Optical storage and charging cooperative control method and system based on multi-energy complementation

Abstract

The invention provides an optical storage and charging cooperative control method and system based on multi-energy complementation. The method comprises the following sub-steps: respectively establishing a photovoltaic power generation model, an energy storage system model and a charging load model; acquiring historical illumination information, charging information and electricity price information, constructing a prediction model based on a neural network, and predicting and outputting illumination intensity, charging load demand power and electricity price in a future time period; constructing a target optimization function by taking the annual net cost and the power deviation rate as optimization targets; according to the method, the cooperative optimization control of the photovoltaic power generation, energy storage and charging system is realized, the annual net cost is reduced, the power deviation is reduced, the energy storage and charging cooperative control strategy is established, the target optimization function is solved by adopting the improved whale optimization algorithm, and the charging and discharging power sequence is generated according to the optimal solution obtained by solving and is input to the system for execution. And the operation efficiency and reliability of the whole system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic, storage and charging coordinated control, and in particular to a photovoltaic, storage and charging coordinated control method and system based on multi-energy complementarity. Background Art

[0002] The rapid growth in the number of new energy vehicles has gradually highlighted the problem of charging difficulties; in essence, this is the contradiction between the insufficient distribution capacity of charging stations and the growing demand for charging; the introduction of energy storage units, the use of photovoltaic self-generation for self-use, combined with energy transfer and load scheduling, can achieve power capacity expansion during peak electricity consumption periods, which is undoubtedly a key way to solve the charging problem in hot cities; the combination of energy storage, photovoltaics, and charging stations is called an integrated photovoltaic storage and charging system.

[0003] Publication number CN119726855A is a multi-energy coupling complementary photo-storage-charging management system, which includes a photovoltaic power generation module, an energy storage module including a lithium battery pack, a grid input terminal, an energy conversion module for converting photovoltaic power into storable power, an energy storage management module for monitoring and controlling the charging and discharging process of the energy storage equipment, an energy scheduling module for allocating photovoltaic power generation, energy storage module, and grid input power through a multi-energy coupling algorithm, a charging management module for controlling the stability of external output power, system control software integrating a multi-energy complementary control model and an energy efficiency optimization algorithm, and a data acquisition module for real-time collection of photovoltaic power generation, energy storage status, grid power supply, and load demand data.

[0004] The existing supplementary solar storage and charging system adopts the traditional multi-energy coupling algorithm, which has the defects of insufficient global search capability, easy to fall into local optimality, and slow convergence speed, resulting in insufficient energy scheduling accuracy. In addition, it lacks a dynamic SOC threshold adaptive adjustment mechanism and load priority management strategy, causing battery overcharging and over-discharging, accelerated life decay, and limited new energy consumption rate, reducing the operating efficiency and reliability of the overall system. Summary of the Invention

[0005] In view of this, the present invention proposes a photovoltaic, energy storage and charging coordinated control method and system based on multi-energy complementarity. By constructing an objective function with annual net cost and power deviation rate as optimization targets, and adopting an improved whale optimization algorithm to enhance the global optimization capability, combined with neural network prediction and dynamic SOC management, the coordinated optimization control of photovoltaic power generation, energy storage and charging systems is realized, which reduces the annual net cost, reduces the power deviation, and improves the operating efficiency and reliability of the overall system.

[0006] The technical solution of the present invention is implemented as follows: In a first aspect, the present invention provides a method for coordinated control of photovoltaic storage and charging based on multi-energy complementarity, the method comprising the following sub-steps:

[0007] S1, establish corresponding photovoltaic power generation model, energy storage system model and charging load model according to the photovoltaic power generation system, energy storage system and charging system respectively;

[0008] S2, obtains historical light information, historical charging information, and historical electricity price information, and builds a prediction model based on a neural network to predict and output the light intensity, charging load demand power, and electricity price in the future period;

[0009] S3, taking annual net cost and power deviation rate as optimization targets, uses linear weighting method to construct the target optimization function;

[0010] S4, based on the predicted future electricity prices, charging load demand power and light intensity data, formulates a photovoltaic storage and charging coordinated control strategy, uses the predicted data as the input of the control strategy, uses the improved whale optimization algorithm to solve the target optimization function, generates the charging and discharging power sequence according to the optimal solution obtained, and inputs it into the system for execution.

[0011] On the basis of the above technical solution, preferably, in step S1, corresponding photovoltaic power generation model, energy storage system model and charging load model are respectively established according to the photovoltaic power generation system, energy storage system and charging system, wherein,

[0012] The photovoltaic power generation model expression is:

[0013] P PV (t) = η PV (t)·A PV ·G(t)·[1-α(T(t))·(T(t)-T ref )]·f s (t)

[0014] Where η PV is the photoelectric conversion efficiency coefficient, η PV (t) = η PV，0 ·e -λt ,λ is the decay rate,η PV，0 is the initial value of the photoelectric conversion efficiency coefficient; A PV is the total area of the photovoltaic panel, G(t) is the light intensity at time t, T(t) is the ambient temperature at time t, T ref is the reference temperature for photovoltaic panel efficiency test, α is the temperature coefficient, P PV (t) is the photovoltaic output power;

[0015]

[0016] Where, f s (t) is the local shadow correction factor at time t, S i (t) is the area ratio of the i-th occluded area at time t, k iis the occlusion coefficient;

