Virtual power plant economic optimization scheduling method based on fusion optimization algorithm

Abstract

The application discloses a virtual power plant economic optimization scheduling method based on a fusion optimization algorithm and belongs to the technical field of virtual power plant energy scheduling.The application aims at the problem that the existing power scheduling algorithm lacks the ability of fully scheduling distributed resources and flexible loads and cannot obtain the optimal power load distribution scheme.The application comprises the following steps: obtaining a predicted target time load value, a target time photovoltaic power generation output value, a target time wind power generation output value, distributed energy storage device charging and discharging potential data and distributed energy storage device constraint conditions; establishing a virtual power plant economic optimization target function; and adopting a moss colony optimization algorithm to perform power supply scheduling distribution at the target time, so that the common power distribution output of the distributed photovoltaic power generation device, the distributed wind power generation device, the distributed thermal power unit and the distributed energy storage device meets the target time load value and the optimal economic performance is obtained.The application is used for virtual power plant economic optimization scheduling.

Description

TECHNICAL FIELD

[0001] The present application relates to a virtual power plant economic optimization scheduling method based on a fusion optimization algorithm, and belongs to the technical field of virtual power plant energy scheduling. BACKGROUND

[0002] With the rapid development of economy and the continuous growth of population, the demand for electricity is increasing, and renewable energy is developing rapidly. Photovoltaic power generation is gradually changing from centralized to distributed and coexisting with centralized, and together with wind power generation, it has gradually become an important part of the power system. However, due to the frequent fluctuations in renewable energy output, its reliability is poor, and it has strong indirectness and instability. The instability of the output will bring great difficulties to the grid peak regulation and frequency modulation. Renewable energy has brought challenges to the development of the power system, such as demand side management, grid stability, and other problems that need to be solved.

[0003] In order to further enhance the competitiveness of distributed energy in the electricity market and strengthen the control of distributed energy, by organically integrating distributed energy, energy storage systems and traditional power systems, the energy utilization efficiency is improved, and the flexibility and stability of the power system are enhanced.

[0004] The emergence of virtual power plants is an innovation of the traditional power system mode. Through intelligent technology and network connection, centralized management and optimal scheduling of energy are realized. The traditional power dispatching algorithm lacks the ability to fully dispatch distributed resources and flexible loads when facing the complexity of the virtual power plant VPP system, and often cannot balance economic benefits, emission reduction and energy utilization efficiency. Therefore, under the premise of ensuring the stable operation of the power system, the economic benefits need to be maximized, and a virtual power plant economic optimization scheduling method is needed. SUMMARY

[0005] In view of the problem that the existing power dispatching algorithm lacks the ability to fully dispatch distributed resources and flexible loads, and cannot obtain the optimal scheme of power load distribution, the present application provides a virtual power plant economic optimization scheduling method based on a fusion optimization algorithm.

[0006] The virtual power plant economic optimization scheduling method based on the fusion optimization algorithm of the present application comprises,

[0007] According to the historical load data of the virtual power plant, the load value at the target time is predicted by an ensemble learning algorithm. At the same time, according to the photovoltaic power generation related data, the photovoltaic power generation output value of the distributed photovoltaic power generation equipment at the target time is predicted by an ensemble learning algorithm, and according to the wind power generation related data, the wind power generation output value of the distributed wind power generation equipment at the target time is predicted by an ensemble learning algorithm;

[0008] The charging and discharging potential data of the distributed energy storage equipment is obtained, and the constraint conditions of the distributed energy storage equipment are determined;

[0009] According to the load value at the target moment, the photovoltaic power generation output value at the target moment, the wind power generation output value at the target moment, the charge-discharge potential data, and the constraint conditions of the distributed energy storage device and the economic optimization target function of the virtual power plant, the moss colony optimization algorithm is used for power supply scheduling distribution at the target moment, so that the common power distribution output of the distributed photovoltaic power generation device, the distributed wind power generation device, the distributed thermal power unit and the distributed energy storage device meets the load value at the target moment, and the optimal economic performance is obtained.

