization

Abstract

The invention relates to a virtual power plant optimal scheduling method based on a particle swarm optimization algorithm, which aims at obtaining an optimal virtual power plant scheduling scheme, adopts the particle swarm optimization algorithm to optimize the virtual power plant scheduling scheme, and comprises the following steps: S1, obtaining the generation power and related load power of all units in a virtual power plant; s2, inputting related parameters of a particle swarm optimization algorithm; s3, initializing positions and speeds of particles; s4, calculating the fitness value of each particle; s5, updating the speed and position of the particles, and updating individual optimization and group optimization; s6, recalculating the fitness value of each particle; s7, judging whether the number of times of stopping iteration is reached or not, if so, outputting an optimization result, and otherwise, turning to the next step; s8, judging whether the fitness value of the particle is unchanged after continuous m iterations, if not, returning to S5, and if yes, updating the particle speed; s9, carrying out SCR (Selective Catalytic Reduction) calculation on the particles and picking out inferior particles; and S10, respectively updating the value of each dimension of the inferior particles, and then returning to the step S4 to continue iteration. The method is beneficial to improving the scheduling effect of the virtual power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated energy system scheduling optimization, and in particular to a virtual power plant optimization scheduling method based on particle swarm algorithm. Background Art

[0002] Renewable energy generation has a disadvantage that cannot be ignored, that is, there is uncertainty in the transmission of electric power. In addition, new energy generation, including wind power generation and photovoltaic power generation, accounts for an increasingly higher proportion in the power generation of the power system, so it will have a greater impact on the power system. In particular, power fluctuations will cause the frequency of the power grid to fluctuate. If wind power generation and photovoltaic power generation are directly connected to the grid, it will pose a certain threat to the stability, power quality and frequency quality of the power system. Therefore, considering how to effectively smooth the output power of new energy generation, reduce the impact of its fluctuations on the power system, and improve the operating capacity of wind farms and photovoltaic farms is of practical significance for the large-scale development and application of new energy generation.

[0003] At present, in order to smooth the original power generated by renewable energy generation, the main method is to use virtual power plant technology to balance energy supply and demand by integrating and optimizing distributed energy resources, so as to maximize the rational use of renewable energy. However, the model has the characteristics of high-dimensional variables, nonlinearity, and complex constraints. Although it can be converted into a mixed integer linear programming model through linearization, there are too many decision variables that need to be converted in the model, so other methods need to be sought to solve the model. Summary of the invention

[0004] The purpose of the present invention is to provide a virtual power plant optimization scheduling method based on particle swarm algorithm, which is beneficial to improving the scheduling effect of virtual power plants.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: a virtual power plant optimization scheduling method based on particle swarm algorithm, with the goal of obtaining the optimal virtual power plant scheduling plan, using particle swarm optimization algorithm to optimize the virtual power plant scheduling plan, including the following steps:

[0006] S1. Obtain the power generation power and related load power of all units in the virtual power plant and perform data preprocessing;

[0007] S2. Input the relevant parameters of the particle swarm optimization algorithm, including population size, number of iterations and inertia weight; each particle in the particle swarm optimization algorithm represents a scheduling scheme;

[0008] S3, initialize the position and velocity of the particle;

[0009] S4, calculate the fitness value of each particle and record it for archiving;

[0010] S5, update the speed and position of particles, update the individual optimum and group optimum;

[0011] S6, recalculate the fitness value of each particle and record it for archiving;

[0012] S7, determine whether the number of termination iterations has been reached, if yes, go to step S11, otherwise go to step S8;

[0013] S8, judging whether the fitness value of the particle has not changed in the continuous m iterations, otherwise returning to step S5, if yes, updating the speed of each particle;

[0014] S9, calculate the self-conductivity SCR of the particles, and select the inferior particles according to the SCR value;

[0015] S10, generate a random number for each dimension of the inferior particle respectively. If the generated random number is smaller than the variation value of the particle dimension, replace the value of the dimension of the inferior particle with the value of the dimension corresponding to the optimal individual particle, and then return to step S4 to continue iteration;

[0016] S11. End the optimization process and output the optimization result, which is the optimal virtual power plant scheduling plan.