[0017] The energy storage system model expression is:

[0018]

[0019] Where SOC(t) is the state of charge of the energy storage battery at time t, η ch is the charging efficiency of the energy storage battery, η dis is the discharge efficiency of the energy storage battery, E max is the total capacity of the energy storage battery, Δt is the time interval, P ch (t) is the charging power of the energy storage battery at time t, P dis (t) is the discharge power of the energy storage battery at time t, is the maximum charging power of the energy storage battery, is the maximum discharge power of the energy storage battery, SOC min SOC is the lower limit dynamic threshold of the state of charge of the energy storage battery. min =SOC min，0 +ΔSOC SOH (t), SOC min，0 is the lower initial threshold of the state of charge of the energy storage battery, ΔSOC SOH (t) is the threshold offset of SOH, SOC max The upper dynamic threshold of the state of charge of the energy storage battery, SOC max =SOC max，0 +ΔSOC SOH (t), ΔSOC SOH (t) = -γ(1-SOH), γ is the adjustment coefficient;

[0020] The charging load model expression is:

[0021]

[0022] Where, δ i (t) is the charging state variable of the i-th electric vehicle, which takes the value of 0 or 1, δ i (t) = 1, indicating that the i-th vehicle is charging at time t; i (t) = 0 means that the i-th vehicle is not charged at time t; N EV is the total number of electric vehicles connected to the system; is the rated charging power of the i-th electric vehicle.

[0023] Based on the above technical solution, preferably, step S2 includes the following sub-steps:

[0024] Obtaining historical light information, including hourly light intensity, temperature and humidity, cloud cover, wind speed, and weather type;

[0025] Preprocess the historical lighting information and align the time series data to obtain a lighting training dataset;

[0026] A light intensity prediction model is constructed based on the CNN-LSTM network structure. The light training dataset is input into the CNN-LSTM network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal light intensity prediction model and output the light intensity prediction value for the future period.

[0027] On the basis of the above technical solution, preferably, step S2 further includes the following sub-steps:

[0028] Obtain historical charging information, including charging start time, end time, charging pile power time series data, vehicle ID, vehicle battery capacity, SOC history, vehicle type, holiday marking code information, and geographic location;

[0029] Perform data preprocessing on historical charging information and extract historical charging feature information to obtain a charging demand feature training set;

[0030] A charging demand prediction model is constructed based on the Transformer network structure. The charging demand feature training set is input into the Transformer network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal charging demand prediction model and output the charging load demand power in the future period.

[0031] On the basis of the above technical solution, preferably, step S2 further includes the following sub-steps:

[0032] Obtaining historical electricity price information, including real-time time-of-use electricity prices, day-ahead market electricity price data, holiday flag codes, renewable energy output ratio, and historical charging load;

[0033] Perform data preprocessing on historical electricity price information and extract historical electricity price feature information to obtain an electricity price information feature training set;

[0034] An electricity price prediction model is constructed based on the Prophet network structure. The electricity price information feature training set is input into the Prophet network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal electricity price prediction model and output the electricity price forecast value for the future period.

[0035] On the basis of the above technical solution, preferably, in step S3, the annual net cost and the power deviation rate are used as optimization targets, and a linear weighted method is used to construct a target optimization function, which is expressed as follows:

[0036] minF=λ1CANC +λ2PDR

[0037] Where C ANC is the annual net cost, PDR represents the power deviation rate, λ1 and λ2 are the weight coefficients of the annual net cost and power deviation rate respectively;

[0038] C ANC =C int +C o&m +C rep +C buy -(I sale +I EVsale )

[0039] Where C int is the initial cost, C o&m is the operating cost, C rep is the equipment replacement cost, C buy is the cost of purchasing electricity, I sale is the sales revenue of electric energy, I EVsale Revenue from charging electric vehicles;

[0040]

[0041] Where, EER(t) is the energy excess rate, LLR(t) is the load loss rate, t s is the total number of hours in a year; P su (t) is the excess power that is not utilized in the system at time t, P oload (t) is the power demand of other loads at time t; P sh (t) is the load power that the system cannot meet at time t.

[0042] On the basis of the above technical solution, preferably, the step S4 of formulating the photovoltaic storage and charging coordinated control strategy based on the predicted future time period electricity price, charging load demand power and light intensity data includes the following steps:

[0043] S41: Input the predicted future electricity price, charging load demand power and light intensity data, initialize the time step t = 1, and determine whether the current time step t is less than t s , if t <t s , then calculate the net load ΔP(t) based on the predicted charging load demand power and light intensity data, the expression is: ΔP(t)=P EV (t)-P PV (t);

[0044] S42, determining whether the net load ΔP(t) is greater than 0. If ΔP(t)>0, determining whether the state of charge of the energy storage battery at time t is greater than the lower limit dynamic threshold of the state of charge of the energy storage battery;

[0045] S43, if SOC(t)>SOC min , then the energy storage discharge calculates the discharge power of time step t, and updates the SOC and calculates the remaining power gap ΔP based on the net load and the discharge power of time step t r1 (t), if ΔP r1 (t)>0, then purchase electricity from the grid; if SOC(t)≤SOC min , then purchase electricity directly from the grid;