[0010] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm, the prediction method of the photovoltaic power generation output value at the target moment comprises:

[0011] According to the influence of the corresponding historical moment sunshine intensity, temperature and terrain condition, and in combination with the meteorological data, the target moment photovoltaic power generation output value of the distributed photovoltaic power generation device is predicted;

[0012] According to the influence of the corresponding historical moment wind speed, wind direction and humidity, and in combination with the meteorological data, the target moment wind power generation output value of the distributed wind power generation device is predicted.

[0013] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm, the charge-discharge potential data of the distributed energy storage device comprises a state of charge, a state of health, a voltage and a current;

[0014] The time characteristics and derivative variables of the charge-discharge potential data are extracted;

[0015] The state of charge at the target moment is predicted based on the corresponding historical data by using a random forest model;

[0016] The time characteristics are predicted based on the corresponding historical data by using an LSTM model, and the dynamic change of the charge-discharge potential data is captured.

[0017] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm, the constraint conditions of the distributed energy storage device comprise:

[0018] Energy balance constraint:

[0019] E t+1 = E t + η charge · P charge,t - η dlischarge · P dlscharge,t ,

[0020] In the formula, E t+1 is the reserve energy of the distributed energy storage device at t+1 moment, E t is the reserve energy of the distributed energy storage device at t moment, η charge is the charging efficiency of the distributed energy storage device, and Pcharge,t is the charging rate of the distributed energy storage device at time t, η dlischarge is the energy release efficiency of distributed energy storage equipment, P dlscharge,t is the energy release rate of the distributed energy storage device at time t;

[0021]

[0022] In the formula is the maximum charging rate, is the maximum energy release rate;

[0023] E min ≤E t ≤E max ,

[0024] Where E min is the minimum value of reserve energy, E max The maximum value of reserve energy.

[0025] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm of the present invention, the virtual power plant economic optimization objective function is:

[0026] minM total =C OM +C fuel +C gridbuy +C gridsell +C storge +C L +C CO2 ,

[0027] Where M total is the total cost of power distribution, C OM is the total power generation cost, C fuel is the fuel cost, C gridbuy is the cost of purchasing electricity from the upper grid, C gridsell is the cost of selling electricity to the upper grid, C storge is the energy storage cost, C L The compensation cost for dispatching thermal power units, C CO2 The cost of carbon emissions.

[0028] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm of the present invention, the moss colony optimization algorithm includes:

[0029] Define decision variables I i :

[0030] I i =[P load ,P pv-i ,P wind-i , P Gt-i , P battery-i ],

[0031] i = 1, 2, 3, …, n;

[0032] Definition of the moss population F:

[0033] F = [I1, I2, …, In], n ],

[0034] In the formula, P load is the load power, which is determined according to the target time load value, P pv-i is the photovoltaic power in the i th power supply scheduling allocation strategy, which is determined according to the target time photovoltaic power generation output value, P wind-i is the wind power in the i th power supply scheduling allocation strategy, which is determined according to the target time wind power generation output value, P Gt-i is the thermal power in the i th power supply scheduling allocation strategy, P battery-i is the energy storage power in the i th power supply scheduling allocation strategy, which is determined according to the charging and discharging potential data;

[0035] Moss population initialization is performed, and the moss population F is randomly generated in the value range of the decision variable I i as a moss individual;

[0036] Iterative calculation: the fitness value of the moss individual I i on each target of the virtual power plant economic optimization target function is calculated, and an initial Pareto optimal solution set is obtained;

[0037] The moss individual with the fitness value greater than the fitness threshold in the initial Pareto optimal solution set on each target is selected, the solution space is expanded to a better area, new moss individuals are found to join the initial Pareto optimal solution set, so that the initial Pareto optimal solution set is concentrated to the optimal solution area, and the moss individuals in the concentrated Pareto optimal solution set reach the target number;