[0017] Furthermore, in step S1, when performing data preprocessing, abnormal parameters are screened out and several groups of 24-hour parameters are randomly selected as verification data.

[0018] Furthermore, in step S4, the fitness value of each particle is calculated using the fitness function of formula (1):

[0019] f=R VPP -C VPP (1)

[0020] Where, f is the benefit of the virtual power plant VPP; R VPP and C VPP They are the total revenue and total cost of VPP internal operation;

[0021] The total operating cost is expressed as:

[0022]

[0023] In the formula, C F is the operating cost of the thermal power unit; C WT and are the operation and maintenance cost of wind turbines and the penalty cost for wind abandonment; C PV and are the operation and maintenance cost of the photovoltaic unit and the penalty cost for abandonment of light; C ESS is the operation and maintenance cost of the energy storage equipment; C gridis the electricity cost of the interaction between VPP and the upper grid; C P2G is the operating cost of the P2G equipment; C CS is the carbon sequestration cost of VPP; a f 、b f and c f are fuel cost coefficient, P G,t is the total output power of the thermal power unit during period t; WT and δ PV are the operating cost coefficients of wind power generation and photovoltaic power generation, P WT,t and P PV,t are the power generation of wind turbines and photovoltaic units in time period t respectively; and are the penalty cost factors for wind and solar abandonment respectively; P WT,pre,t and P PV,pre,t are the predicted output power of wind power and photovoltaic power in time period t respectively; δ ESS is the operation and maintenance cost factor of the energy storage equipment, and are the charging and discharging power of the energy storage device in period t; buy,t and δ sell,t are the prices of electricity purchased and sold by VPP to the external power grid; P grid,buy,t and P grid,sell,t are the amount of electricity purchased and sold by VPP to the upper grid in period t; P2G is the operating cost coefficient of P2G, P P2G,t is the P2G energy consumption in time period t; CCS is the cost of storing unit carbon dioxide; N CCS,t is the amount of carbon dioxide that needs to be stored in time period t, as shown in formula (3):

[0024]

[0025] Where N P2G,t is the amount of carbon dioxide consumed by P2G in period t; η C The amount of carbon dioxide required to produce a unit of natural gas;

[0026] The total operating profit is expressed as:

[0027]

[0028] In the formula, R SE,t is the electricity sales revenue of VPP in period t; sell,t P is the price at which VPP sells electricity; VPP,t is the planned output power of VPP during period t. is the natural gas production in period t; P2Gis the electroporation efficiency; H g is the calorific value of natural gas; S g is the price of natural gas per unit; R SG,t The income from participating in the natural gas market. GN,t is the net output power of the thermal power unit during period t; P CC,t is the total energy consumption of carbon capture equipment during period t; P bas and P opt,t are the basic energy consumption and operating energy consumption of carbon capture in period t respectively; P CO2 P is the energy consumption for treating unit carbon dioxide; GC,t Energy consumption of carbon capture provided for thermal power units.

[0029] Furthermore, in step S5, the speed and position of the particles are updated according to formulas (7) and (8), and the individual optimum and the group optimum are updated;

[0030] v l,n+1 =wv l,n +c1r1(P best,l -x l,n )+c2r2(G best,n -x l,tn ) (7)

[0031]

[0032]

[0033] Among them, v l,n+1 is the velocity of particle l at the next iteration n+1; v l,t＝n is the speed of particle l in the current iteration n, w is the inertia weight of particle speed change, which controls the degree of particle speed retention; c1 and c2 are acceleration coefficients, which represent individual learning factors and social learning factors, respectively, and control the degree to which particles approach individual optimality and global optimality; r1 and r2 are random numbers in the interval [0,1]; P best,l is the individual optimal position found by particle l so far; G best,n is the global optimal position found by the entire particle swarm so far; x l,n+1 is the position of particle l at the next iteration n+1; x l,n is the velocity of particle l at the current iteration n; ρ n is the inertia weight of particle position change; ρ max and ρ min are the maximum and minimum values ​​of the inertia weight respectively; R1 controls the amplitude of the sine and cosine functions and can be adjusted according to the iterative process; a is a set constant; R2, R3 and R4 represent three random numbers that obey a uniform distribution; N is the total number of iterations.