[0046] S44, calculate and obtain the power P purchased by the system from the grid at time step t bug (t), and calculate and update the remaining power gap ΔP according to the remaining power gap and the power purchased from the grid by the system at time step t r1 (t), if ΔP r1 (t)>0, calculate the load loss rate, increase a time step, and return to step S41 for a loop; if ΔP r1 (t)≤0, then increase the time step and return to step S41 for loop;

[0047] S45, if ΔP(t)≤0, determining whether the state of charge of the energy storage battery at time t is greater than the lower limit dynamic threshold of the state of charge of the energy storage battery;

[0048] S46, if SOC(t) <SOC max , then the energy storage charging calculates the charging power of time step t, and updates the SOC and calculates the remaining excess power ΔP based on the net load and the charging power of time step t r2 (t), if ΔP r1 (t)>0, then sell electricity to the grid. If SOC(t)>SOC max , then sell electricity directly to the grid;

[0049] S47, calculate and obtain the power P sold by the system to the grid at time step t bug (t), and calculate and update the remaining excess power ΔP according to the remaining excess power and the power sold to the grid by the system in time step t r2 (t), if ΔP r2 (t)>0, calculate the energy excess rate, increase a time step, and return to step S41 for a loop; if ΔP r2 If (t)≤0, increase the time step and return to step S41 for a loop.

[0050] On the basis of the above technical solution, preferably, the improved whale optimization algorithm is used to solve the target optimization function in step S4, and the charge and discharge power sequence is generated according to the optimal solution obtained, and input into the system for execution, including the following sub-steps:

[0051] Input the predicted future electricity price, charging load demand power and light intensity data, set the number of whale individuals N, and the maximum number of iterations T max , objective function weights λ1 and λ2 and search space boundaries [X min ,X max ];

[0052] A chaotic sequence is generated using chaotic mapping, which is then mapped to the search space to obtain the initial individual whale positions. The fitness value of each individual whale is then calculated based on the target optimization function.

[0053] The inertia weight and energy matrix parameters are dynamically adjusted according to the number of iterations, where:

[0054] The inertia weight update expression is:

[0055]

[0056] Where t is the current iteration number, T max is the maximum number of iterations, ω max is the maximum value of inertia weight, ω min is the minimum value of inertia weight;

[0057] The update expression of the transformable matrix is:

[0058] A=2a·ra

[0059] a=2-2·t / T max

[0060] Where A is the energy conversion matrix, a is the convergence factor that decreases linearly from 2 to 0, and r is a random number in the interval [0,1].

[0061] Generate a random probability threshold p, p∈[0,1]. When p<0.5, determine whether the absolute value of the transformable matrix is less than 1. If |A|<1, use the shrinking and surrounding strategy to update the whale position. If |A|≥1, use the spiral approximation strategy to update the whale position. When p≥0.5, use the shrinking and surrounding strategy to update the whale position.

[0062] Apply boundary constraints to the updated position, calculate the fitness values of all individuals, select the current optimal individual, and use Gaussian difference mutation to perturb the current optimal individual to obtain the current optimal solution;

[0063] When the maximum number of iterations is reached, the optimal solution is output, the charging and discharging power sequence is decoded, and input into the system for execution.

[0064] In a second aspect, the present invention further provides a photovoltaic storage and charging coordinated control system based on multi-energy complementarity, which is implemented using a photovoltaic storage and charging coordinated control method based on multi-energy complementarity. The system includes:

[0065] Modeling module, used to establish corresponding photovoltaic power generation model, energy storage system model and charging load model according to photovoltaic power generation system, energy storage system and charging system respectively;

[0066] The data prediction module is used to obtain historical light intensity, charging load power demand, and electricity price information, and build a prediction model based on a neural network to predict and output future light intensity, charging load power demand, and electricity price.

[0067] An objective function construction module is used to construct an objective optimization function using a linear weighted method with annual net cost and power deviation rate as optimization targets;

[0068] The optimization control module formulates a photovoltaic storage and charging coordinated control strategy based on the predicted future electricity prices, charging load demand power and light intensity data. The predicted data is used as the input of the control strategy, and the improved whale optimization algorithm is used to solve the target optimization function. The charging and discharging power sequence is generated according to the optimal solution obtained and input into the system for execution.

[0069] In a third aspect, the present invention also provides a computer-readable storage medium, on which is stored a program for a method for coordinated control of light, storage and charging based on multi-energy complementarity. When the program for coordinated control of light, storage and charging based on multi-energy complementarity is executed, a method for coordinated control of light, storage and charging based on multi-energy complementarity is implemented.

[0070] The photovoltaic storage and charging coordinated control method and system based on multi-energy complementarity of the present invention have the following beneficial effects compared with the prior art:

[0071] (1) By sequentially constructing photovoltaic power generation, energy storage system and charging load models, and using historical data combined with neural networks to accurately predict the light intensity, charging load demand power and electricity price in the future period, the objective function is constructed with the annual net cost and power deviation rate as the optimization target, and the improved whale optimization algorithm is used to solve the objective function to formulate the photovoltaic storage and charging coordinated control strategy, and finally the optimal charging and discharging power sequence is generated and input into the system for execution, which effectively improves the economy and stability of the system operation, realizes the coordinated optimization control of photovoltaic power generation, energy storage and charging systems, reduces the annual net cost, reduces the power deviation, and improves the operating efficiency and reliability of the overall system;