[0038] The current position and fitness value information of each moss individual in the concentrated Pareto optimal solution set are shared between the moss individuals, and the moss individual with the fitness value greater than the fitness threshold is reserved through the competition mechanism, so that the number of moss individuals in the concentrated Pareto optimal solution set is equal to the number of moss individuals in the initial Pareto optimal solution set. Return to the next round of iterative calculation until the termination condition is met;The power supply scheduling allocation strategy corresponding to the moss individual with the maximum fitness value on each target in the final Pareto optimal solution set is selected as the final power supply scheduling allocation strategy.

[0039] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm, the fitness matrix F0 of the moss population F is:

[0040]

[0041] wherein F n4 represents the fitness value of the nth moss individual on the 4th target;

[0042] In the initial Pareto optimal solution set sorting, the dominance relationship between moss individuals is represented by an indication matrix D, if moss individual i dominates moss individual i', then D ii′ = 1, otherwise D ii′ = 0; i' = 1, 2, 3, …, n;

[0043]

[0044] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm, assuming that the number of moss individuals with fitness values greater than the fitness threshold on each target in the initial Pareto optimal solution set is m, the m moss individuals are expanded to a more optimal region in the solution space, and the updated position I new is represented as:

[0045] I new = I + Δ,

[0046] I = [I1, I2, …, In] ; m

[0047] wherein Δ is an individual expansion quantity matrix:

[0048]

[0049] wherein δ m is the expansion quantity of the mth moss individual.

[0050] According to the virtual power plant economic optimization scheduling method based on the fusion optimization algorithm,

[0051] F max and F min are set as the maximum fitness value and the minimum fitness value of each target, and the calculation method of the normalized standardized fitness value F ij ' is:

[0052]

[0053] wherein j = 1, 2, 3, 4;

[0054] The standardized fitness value F ij ' is located in the interval [0, 1];

[0055] The competition mechanism is realized by operating the fitness matrix F0, and each value in the fitness matrix F0 is normalized to form a new matrix R:​

[0056]

[0057] In the competition phase, the position I of the reserved moss individual is selected according to the value of R final is:

[0058] I final = I[R>τ],

[0059] Wherein, τ is a set fitness threshold.

[0060] The economic optimization scheduling method of the virtual power plant based on the fusion optimization algorithm according to the present application, the termination condition is that the mutation rate is less than the mutation rate threshold:

[0061]

[0062] In the formula Is the optimal fitness value of the Tth iteration.

[0063] The present application has the following advantages: the present application can solve the problem of lack of sufficient scheduling ability for distributed resources and flexible loads in the existing scheduling algorithm, and the power supply scheduling distribution strategy is selected by the moss colony optimization algorithm, so that the optimal load scheme is output while ensuring the stability and economy of the virtual power plant, and the distribution scheme of each distributed resource is adjusted according to the load scheme output by the virtual power plant, thereby improving the economy and stability of the virtual power plant. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 Is the overall flowchart of the economic optimization scheduling method of the virtual power plant based on the fusion optimization algorithm according to the present application;

[0065] Figure 2 Is the wind power output value prediction flowchart;

[0066] Figure 3 Is the photovoltaic power output value prediction flowchart;

[0067] Figure 4 Is the virtual power plant load prediction flowchart;

[0068] Figure 5 Is the moss colony optimization algorithm flowchart. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0070] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0071] The present application will be further described below in conjunction with the drawings, but not as a limitation of the present application.