[0034] Further, in step S8, when the position of a particle changes and the fitness value of the particle remains unchanged during the m consecutive iterations, the speed of each particle is updated according to the speed correction formula of formula (10);

[0035]

[0036] Among them, v l,n+1 It represents the speed of the next iteration n+1 of the lth particle, l represents the lth particle, n represents the current iteration, and m represents the set number of consecutive iterations.

[0037] Furthermore, in step S9, in order to avoid falling into a local optimum in the process of finding the optimal solution, the self-conductivity of the particle is calculated according to formula (11);

[0038]

[0039] Among them, SCR(l,n) is the ratio of the change in the individual optimal fitness of the lth particle in the first q iterations to the change in the global optimal individual fitness at the nth iteration; f() represents the fitness function.

[0040] Furthermore, in step S10, the values ​​of some dimensions of the detected inferior particles are changed with a certain probability, so that the inferior particles escape from the current inferior area; when the value of SCR is 0 or infinite, it indicates that it is currently in a local optimal state; based on the idea of ​​genetic variation, the positions of the screened inferior particles and the global optimal particles are exchanged with a certain probability.

[0041] The present invention also provides a virtual power plant optimization scheduling system for implementing the above method, comprising:

[0042] Data acquisition module, used to collect the power generation and related load power of all units in the virtual power plant and perform data preprocessing;

[0043] A particle swarm optimization module, which is used to optimize virtual power plant scheduling using a particle swarm optimization algorithm based on the collected data; and

[0044] The self-conductivity calculation module is used to be called by the particle swarm optimization module to calculate the self-conductivity of particles and select inferior particles according to the SCR value.

[0045] The present invention also provides a computer device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, and the above method is implemented when the computer program instructions are executed by the processor.

[0046] The present invention also provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above method is implemented.

[0047] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a virtual power plant optimization scheduling method based on particle swarm algorithm, which uses SCA algorithm to optimize the particle position update method of PSO algorithm. In addition, in order to further develop the local search capability of the algorithm in later iterations, a reverse search strategy is adopted for the local optimal particles. In the process of continuous iterations, when the position of the particle changes and the fitness value stagnates, the current speed is used as the vector sum of the speeds of the previous m iterations for intervention. While maintaining the advantages of the PSO algorithm, the present invention reduces the probability of falling into the local optimum by increasing the diversity of the population, and improves the efficiency and accuracy of the algorithm in finding the optimal solution. Applying this method to the optimization scheduling of virtual power plants can obtain better optimization scheduling effects. Therefore, the present invention has strong practicality and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The figure is a flow chart of the implementation of the particle swarm optimization algorithm according to the embodiment of the present invention.

[0049] Figure 2 Schematic diagram of a reverse search strategy in a particle swarm optimization algorithm according to an embodiment of the present invention.

[0050] Figure 3 The figure is a comparison of solution results of the high-dimensional test function according to the embodiment of the present invention.

[0051] Figure 4 This is a structural block diagram of a virtual power plant according to an embodiment of the present invention.

[0052] Figure 5 The original power generated by wind power and photovoltaic power and the load power on four typical days in the virtual power plant of the embodiment of the present invention.

[0053] Figure 6 This is the solution result on the third typical day in the virtual power plant according to the embodiment of the present invention. DETAILED DESCRIPTION

[0054] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0055] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0056] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0057] like Figure 1-2 As shown, this embodiment provides a virtual power plant optimization scheduling method based on a particle swarm algorithm, with the goal of obtaining an optimal virtual power plant scheduling scheme, and using a particle swarm optimization algorithm to optimize the virtual power plant scheduling scheme, including the following steps:

[0058] S1. Obtain the power generation power and related load power of all units in the virtual power plant and perform data preprocessing.

[0059] During the data preprocessing process, abnormal parameters are screened out and several groups of 24-hour parameters are randomly selected as verification data.

[0060] S2. Input the relevant parameters of the particle swarm optimization algorithm, including population size, number of iterations, and inertia weight.