[0072] (2) The dynamic characteristics of photovoltaic power generation are described by the photoelectric conversion efficiency coefficient and the temperature correction term, and the shadow correction factor, the area ratio of the shaded area and the shade coefficient are introduced to quantify the impact of local shade on power generation efficiency, avoid the linear assumption error of the traditional model, and improve the accuracy of power generation prediction;

[0073] (3) The initial population is generated by chaotic mapping to effectively avoid premature convergence, and the introduction of nonlinear inertia weights and dynamic spiral constants enables the algorithm to have stronger global exploration capabilities in the early stages of iteration. The linear decrease of the convergence factor and the combination of random numbers accelerate the convergence speed, and the Gaussian difference mutation is used to perturb the optimal individual to avoid local optimality, thereby being able to solve the target optimization function more accurately, thereby obtaining a better charge and discharge power sequence, improving the operating efficiency of the system, reducing operating costs, and possibly extending the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0075] Figure 1 This is a flow chart of the photovoltaic storage and charging coordinated control method based on multi-energy complementarity of the present invention;

[0076] Figure 2 This is a target optimization flow chart of the photovoltaic storage and charging coordinated control method based on multi-energy complementarity of the present invention. DETAILED DESCRIPTION

[0077] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0078] like Figure 1 and Figure 2 As shown, in a first aspect, the present invention provides a method for coordinated control of light storage and charging based on multi-energy complementarity, the method comprising the following sub-steps:

[0079] S1: Establish corresponding photovoltaic power generation model, energy storage system model and charging load model according to the photovoltaic power generation system, energy storage system and charging system respectively.

[0080] The photovoltaic power generation model expression in step S1 is:

[0081] P PV (t) = η PV (t)·A PV ·G(t)·[1-α(T(t))·(T(t)-Tref )]·f s (t)

[0082] Where η PV is the photoelectric conversion efficiency coefficient, η PV (t) = η PV，0 ·e -λt ,λ is the decay rate,η PV，0 is the initial value of the photoelectric conversion efficiency coefficient; A PV is the total area of the photovoltaic panel, G(t) is the light intensity at time t, T(t) is the ambient temperature at time t, T ref is the reference temperature for photovoltaic panel efficiency test, α is the temperature coefficient, P PV (t) is the photovoltaic output power;

[0083]

[0084] Where, f s (t) is the local shadow correction factor at time t, S i (t) is the area ratio of the i-th occluded area at time t, k i is the occlusion coefficient;

[0085] It should be noted that photovoltaic output power is affected by light intensity, ambient temperature and local shadows. The dynamic characteristics of photovoltaic power generation are described by the photoelectric conversion efficiency coefficient and the temperature correction term, and a shadow correction factor is introduced. The impact of local shading on power generation efficiency is quantified through the area ratio and shading coefficient of the blocked area, avoiding the linear assumption error of the traditional model and improving the accuracy of power generation prediction.

[0086] The energy storage system model expression is:

[0087]

[0088] Where SOC(t) is the state of charge of the energy storage battery at time t, η ch is the charging efficiency of the energy storage battery, η dis is the discharge efficiency of the energy storage battery, E max is the total capacity of the energy storage battery, Δt is the time interval, P ch (t) is the energy storage battery charging power at time t, P dis (t) is the discharge power of the energy storage battery at time t, is the maximum charging power of the energy storage battery, is the maximum discharge power of the energy storage battery, SOC min SOC is the lower limit dynamic threshold of the state of charge of the energy storage battery. min =SOC min，0 +ΔSOC SOH (t), SOCmin，0 is the lower initial threshold of the state of charge of the energy storage battery, ΔSOC SOH (t) is the threshold offset of SOH, SOC max The upper dynamic threshold of the state of charge of the energy storage battery, SOC max =SOC max，0 +ΔSOC SOH (t), ΔSOC SOH (t) = -γ(1-SOH), γ is the adjustment coefficient;

[0089] It should be noted that the energy storage battery achieves bidirectional regulation through charging efficiency, discharging efficiency and dynamic threshold. The dynamic threshold is associated with the battery health status. The threshold offset is dynamically adjusted to avoid overcharging and over-discharging of the battery, extend the service life, and constrain the charging and discharging power. The energy storage system adjusts the charging and discharging strategy in real time according to the maximum charging and discharging power and SOC status to ensure stable system operation.

[0090] The charging load model expression is:

[0091]

[0092] Where, δ i (t) is the charging state variable of the i-th electric vehicle, which takes the value of 0 or 1, δ i (t) = 1, indicating that the i-th vehicle is charging at time t; i (t) = 0 means that the i-th vehicle is not charged at time t; N EV is the total number of electric vehicles connected to the system; is the rated charging power of the i-th electric vehicle.

[0093] It should be noted that the charging load model adjusts the charging priority and power distribution of multiple electric vehicles in real time through charging state variables and rated charging power, combines photovoltaic output and energy storage status, prioritizes the consumption of renewable energy, and reduces dependence on the power grid.

[0094] S2 obtains historical lighting information, historical charging information, and historical electricity price information, and builds a prediction model based on a neural network to predict and output the lighting intensity, charging load demand power, and electricity price in future time periods.