[0072] In conjunction with Figures 1 to 4 As shown in the drawings, the present application provides a virtual power plant economic optimization scheduling method based on fusion optimization algorithm, comprising,

[0073] According to the historical load data of the virtual power plant, the load value at the target time is predicted by the ensemble learning algorithm; at the same time, according to the related data of photovoltaic power generation, the photovoltaic power generation output value of the distributed photovoltaic power generation equipment at the target time is predicted by the ensemble learning algorithm, and according to the related data of wind power generation, the wind power generation output value of the distributed wind power generation equipment at the target time is predicted by the ensemble learning algorithm;

[0074] The charging and discharging potential data of the distributed energy storage equipment is obtained; and the constraint conditions of the distributed energy storage equipment are determined;

[0075] According to the load value at the target time, the photovoltaic power generation output value at the target time, the wind power generation output value at the target time, the charging and discharging potential data, the constraint conditions of the distributed energy storage equipment and the economic optimization target function of the virtual power plant, the moss colony optimization algorithm is used for power supply scheduling and distribution at the target time, so that the common power distribution output of the distributed photovoltaic power generation equipment, the distributed wind power generation equipment, the distributed thermal power unit and the distributed energy storage equipment meets the load value at the target time, and the optimal economic performance is obtained.

[0076] The present embodiment predicts the virtual power plant load and the distributed power generation output according to the historical load distribution of the virtual power plant and the performance parameters of the distributed power generation equipment, in combination with the local specific weather condition prediction information. By obtaining the state of the distributed energy storage equipment in the virtual power plant, the potential situation of the charging and discharging of the energy storage equipment is obtained. According to the prediction data information of the virtual power plant and the decision variables, the moss colony of the economic scheduling scheme of the virtual power plant is initialized; the fitness of the moss colony is calculated, and the Pareto optimal solution set is obtained according to the multi-objective function. According to the minimum value of each target in the Pareto optimal solution set, the moss individuals expand to the better area in the solution space according to their fitness values, and the Pareto solution set is concentrated to the optimal solution area; the moss individuals share their current position and fitness information, helping other individuals to refer to excellent scheduling strategies, and the moss individuals will compete, and the poor scheduling scheme is eliminated, and the scheme with higher fitness is retained; until the power supply scheduling and distribution strategy is finally determined.

[0077] In conjunction with Figure 2 and Figure 3As shown, the prediction method of the target time photovoltaic power generation output value includes:

[0078] According to the influence of the corresponding historical time sunshine intensity, temperature, and terrain condition on the distributed photovoltaic power generation equipment, combined with the meteorological data, the target time photovoltaic power generation output value of the distributed photovoltaic power generation equipment is predicted.

[0079] According to the influence of the corresponding historical time wind speed, wind direction, and humidity on the output power of the distributed wind power generation equipment, combined with the meteorological data, the target time wind power generation output value of the distributed wind power generation equipment is predicted.

[0080] The original data including historical meteorological data, geographical data, external influencing factors, and other variables are input into the base model of the integrated learning algorithm and introduced into the system. The data preprocessed by the base model are trained, and finally the integrated prediction results are processed to obtain the final distributed power generation equipment output prediction value. The joint probability distribution of the distributed power generation equipment output prediction value is shown in the following formula:

[0081] f(v,t,p,h)=C te ·C sh ·C in ·f v (v;k,λ)f t (t;μ t ,σ t )f p (p;μ p ,σ p )f h (h;μ h ,σ h )

[0082] Wherein, f t (t;μ t ,σ t ) is the probability distribution of temperature, f p (p;μ p ,σ p ) is the probability distribution of air pressure, f h (h;μ h ,σ h ) is the probability distribution of humidity, C te is the terrain correction coefficient, C sh is the error correction coefficient, and C in is the mutual influence correction coefficient between units.

[0083] Further, the constraint conditions in the embodiment include economic optimization constraint conditions of the multi-virtual power plant and network topology constraint conditions of the multi-virtual power plant.

[0084] The charge-discharge potential data of the distributed energy storage device includes state of charge (SOC), state of health (SOH), voltage and current;

[0085] extracting time features and derived variables of the charge-discharge potential data;

[0086] predicting the state of charge at the target time based on the corresponding historical data using a random forest model;

[0087] using an LSTM model to predict the time features based on the corresponding historical data, capturing the dynamic changes of the charge-discharge potential data.