[0061] In the particle swarm optimization algorithm, each particle represents a scheduling scheme, that is, the power generation and power consumption of all units in the virtual power plant within a scheduling cycle (in this embodiment, 24 hours is set as a scheduling cycle).

[0062] S3. Initialize the position and velocity of the particle.

[0063] S4. Calculate the fitness value of each particle and record it for archiving.

[0064] Specifically, the fitness function of formula (1) is used to calculate the fitness value of each particle:

[0065] f=R VPP -C VPP (1)

[0066] Where f is the benefit of the virtual power plant (VPP); R VPP and C VPP They are the total revenue and total cost of VPP internal operation respectively.

[0067] The total operating cost is expressed as:

[0068]

[0069] In the formula, C F is the operating cost of the thermal power unit; CWT and are the operation and maintenance cost of wind turbines and the penalty cost for wind abandonment; C PV and are the operation and maintenance cost of the photovoltaic unit and the penalty cost for abandonment of light; C ESS is the operation and maintenance cost of the energy storage equipment; C grid is the electricity cost of the interaction between VPP and the upper grid; C P2G is the operating cost of the P2G equipment; C CS is the carbon sequestration cost of VPP; a f 、b f and c f are fuel cost coefficient, P G,t is the total output power of the thermal power unit during period t; WT and δ PV are the operating cost coefficients of wind power generation and photovoltaic power generation, P WT,t and P PV,t are the power generation of wind turbines and photovoltaic units in time period t respectively; and are the penalty cost factors for wind and solar abandonment respectively; P WT,pre,t and P PV,pre,t are the predicted output power of wind power and photovoltaic power in time period t respectively; δ ESS is the operation and maintenance cost factor of the energy storage equipment, and are the charging and discharging power of the energy storage device in period t; buy,t and δ sell,t are the prices of electricity purchased and sold by VPP to the external power grid; P grid,buy,t and P grid,sell,t are the amount of electricity purchased and sold by VPP to the upper grid in period t; P2G is the operating cost coefficient of P2G, P P2G,t is the P2G energy consumption in time period t; CCS is the cost of storing unit carbon dioxide; N CCS,t is the amount of carbon dioxide that needs to be stored in time period t, as shown in formula (3):

[0070]

[0071] Where N P2G,t is the amount of carbon dioxide consumed by P2G in period t; η C The amount of carbon dioxide required to produce a unit of natural gas;

[0072] The total operating profit is expressed as:

[0073]

[0074] In the formula, R SE,t is the electricity sales revenue of VPP in period t; sell,t P is the price at which VPP sells electricity; VPP,t is the planned output power of VPP during period t. is the natural gas production in period t; P2G is the electroporation efficiency; H g is the calorific value of natural gas; S g is the price of natural gas per unit; R SG,t The income from participating in the natural gas market. GN,t is the net output power of the thermal power unit during period t; P CC,t is the total energy consumption of carbon capture equipment during period t; P bas and P opt,t are the basic energy consumption and operating energy consumption of carbon capture in period t respectively; P CO2 P is the energy consumption for treating unit carbon dioxide; GC,t Energy consumption of carbon capture provided for thermal power units.

[0075] S5. Update the speed and position of the particles according to formulas (7) and (8), and update the individual optimum and the group optimum.

[0076] v l,n+1 =wv l,n +c1r1(P best,l -x l,n )+c2r2(G best,n -x l,tn ) (7)

[0077]

[0078]

[0079] Among them, v l,n+1 is the velocity of particle l at the next iteration n+1; v l,t＝n is the speed of particle l in the current iteration n, w is the inertia weight, which controls the degree of particle speed retention and affects the global search ability of the algorithm; c1 and c2 are acceleration coefficients, which represent the individual learning factor and social learning factor, respectively, and control the degree to which the particle approaches the individual optimum and the global optimum; r1 and r2 are random numbers in the interval [0,1], which add randomness to the algorithm; P best,l is the individual optimal position found by particle l so far; G best,n is the global optimal position found by the entire particle swarm so far; x l,n+1 is the position of particle l at the next iteration n+1; x l,n is the velocity of particle l at the current iteration n; ρ n is the inertia weight; ρmax and ρ min are the maximum and minimum values ​​of the inertia weight respectively; R1 controls the amplitude of the sine and cosine functions and can be flexibly adjusted according to the iterative process; a is a set constant, which is 2 in this embodiment; R2, R3 and R4 represent three random numbers that obey a uniform distribution; N is the total number of iterations.