[0095] Step S2 includes the following sub-steps:

[0096] Obtaining historical light information, including hourly light intensity, temperature and humidity, cloud cover, wind speed, and weather type;

[0097] Preprocess the historical lighting information and align the time series data to obtain a lighting training dataset;

[0098] A light intensity prediction model is constructed based on the CNN-LSTM network structure. The light training dataset is input into the CNN-LSTM network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal light intensity prediction model and output the light intensity prediction value for the future period.

[0099] It should be noted that multi-dimensional spatiotemporal data such as light intensity, temperature and humidity, cloud cover, wind speed, and weather type are integrated to capture the coupled effects of environmental factors on photovoltaic power generation; the CNN layer is used to extract local spatiotemporal features and reduce data dimensions; the LSTM layer is used to learn the long-term time dependence of light intensity, and then use the CNN-LSTM combination model to have both spatial feature extraction and time series modeling capabilities. It is suitable for nonlinear and high-dimensional meteorological data prediction, captures the dynamic changes of light intensity through multi-channel input, and outputs hourly forecast values for the next 1-24 hours, providing a basis for photovoltaic power generation prediction.

[0100] Obtain historical charging information, including charging start time, end time, charging pile power time series data, vehicle ID, vehicle battery capacity, SOC history, vehicle type, holiday marking code information, and geographic location;

[0101] Perform data preprocessing on historical charging information and extract historical charging feature information to obtain a charging demand feature training set;

[0102] A charging demand prediction model is constructed based on the Transformer network structure. The charging demand feature training set is input into the Transformer network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal charging demand prediction model and output the charging load demand power in the future period.

[0103] It should be noted that by integrating charging behavior data with external factors such as holidays and geographic locations, and characterizing user charging habits and scenario dependencies, the self-attention mechanism in the Transformer network structure can capture the long-term dependencies and burst patterns of charging demand. In addition, position encoding introduces timestamps and geographic location encoding to enhance sequence order and spatial context perception. As a result, Transformer performs well in long sequence prediction and can be parallelized for calculation, making it suitable for load forecasting of large-scale charging pile clusters. The multi-head attention mechanism captures the periodicity and burstiness of user charging behavior and outputs the charging load demand power in future time periods.

[0104] Obtaining historical electricity price information, including real-time time-of-use electricity prices, day-ahead market electricity price data, holiday flag codes, renewable energy output ratio, and historical charging load;

[0105] Perform data preprocessing on historical electricity price information and extract historical electricity price feature information to obtain an electricity price information feature training set;

[0106] An electricity price prediction model is constructed based on the Prophet network structure. The electricity price information feature training set is input into the Prophet network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal electricity price prediction model and output the electricity price forecast value for the future period.

[0107] It should be noted that the Prophet model is used to decompose the electricity price series into trend terms, seasonal terms and holiday terms, automatically fit nonlinear changes, integrate real-time time-of-use electricity prices, day-ahead market electricity prices, renewable energy output ratio and other features, construct a feature training set containing multi-source data, and output the electricity price forecast value for the next 1-7 days through Bayesian parameter estimation and adaptive trend adjustment in the Prophet model.

[0108] S3, taking annual net cost and power deviation rate as optimization objectives, uses linear weighted method to construct the target optimization function.

[0109] The objective optimization function expression is:

[0110] minF=λ1C ANC +λ2PDR

[0111] Where C ANC is the annual net cost, PDR represents the power deviation rate, λ1 and λ2 are the weight coefficients of the annual net cost and power deviation rate respectively;

[0112] C ANC =C m +C o&m +C rep +C buy -(I sale +I EVsale )

[0113] Where C int is the initial cost, C o&m is the operating cost, C rep is the equipment replacement cost, C buy is the cost of purchasing electricity, I sale is the sales revenue of electric energy, I EVsale Revenue from charging electric vehicles;

[0114] The initial cost expression is:

[0115]

[0116] Where N i is the number of equipment of type i, C iis the unit price of the i-th type of equipment, r is the discount rate, m i is the service life of the equipment of category i, C csp is the unit price of special equipment, N cs is the number of special equipment;

[0117] The operating cost expression is:

[0118]

[0119] Where C io&m is the annual operating cost of equipment in category i;

[0120] The equipment replacement cost expression is:

[0121]

[0122] Where N bat is the number of energy storage batteries, C bat_rep is the replacement cost of a single energy storage battery, m bat The service life of the energy storage battery.

[0123] The cost expression for purchasing electricity is:

[0124]

[0125] Where, P buy P is the power of purchased electricity. buy (t) is the electricity purchase price at time t;

[0126] The sales revenue from selling electric energy is expressed as:

[0127]

[0128] Where, P sale P is the power of the electric energy sold. sale (t) is the electricity price sold at time t;

[0129] The expression of electric vehicle charging income is:

[0130]

[0131] Where, P csp P is the revenue related to electric vehicle charging services. EV (t) is the electric vehicle charging load power at time t;

[0132]

[0133] Where, EER(t) is the energy excess rate, LLR(t) is the load loss rate, t s is the total number of hours in a year; Psu (t) is the excess power that is not utilized in the system at time t, P oload (t) is the power demand of other loads at time t; P sh (t) is the load power that the system cannot meet at time t.