[0088] In this embodiment, the constraint conditions of the distributed energy storage device include:

[0089] Energy balance constraint:

[0090] E t+1 = E t + η charge · P charge,t - η dlischarge · P dlscharge,t ,

[0091] where E t+1 is the reserve energy of the distributed energy storage device at t+1, E t is the reserve energy of the distributed energy storage device at t, η charge is the charging efficiency of the distributed energy storage device, P charge,t is the charging rate of the distributed energy storage device at t, η dlischarge is the discharging efficiency of the distributed energy storage device, P dlscharge,t is the discharging rate of the distributed energy storage device at t;

[0092] The charging and discharging power constraints of the energy storage device are as follows:

[0093]

[0094] where P is the maximum charging rate, is the maximum discharging rate;

[0095] The energy storage constraints of the energy storage device are as follows:

[0096] E min ≤ E t ≤ E max ,

[0097] where E min is the minimum reserve energy, E max is the maximum reserve energy.

[0098] The above obtained energy storage device information is a necessary constraint condition for optimization scheduling.

[0099] Still further, the virtual power plant economic optimization objective function is:

[0100] min M total = C OM + C fuel + C gridbuy + C gridsell + C storge + C L + C CO2 ,

[0101] where M total is the total distribution cost, C OM is the total generation cost, C fuel is the fuel cost, C gridbuy is the purchase cost from the upper-level power grid, C gridsell is the sale cost to the upper-level power grid, C storge is the energy storage cost, C L is the thermal power unit dispatch compensation cost, C CO2 is the carbon emission cost.

[0102] The moss optimization algorithm of the embodiment proposes the following rules according to the growth and ecological behavior of mosses in nature:

[0103] (1) In the algorithm, the fitness value of an individual is equivalent to the survival ability of a moss individual. A high-fitness individual represents a better solution in the target optimization, simulating the process of natural selection.

[0104] (2) Mosses occupy new areas through reproduction and expansion. Through individual expansion, individuals move to better positions in the solution space according to their fitness.

[0105] (3) Moss individuals can communicate with each other through chemical signals or other means to help each other find better growth conditions. Individuals in the moss algorithm share their fitness and position information, helping other individuals to learn from excellent strategies, thereby enhancing the overall search capability.

[0106] (4) As moss individuals expand, the moss colony gradually increases, and the number of candidate solutions in the solution space also increases. To prevent too many solutions or poor-quality solutions from occupying resources, a competition mechanism is introduced in the moss optimization algorithm: in the solution space, nutrients are limited, and moss individuals will compete for nutrient resources. If a moss individual has a lower fitness than its surrounding individuals, it will lose nutrients and decline, or even die.

[0107] (5) By comparing the fitness values of moss individuals, poor-fitness individuals are screened and eliminated, and high-fitness individuals are retained. This process can reduce the computational overhead of the algorithm, while promoting the concentration of moss individuals to the optimal solution area.

[0108] (6) Moss can quickly adjust its growth strategy when facing environmental changes. In the dynamic adjustment mechanism of the algorithm, individuals constantly update their positions and strategies according to environmental and fitness changes to avoid local optimization.

[0109] The present embodiment uses the moss optimization algorithm to optimize for economic benefits, obtaining a scheduling scheme with the lowest operating cost for the virtual power plant.

[0110] The initial stage of the moss optimization algorithm is similar to planting moss. A certain number of candidate solutions, called "moss individuals", are randomly generated in the solution space. These individuals can be regarded as the initial colonies of moss. Each moss individual corresponds to a specific solution, and its position is determined by the decision variables of the problem.