[0080] S6. Recalculate the fitness value of each particle and record it for archiving.

[0081] S7, determine whether the number of termination iterations has been reached, if it has been reached, go to step S11, if not, go to step S8 to perform the next step.

[0082] S8. If the termination number of iterations is not reached, further determine whether the fitness value of the particle has not changed in the continuous m iterations. If not, return to step S5, update the speed and position of the particle according to formulas (7) and (8), update the individual optimal and group optimal, and if so, update the speed of each particle; specifically, when the position of the particle changes and the fitness value of the particle remains unchanged during the continuous m iterations, update the speed of each particle according to the speed correction formula of formula (10):

[0083]

[0084] Among them, v l,n+1 It represents the speed of the next iteration n+1 of the lth particle, l represents the lth particle, n represents the current iteration, and m represents the set number of consecutive iterations.

[0085] S9. Calculate the self-conduction rate (SCR) of the particles and select the inferior particles according to the SCR value.

[0086] Specifically, in order to avoid falling into the local optimum in the process of finding the optimal solution, the self-conductivity of the particle is calculated according to formula (11);

[0087]

[0088] Among them, SCR(l,n) is the ratio of the change in the individual optimal fitness of the lth particle in the first q iterations to the change in the global optimal individual fitness at the nth iteration; f() represents the fitness function.

[0089] S10, generate a random number for each dimension of the inferior particle. If the generated random number is smaller than the variation value of the particle dimension, replace the value of the dimension of the inferior particle with the value of the dimension corresponding to the optimal individual particle, and then return to step S4 to continue iteration.

[0090] S11. End the optimization process and output the optimization result, which is the optimal virtual power plant scheduling plan.

[0091] Specifically, the values ​​of some dimensions of the detected inferior particles are changed with a certain probability, so that the inferior particles escape from the current inferior area; when the SCR value is 0 or infinite, it means that it is currently in a local optimal state; based on the idea of ​​genetic variation, the positions of the screened inferior particles and the global optimal particles are exchanged with a certain probability.

[0092] Before applying the method of this embodiment, Matlab software was used for simulation analysis. In order to verify the effectiveness and rationality of the method proposed in the present invention, it was compared with the traditional PSO algorithm, differential evolution algorithm (DE), and grey wolf optimizer algorithm (GWO). In order to simulate the high dimensionality and nonlinearity of the virtual power plant model, three 30-dimensional test functions shown in formula (12) were selected for testing. Figure 3 It can be seen from the trend of the iteration curve that, compared with the other three solving algorithms, the method proposed in the present invention can converge at the fastest speed and the convergence value is the smallest when solving the test function, indicating that the convergence speed is the fastest and the convergence accuracy is the highest among the concentrated comparison algorithms, proving that the present method has higher solution accuracy and solution speed.

[0093]

[0094] In order to verify the application of the algorithm proposed in this invention in virtual power plants, the following Figure 4 The virtual power plant model shown in Figure 5 The original power generated by wind power and photovoltaic power and the load power of the virtual power plant shown in the four typical days are input into the above virtual power plant model.

[0095] Figure 6 The figure shows the solution result of the third typical day in the virtual power plant. The thermal power unit generates more electricity and emits less carbon, which is because the carbon capture equipment in the virtual power plant absorbs most of the carbon dioxide produced by the thermal power unit. In addition, under the incentive of the carbon-green certificate coupling trading mechanism, the virtual power plant has increased the utilization of renewable energy in the system in order to reduce costs, and sold the excess electricity in the system to the external power grid to earn profits. It can be seen that the method proposed in the present invention can be well applied to the optimization and scheduling of virtual power plants.

[0096] This embodiment also provides a virtual power plant optimization scheduling system for implementing the above method, including: a data acquisition module, a particle swarm optimization module and a self-conductivity calculation module.