[0134] S4, based on the predicted future electricity prices, charging load demand power and light intensity data, formulates a photovoltaic storage and charging coordinated control strategy, uses the predicted data as the input of the control strategy, uses the improved whale optimization algorithm to solve the target optimization function, generates the charging and discharging power sequence according to the optimal solution obtained, and inputs it into the system for execution.

[0135] Step S4, based on the predicted future electricity price, charging load demand power and light intensity data, formulates a photovoltaic storage and charging coordinated control strategy, including the following steps:

[0136] S41: Input the predicted future electricity price, charging load demand power and light intensity data, initialize the time step t = 1, and determine whether the current time step t is less than t s , if t <t s , then calculate the net load ΔP(t) based on the predicted charging load demand power and light intensity data, the expression is: ΔP(t)=P EV (t)-P PV (t);

[0137] S42, determining whether the net load ΔP(t) is greater than 0. If ΔP(t)>0, determining whether the state of charge of the energy storage battery at time t is greater than the lower limit dynamic threshold of the state of charge of the energy storage battery;

[0138] S43, if SOC(t)>SOC min , then the energy storage discharge calculates the discharge power of time step t, and updates the SOC and calculates the remaining power gap ΔP based on the net load and the discharge power of time step t r1 (t), if ΔP r1 (t)>0, then purchase electricity from the grid; if SOC(t)≤SOC min , then purchase electricity directly from the grid;

[0139] Among them, the discharge power expression of the energy storage discharge calculation time step t is:

[0140]

[0141] Update the SOC expression to:

[0142]

[0143] Calculate the remaining power gap ΔP based on the net load and the discharge power at time step tr1 (t), the expression is:

[0144] △P r1 (t)=△P(t)-P dis (t);

[0145] S44, calculate and obtain the power P purchased by the system from the grid at time step t bug (t), and calculate and update the remaining power gap ΔP according to the remaining power gap and the power purchased from the grid by the system at time step t r1 (t), if ΔP r1 (t)>0, calculate the load loss rate, increase a time step, and return to step S41 for a loop; if ΔP r1 (t)≤0, then increase the time step and return to step S41 for loop;

[0146] Where, the power P purchased by the system from the grid at time step t is bug (t) is expressed as:

[0147]

[0148] The updated residual power gap expression is:

[0149] △P r1 (t)=△P r1 (t)-P buy (t)

[0150] S45, if ΔP(t)≤0, determining whether the state of charge of the energy storage battery at time t is greater than the lower limit dynamic threshold of the state of charge of the energy storage battery;

[0151] S46, if SOC(t) <SOC max , then the energy storage charging calculates the charging power of time step t, and updates the SOC and calculates the remaining excess power ΔP based on the net load and the charging power of time step t r2 (t), if ΔP r1 (t)>0, then sell electricity to the grid. If SOC(t)>SOC max , then sell electricity directly to the grid;

[0152] Among them, the charging power expression of time step t is:

[0153]

[0154] Update the SOC expression to:

[0155]

[0156] Update the remaining excess power expression to:

[0157] △P r2 (t)=|△P(t)|-P ch (t);

[0158] S47, calculate and obtain the power P sold by the system to the grid at time step t sale (t), and calculate and update the remaining excess power ΔP according to the remaining excess power and the power sold to the grid by the system in time step t r2 (t), if ΔP r2 (t)>0, calculate the energy excess rate, increase a time step, and return to step S41 for a loop; if ΔP r2 If (t)≤0, increase the time step and return to step S41 for a loop.

[0159] Among them, the power P sold by the system to the grid in time step t is sale (t) is expressed as:

[0160]

[0161] Update the remaining excess power expression to:

[0162] △P r2 (t)=△P r2 (t)-P sell (t);

[0163] It should be noted that the energy storage charging and discharging and grid interaction strategies are dynamically adjusted through real-time prediction data, with the goal of minimizing the annual net cost and reducing the power deviation rate. By judging whether the system power supply and demand status is power shortage or surplus, energy storage is preferentially used to adjust power according to the SOC dynamic threshold and charging and discharging efficiency. When energy storage regulation is insufficient, the power gap / surplus is balanced by purchasing or selling electricity, and the status is updated step by step until the full-time optimization is completed.

[0164] In step S4 of this embodiment, the improved whale optimization algorithm is used to solve the target optimization function, and the charge and discharge power sequence is generated according to the optimal solution obtained, and is input into the system for execution, including the following sub-steps:

[0165] Input the predicted future electricity price, charging load demand power and light intensity data, set the number of whale individuals N, and the maximum number of iterations T max , objective function weights λ1 and λ2 and search space boundaries [X min ,X max ];

[0166] A chaotic sequence is generated using chaotic mapping, which is then mapped to the search space to obtain the initial individual whale positions. The fitness value of each individual whale is then calculated based on the target optimization function.

[0167] The inertia weight and energy matrix parameters are dynamically adjusted according to the number of iterations, where:

[0168] The inertia weight update expression is:

[0169]

[0170] Where t is the current iteration number, T max is the maximum number of iterations, ω max is the maximum value of inertia weight, ω min is the minimum value of inertia weight;

[0171] The update expression of the transformable matrix is:

[0172] A=2a·ra

[0173] a=2-2·t / T max

[0174] Where A is the energy conversion matrix, a is the convergence factor that decreases linearly from 2 to 0, and r is a random number in the interval [0,1].