[0111] In combination Figure 5 As shown in the figure, the moss colony optimization algorithm includes:

[0112] Define decision variable I i :

[0113] I i =[P load ,P pv-i ,P wind-i ,P Gt-i ,P battery-i ],

[0114] i=1,2,3,……,n;

[0115] Set the parameters of the moss optimization algorithm and initialize the population. Assume that the initial population size is F, and the initial population is randomly generated within the value range of the decision variables. Each individual represents a possible scheduling strategy. The initial individuals are generated based on historical data.

[0116] Define the moss population F:

[0117] F=[I1,I2,...,I n ],

[0118] In the formula, P load is the load power, which is determined according to the load value at the target time, P pv-i is the photovoltaic power in the i-th power supply scheduling allocation strategy, which is determined according to the photovoltaic power output value at the target time, P wind-i is the wind power in the i-th power supply scheduling allocation strategy, which is determined according to the wind power output value at the target time, P Gt-i is the thermal power in the i-th power supply scheduling allocation strategy, and P battery-i is the energy storage power in the i-th power supply scheduling allocation strategy, which is determined according to the charging and discharging potential data.

[0119] Moss population initialization, randomly generate moss population F in the value range of decision variables, decision variables I i As a moss individual;

[0120] Iterative calculation: calculate the moss individual I i The fitness value of each target of the virtual power plant economic optimization objective function is obtained, and the initial Pareto optimal solution set is obtained;

[0121] Select the moss individual in the initial Pareto optimal solution set whose fitness value in each target is greater than the fitness threshold, expand to the better area of the solution space, find new moss individuals to join the initial Pareto optimal solution set, and concentrate the initial Pareto optimal solution set to the optimal solution area, until the number of moss individuals in the concentrated Pareto optimal solution set reaches the target number;

[0122] Make each moss individual in the concentrated Pareto optimal solution set share the current position and fitness value information of each moss individual, and retain the moss individual with a fitness value greater than the fitness threshold through the competition mechanism, so that the number of moss individuals in the concentrated Pareto optimal solution set is equal to the number of moss individuals in the initial Pareto optimal solution set; return to the next round of iterative calculation until the termination condition is met; select the power supply scheduling allocation strategy corresponding to the moss individual with the maximum fitness value in each target in the final Pareto optimal solution set as the final power supply scheduling allocation strategy.

[0123] The fitness function is defined according to the objective function of the problem, and is usually measured by economic efficiency, cost, emission, renewable energy utilization rate and other multiple targets to evaluate the performance of each solution in virtual power plant scheduling. For multi-objective optimization problems, the fitness function can consider multiple objectives to achieve balanced optimization of multiple objectives. By calculating the fitness value of each individual in each target, its performance in a specific target can be evaluated. It helps to determine which individual performs better in meeting different targets. Evaluating the fitness value can help select and retain outstanding individuals in each iteration. High fitness individuals will be preferentially retained to enhance the overall performance of the population, assuming that there are n individuals in the population, and each individual has 4 objective functions in this embodiment.

[0124] In this embodiment, the fitness matrix F0 of the moss population F is:

[0125]

[0126] In the formula, F n4 represents the fitness value of the nth moss individual in the fourth target;

[0127] Adaptive evaluation allows the algorithm to identify non-dominated solutions and form the Pareto front. Individuals on the Pareto front represent the best trade-off between different objectives, providing the decision maker with a variety of choices.

[0128] In the initial Pareto optimal solution set sorting, the dominance relationship between the moss individuals is represented by the indicator matrix D. If moss individual i dominates moss individual i', then D ii′ = 1, otherwise D ii′ = 0; i' = 1, 2, 3,..., n.

[0129]

[0130] Moss individuals will expand like moss plants, growing towards better areas in the solution space. This process is achieved through the expansion mechanism, i.e. each moss individual selects the best expansion direction based on the surrounding environment and nutrient distribution. Generally, moss individuals will tend to grow in areas with more nutrients and higher fitness, and the expansion step determines the distance the moss individual moves in each expansion process. The expansion of individuals can be achieved through vector and matrix operations.