[0097] The data acquisition module is used to collect the power generation and related load power of all units in the virtual power plant and perform data preprocessing.

[0098] The particle swarm optimization module is used to optimize virtual power plant scheduling using a particle swarm optimization algorithm based on the collected data.

[0099] The self-conductivity calculation module is used to be called by the particle swarm optimization module to calculate the self-conductivity of particles and select inferior particles according to the value of SCR.

[0100] This embodiment further provides a computer device, including: at least one processor, at least one memory, and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, the above method is implemented.

[0101] This embodiment further provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above method is implemented.

[0102] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0103] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

Claims

1. A virtual power plant optimization scheduling method based on particle swarm algorithm, characterized in that: With the goal of obtaining the optimal virtual power plant scheduling plan, the particle swarm optimization algorithm is used to optimize the virtual power plant scheduling plan, including the following steps: S1. Obtain the power generation power and related load power of all units in the virtual power plant and perform data preprocessing; S2. Input the relevant parameters of the particle swarm optimization algorithm, including population size, number of iterations and inertia weight; each particle in the particle swarm optimization algorithm represents a scheduling scheme; S3, initialize the position and velocity of the particle; S4, calculate the fitness value of each particle and record it for archiving; S5, update the speed and position of particles, update the individual optimum and group optimum; S6, recalculate the fitness value of each particle and record it for archiving; S7, determine whether the number of termination iterations has been reached, if yes, go to step S11, otherwise go to step S8; S8, judging whether the fitness value of the particle has not changed in the continuous m iterations, otherwise returning to step S5, if yes, updating the speed of each particle; S9, calculate the self-conductivity SCR of the particles, and select the inferior particles according to the SCR value; S10, generate a random number for each dimension of the inferior particle respectively. If the generated random number is smaller than the variation value of the particle dimension, replace the value of the dimension of the inferior particle with the value of the dimension corresponding to the optimal individual particle, and then return to step S4 to continue iteration; S11. End the optimization process and output the optimization result, which is the optimal virtual power plant scheduling plan.

2. The virtual power plant optimization scheduling method based on particle swarm algorithm according to claim 1 is characterized in that: In step S1, when performing data preprocessing, abnormal parameters are screened out and several groups of 24-hour parameters are randomly selected as verification data.

3. The virtual power plant optimization scheduling method based on particle swarm algorithm according to claim 1 is characterized in that: In step S4, the fitness value of each particle is calculated using the fitness function of formula (1): f=R VPP -C VPP (1) Where, f is the benefit of the virtual power plant VPP; R VPP and C VPP They are the total revenue and total cost of VPP internal operation; The total operating cost is expressed as: In the formula, C F is the operating cost of the thermal power unit; C WT and are the operation and maintenance cost of wind turbines and the penalty cost for wind abandonment; C PV and are the operation and maintenance cost of the photovoltaic unit and the penalty cost for abandonment of light; C ESS is the operation and maintenance cost of the energy storage equipment; C grid is the electricity cost of the interaction between VPP and the upper grid; C P2G is the operating cost of the P2G equipment; C CS is the carbon sequestration cost of VPP; a f 、b f and c f are fuel cost coefficient, P G,t is the total output power of the thermal power unit during period t; WT and δ PV are the operating cost coefficients of wind power generation and photovoltaic power generation, P WT,t and P PV,t are the power generation of wind turbines and photovoltaic units in time period t respectively; and are the penalty cost factors for wind and solar abandonment respectively; P WT,pre,t and P PV,pre,t are the predicted output power of wind power and photovoltaic power in time period t respectively; δ ESS is the operation and maintenance cost factor of the energy storage equipment, and are the charging and discharging power of the energy storage device in period t; buy,t and δ sell,t are the prices of electricity purchased and sold by VPP to the external power grid; P grid,buy,t and P grid,sell,t are the amount of electricity purchased and sold by VPP to the upper grid in period t; P2G is the operating cost coefficient of P2G, P P2G,t is the P2G energy consumption in time period t; CCS is the cost of storing unit carbon dioxide; N CCS,t is the amount of carbon dioxide that needs to be stored in time period t, as shown in formula (3): Where N P2G,t is the amount of carbon dioxide consumed by P2G in period t; η C The amount of carbon dioxide required to produce a unit of natural gas; The total operating profit is expressed as: In the formula, R SE,t is the electricity sales revenue of VPP in period t; sell,t P is the price at which VPP sells electricity; VPP,t is the planned output power of VPP during period t. is the natural gas production in period t; P2G is the electroporation efficiency; H g is the calorific value of natural gas; S g is the price of natural gas per unit; R SG,t The income from participating in the natural gas market. GN,t is the net output power of the thermal power unit during period t; P CC,t is the total energy consumption of carbon capture equipment during period t; P bas and P opt,t are the basic energy consumption and operating energy consumption of carbon capture in period t respectively; P CO2 P is the energy consumption for treating unit carbon dioxide; GC,t Energy consumption of carbon capture provided for thermal power units.