[0175] Generate a random probability threshold p, p∈[0,1]. When p<0.5, determine whether the absolute value of the transformable matrix is less than 1. If |A|<1, use the shrinking and surrounding strategy to update the whale position. If |A|≥1, use the spiral approximation strategy to update the whale position. When p≥0.5, use the shrinking and surrounding strategy to update the whale position.

[0176] Apply boundary constraints to the updated position, calculate the fitness values of all individuals, select the current optimal individual, and use Gaussian difference mutation to perturb the current optimal individual to obtain the current optimal solution;

[0177] When the maximum number of iterations is reached, the optimal solution is output, the charging and discharging power sequence is decoded, and input into the system for execution.

[0178] It should be noted that the generation of the initial population through the Cubic chaotic map effectively increases the diversity of the population, thereby avoiding the algorithm from falling into the local optimal solution in the early stage of iteration. The introduction of nonlinear inertia weight enables the algorithm to have stronger global exploration capabilities in the early stage of iteration; the inertia weight is dynamically adjusted according to the number of iterations, so that the algorithm can explore the search space more widely in the early stage of search, thereby increasing the possibility of finding the global optimal solution; the linear decrease of the convergence factor and the combination of random numbers enable the algorithm to dynamically adjust the search strategy during the iteration process; in the early stage of iteration, the convergence factor is large, and the algorithm tends to global search; as the number of iterations increases, the convergence factor gradually decreases, and the algorithm gradually turns to local search. This dynamic adjustment strategy helps to speed up the convergence of the algorithm; Gaussian difference mutation is used to perturb the optimal individual. By making small perturbations to the optimal individual, the algorithm can conduct a more detailed search near the optimal solution, thus avoiding falling into the local optimal solution; at the same time, this perturbation also helps the algorithm find a better balance between global search and local search; and thus can more accurately solve the target optimization function, thereby obtaining a better charge and discharge power sequence, improving the system's operating efficiency, reducing operating costs, and possibly extending the service life of the equipment.

[0179] In this embodiment, photovoltaic power generation, energy storage system and charging load models are constructed in sequence, and historical data is combined with neural networks to accurately predict the light intensity, charging load demand power and electricity price in future time periods. Then, the objective function is constructed with the annual net cost and power deviation rate as optimization targets. The improved whale optimization algorithm is used to solve the objective function to formulate a photovoltaic storage and charging coordinated control strategy. Finally, the optimal charging and discharging power sequence is generated and input into the system for execution. This method effectively improves the economy and stability of the system operation, realizes the coordinated optimization control of photovoltaic power generation, energy storage and charging systems, reduces the annual net cost, reduces the power deviation, and improves the operating efficiency and reliability of the entire system.

[0180] In a second aspect, the present invention further provides a photovoltaic storage and charging coordinated control system based on multi-energy complementarity, which is implemented using a photovoltaic storage and charging coordinated control method based on multi-energy complementarity. The system includes:

[0181] Modeling module, used to establish corresponding photovoltaic power generation model, energy storage system model and charging load model according to photovoltaic power generation system, energy storage system and charging system respectively;

[0182] The data prediction module is used to obtain historical light intensity, charging load power demand, and electricity price information, and build a prediction model based on a neural network to predict and output future light intensity, charging load power demand, and electricity price.

[0183] An objective function construction module is used to construct an objective optimization function using a linear weighted method with annual net cost and power deviation rate as optimization targets;

[0184] The optimization control module formulates a photovoltaic storage and charging coordinated control strategy based on the predicted future electricity prices, charging load demand power and light intensity data. The predicted data is used as the input of the control strategy, and the improved whale optimization algorithm is used to solve the target optimization function. The charging and discharging power sequence is generated according to the optimal solution obtained and input into the system for execution.

[0185] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0186] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0187] In the embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0188] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0189] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0190] 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 existing technology, 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 and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or optical disk, etc. Various media that can store program code.

[0191] In addition, it should be noted that, in the system and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it will be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0192] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing system. The computing system can be a well-known general-purpose system. Therefore, the purpose of the present invention can also be achieved simply by providing a program product containing program code for implementing the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0193] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A photovoltaic storage and charging coordinated control method based on multi-energy complementarity, characterized in that: The method includes the following sub-steps: S1, establish corresponding photovoltaic power generation model, energy storage system model and charging load model according to the photovoltaic power generation system, energy storage system and charging system respectively; S2, obtains historical light information, historical charging information, and historical electricity price information, and builds a prediction model based on a neural network to predict and output the light intensity, charging load demand power, and electricity price in the future period; S3, taking annual net cost and power deviation rate as optimization targets, uses linear weighting method to construct the target optimization function; S4, based on the predicted future electricity prices, charging load demand power and light intensity data, formulates a photovoltaic storage and charging coordinated control strategy, uses the predicted data as the input of the control strategy, uses the improved whale optimization algorithm to solve the target optimization function, generates the charging and discharging power sequence according to the optimal solution obtained, and inputs it into the system for execution.