[0131] Assuming that the number of moss individuals with fitness values greater than the fitness threshold on each objective in the initial Pareto optimal solution set is m, then the m moss individuals expand to better areas in the solution space, and the updated positions I new are represented as:

[0132] I new = I + Δ,

[0133] I = [I1, I2,..., In]; m

[0134] where Δ is the individual expansion amount matrix:

[0135]

[0136] where δ m is the expansion amount of the mth moss individual.

[0137] The step size in the moss optimization algorithm is dynamically adjusted. Generally, the step size is larger at the beginning to perform global search, and gradually decreases to local search as the algorithm iterates. In each iteration, the moss individual moves in the solution space according to the expansion direction and step size, generating a new moss position.

[0138] In the information sharing process, individuals can communicate through the maximum and minimum values of the fitness matrix.

[0139] Let F max and F min ​The maximum fitness value and minimum fitness value of each target, the normalized fitness value F ij The calculation method of ′ is:

[0140]

[0141] Where j = 1, 2, 3, 4;

[0142] Normalized fitness value F ij ′ is in the interval [0, 1]; it is convenient for comparing and sharing information.

[0143] The competition mechanism is implemented by operating the fitness matrix F0. Each value in the fitness matrix F0 is normalized to form a new matrix R:

[0144]

[0145] In the competition phase, the position I of the retained moss individual is selected according to the value of R final for:

[0146] I final =I[R>τ],

[0147] Where τ is the set fitness threshold.

[0148] The termination condition is that the mutation rate is less than the mutation rate threshold ∈:

[0149] If after several consecutive iterations, the change in fitness of all individuals is less than the set threshold ∈, then the improvement is considered insufficient and the algorithm terminates:

[0150]

[0151] In the formula is the optimal fitness value of the Tth iteration.

[0152] Determining insufficient improvement is a key termination mechanism for the Moss algorithm. By monitoring the change in fitness or population diversity, the algorithm can be judged as stagnant. This ensures that the algorithm terminates appropriately when nearing the optimal solution, avoiding unnecessary computation while maintaining a certain level of global search capability.

[0153] While the application has been described with reference to particular embodiments thereof, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present application. It will be apparent to those skilled in the art that numerous modifications can be made within the scope of the present application as defined by the appended claims. It is intended that all such modification fall within the spirit and scope of the present application. It will be understood that the features described in connection with one embodiment can be used in connection with another embodiment.