4. The virtual power plant optimization scheduling method based on particle swarm algorithm according to claim 1 is characterized in that: In step S5, the speed and position of the particles are updated according to formulas (7) and (8), and the individual optimum and the group optimum are updated; v l,n+1 =wv l,n +c1r1(P best,l -x l,n )+c2r2(G best,n -x l,tn ) (7) Among them, v l,n+1 is the velocity of particle l at the next iteration n+1; v l,t＝n is the speed of particle l in the current iteration n, w is the inertia weight of particle speed change, which controls the degree of particle speed retention; c1 and c2 are acceleration coefficients, which represent individual learning factors and social learning factors, respectively, and control the degree to which particles approach individual optimality and global optimality; r1 and r2 are random numbers in the interval [0,1]; P best,l is the individual optimal position found by particle l so far; G best,n is the global optimal position found by the entire particle swarm so far; x l,n+1 is the position of particle l at the next iteration n+1; x l,n is the velocity of particle l at the current iteration n; ρ n is the inertia weight of particle position change; ρ max and ρ min are the maximum and minimum values ​​of the inertia weight respectively; R1 controls the amplitude of the sine and cosine functions and can be adjusted according to the iterative process; a is a set constant; R2, R3 and R4 represent three random numbers that obey a uniform distribution; N is the total number of iterations.

5. The virtual power plant optimization scheduling method based on particle swarm algorithm according to claim 1 is characterized in that: In step S8, when the position of a particle changes and the fitness value of the particle remains unchanged during the m consecutive iterations, the speed of each particle is updated according to the speed correction formula of formula (10); Among them, v l,n+1 It represents the speed of the next iteration n+1 of the lth particle, l represents the lth particle, n represents the current iteration, and m represents the set number of consecutive iterations.

6. The virtual power plant optimization scheduling method based on particle swarm algorithm according to claim 1 is characterized in that: In step S9, in order to avoid falling into the local optimum in the process of finding the optimal solution, the self-conductivity of the particle is calculated according to formula (11); Among them, SCR(l,n) is the ratio of the change in the individual optimal fitness of the lth particle in the first q iterations to the change in the global optimal individual fitness at the nth iteration; f() represents the fitness function.

7. The virtual power plant optimization scheduling method based on particle swarm algorithm according to claim 1 is characterized in that: In step S10, the values ​​of some dimensions of the detected inferior particles are changed with a certain probability, so that the inferior particles escape from the current inferior area; when the value of SCR is 0 or infinite, it indicates that it is currently in a local optimal state; based on the idea of ​​genetic variation, the positions of the screened inferior particles and the global optimal particles are exchanged with a certain probability.

8. A virtual power plant optimization scheduling system for implementing the method according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, used to collect the power generation and related load power of all units in the virtual power plant and perform data preprocessing; A particle swarm optimization module, which is used to optimize virtual power plant scheduling using a particle swarm optimization algorithm based on the collected data; and The self-conductivity calculation module is used to be called by the particle swarm optimization module to calculate the self-conductivity of particles and select inferior particles according to the SCR value.

9. A computer device, characterized in that: include: At least one processor, at least one memory and computer program instructions stored in the memory, when the computer program instructions are executed by the processor, implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images