Claims

1. A method for economic optimal scheduling of a virtual power plant based on a fusion optimization algorithm, characterized in that Comprising, According to the virtual power plant historical load data, the target time load value is predicted by an ensemble learning algorithm; meanwhile, according to the photovoltaic power generation related data, the target time photovoltaic power generation output value of the distributed photovoltaic power generation equipment is predicted by an ensemble learning algorithm, and according to the wind power generation related data, the target time wind power generation output value of the distributed wind power generation equipment is predicted by an ensemble learning algorithm; The charging and discharging potential data of the distributed energy storage equipment are acquired; and the constraint conditions of the distributed energy storage equipment are determined; According to the target time load value, the target time photovoltaic power generation output value, the target time wind power generation output value, the charging and discharging potential data, the constraint conditions of the distributed energy storage equipment and the virtual power plant economic optimization objective function, the moss colony optimization algorithm is used for power supply scheduling and distribution at the target time, so that the common power distribution output of the distributed photovoltaic power generation equipment, the distributed wind power generation equipment, the distributed thermal power unit and the distributed energy storage equipment meets the target time load value, and the optimal economic performance is obtained; The constraint conditions of the distributed energy storage equipment include: Energy balance constraint: E t+1 = E t + η charge · P charge,t - η dlischarge · P dlscharge,t , E t+1 is the reserve energy of the distributed energy storage device at time t+1, E t is the reserve energy of the distributed energy storage device at time t, E charge is the charging efficiency of the distributed energy storage device, P charge,t is the charging rate of the distributed energy storage device at time t, P dlischarge is the discharging efficiency of the distributed energy storage device, P dlscharge,t is the discharging rate of the distributed energy storage device at time t. wherein is the maximum rate of charging, is the maximum rate of discharging; E min ≤E t ≤E max , where E min is the minimum reserve energy, E max is the maximum reserve energy; The virtual power plant economic optimization objective function is: minM total = C OM + C fuel + C gridbuy + C gridsell + C storge + C L + C CO2 , In the formula, M total is the total cost of power distribution, C OM is the total generation cost, C fuel is the fuel cost, C gridbuy is the purchase cost of electricity from the upper grid, C gridsell is the sale cost of electricity to the upper grid, C storge is the energy storage cost, C L is the thermal power unit scheduling compensation cost, C CO2 is the carbon emission cost; The moss colony optimization algorithm includes: Defining decision variable I i : I i = [P load , P pv-i , P wind-i , P Gt-i , P battery-i ], i = 1, 2, 3, …, n; The fitness matrix F0 of the moss population F is defined as: F=[I1,I2,...,I n ], In the formula, P load is the load power, determined according to the load value at the target time, P pv-i is the photovoltaic power in the i th power supply scheduling allocation strategy, determined according to the photovoltaic power output value at the target time, P wind-i is the wind power in the i th power supply scheduling allocation strategy, determined according to the wind power output value at the target time, P Gt-i is the thermal power in the i th power supply scheduling allocation strategy, P battery-i is the energy storage power in the i th power supply scheduling allocation strategy, determined according to the charging and discharging potential data; The moss population initialization is performed, and the moss population F is randomly generated in the value range of the decision variable I i as a moss individual; Iterative calculation: Calculate the individual I of the moss i The fitness value on each target of the virtual power plant economic optimization target function is calculated, and an initial Pareto optimal solution set is obtained; In the formula, Δ is an individual expansion quantity matrix: ​ 2. The method of claim 1, wherein, ​ ​ ​ 3. The virtual power plant economic optimization scheduling method based on fusion optimization algorithm according to claim 2, characterized in that, ​ ​ ​ ​ 4. The virtual power plant economic optimization scheduling method based on fusion optimization algorithm according to claim 3, characterized in that, ​ where F n4 represents the fitness value of the nth moss individual on the 4th objective. In the initial Pareto optimal solution set sorting, the dominance relation between the individual mosses is represented by the indication matrix D, if the moss individual i dominates the moss individual i', then D ii′ = 1, otherwise D ii′ = 0; i' = 1, 2, 3, …, n; 5. The method of claim 4, wherein, Assuming that the number of the moss individuals whose fitness values on each objective in the initial Pareto optimal solution set are greater than the fitness threshold value is m, the m moss individuals expand to the better region in the solution space, and the updated position I new is represented as: I new = I + Δ, I = [I1, I2,..., In]T; (1) m ] ; (2) ​ where δ m is the spread of the mth moss individual.

6. The method of claim 5, wherein the fusion optimization algorithm-based economic optimal scheduling method of a virtual power plant is characterized in that, Set F max and F min The maximum fitness value and the minimum fitness value for each target, the normalized standardized fitness value F' ij The calculation method is as follows: wherein j = 1, 2, 3, 4; Standardized fitness value F' ij lies in the interval [0, 1]; The competition mechanism is realized by operating on the fitness matrix F0, and each value in the fitness matrix F0 is normalized to form a new matrix R: In the competition phase, the position I of the reserved moss individual is selected according to the value of R final is: I final = I[R > τ], wherein τ is a set fitness threshold.

7. The virtual power plant economic optimization scheduling method based on fusion optimization algorithm according to claim 6, characterized in that, The termination condition is that the mutation rate is less than a mutation rate threshold ∈: In the formula is the optimal fitness value for the Tth iteration.

Images