2. The photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to claim 1 is characterized in that: In step S1, the corresponding photovoltaic power generation model, energy storage system model and charging load model are established according to the photovoltaic power generation system, energy storage system and charging system, wherein: The photovoltaic power generation model expression is: P PV (t)=η PV (t)·A PV ·G(t)·[1-α(T(t))·(T(t)-T ref )]·f s (t) Where η PV is the photoelectric conversion efficiency coefficient, η PV (t) = η PV，0 ·e -λt ,λ is the decay rate,η PV，0 is the initial value of the photoelectric conversion efficiency coefficient; A PV is the total area of the photovoltaic panel, G(t) is the light intensity at time t, T(t) is the ambient temperature at time t, T ref is the reference temperature for photovoltaic panel efficiency test, α is the temperature coefficient, P PV (t) is the photovoltaic output power; Where, f s (t) is the local shadow correction factor at time t, S i (t) is the area ratio of the i-th occluded area at time t, k i is the occlusion coefficient; The energy storage system model expression is: Where SOC(t) is the state of charge of the energy storage battery at time t, η ch is the charging efficiency of the energy storage battery, η dis is the discharge efficiency of the energy storage battery, E max is the total capacity of the energy storage battery, Δt is the time interval, P ch (t) is the energy storage battery charging power at time t, P dis (t) is the discharge power of the energy storage battery at time t, is the maximum charging power of the energy storage battery, is the maximum discharge power of the energy storage battery, SOC min SOC is the lower limit dynamic threshold of the state of charge of the energy storage battery. min =SOC min，0 +ΔSOC SOH (t), SOC min，0 is the lower initial threshold of the state of charge of the energy storage battery, ΔSOC SOH (t) is the threshold offset of SOH, SOC max The upper dynamic threshold of the state of charge of the energy storage battery, SOC max =SOC max，0 +ΔSOC SOH (t), ΔSOC SOH (t) = -γ(1-SOH), γ is the adjustment coefficient; The charging load model expression is: Where, δ i (t) is the charging state variable of the i-th electric vehicle, which takes the value of 0 or 1, δ i (t) = 1, indicating that the i-th vehicle is charging at time t; i (t) = 0 means that the i-th vehicle is not charged at time t; N EV is the total number of electric vehicles connected to the system; is the rated charging power of the i-th electric vehicle.

3. The photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to claim 2 is characterized in that: Step S2 includes the following sub-steps: Obtaining historical light information, including hourly light intensity, temperature and humidity, cloud cover, wind speed, and weather type; Preprocess the historical lighting information and align the time series data to obtain a lighting training dataset; A light intensity prediction model is constructed based on the CNN-LSTM network structure. The light training dataset is input into the CNN-LSTM network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal light intensity prediction model and output the light intensity prediction value for the future period.

4. The photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to claim 2 is characterized in that: Step S2 also includes the following sub-steps: Obtain historical charging information, including charging start time, end time, charging pile power time series data, vehicle ID, vehicle battery capacity, SOC history, vehicle type, holiday marking code information, and geographic location; Perform data preprocessing on historical charging information and extract historical charging feature information to obtain a charging demand feature training set; A charging demand prediction model is constructed based on the Transformer network structure. The charging demand feature training set is input into the Transformer network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal charging demand prediction model and output the charging load demand power in the future period.

5. The photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to claim 2 is characterized in that: Step S2 also includes the following sub-steps: Obtaining historical electricity price information, including real-time time-of-use electricity prices, day-ahead market electricity price data, holiday flag codes, renewable energy output ratio, and historical charging load; Perform data preprocessing on historical electricity price information and extract historical electricity price feature information to obtain an electricity price information feature training set; An electricity price prediction model is constructed based on the Prophet network structure. The electricity price information feature training set is input into the Prophet network structure for iterative training. The Adam optimization algorithm is used to adjust the model parameters to obtain the optimal electricity price prediction model and output the electricity price forecast value for the future period.

6. The photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to claim 5 is characterized in that: In step S3, the annual net cost and power deviation rate are used as optimization targets, and the linear weighted method is used to construct the target optimization function, which is expressed as follows: minF=λ1C ANC +λ2PDR Where C ANC is the annual net cost, PDR represents the power deviation rate, λ1 and λ2 are the weight coefficients of the annual net cost and power deviation rate respectively; C ANC =C int +C o&m +C rep +C buy -(I sale +I EVsale ) Where C int is the initial cost, C o&m is the operating cost, C rep is the equipment replacement cost, C buy is the cost of purchasing electricity, I sale is the sales revenue from selling electric energy, I EVsale Revenue from charging electric vehicles; Where, EER(t) is the energy excess rate, LLR(t) is the load loss rate, t s is the total number of hours in a year; P su (t) is the excess power that is not utilized in the system at time t, P oload (t) is the power demand of other loads at time t; P sh (t) is the load power that the system cannot meet at time t.

7. The photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to claim 6 is characterized in that: Step S4, based on the predicted future electricity price, charging load demand power and light intensity data, formulates a solar-storage-charging coordinated control strategy, including the following steps: S41: Input the predicted future electricity price, charging load demand power and light intensity data, initialize the time step t = 1, and determine whether the current time step t is less than t s , if t <t s , then calculate the net load ΔP(t) based on the predicted charging load demand power and light intensity data, the expression is: ΔP(t)=P EV (t)-P PV (t); S42, determining whether the net load ΔP(t) is greater than 0. If ΔP(t)>0, determining whether the state of charge of the energy storage battery at time t is greater than the lower limit dynamic threshold of the state of charge of the energy storage battery; S43, if SOC(t)>SOC min , then the energy storage discharge calculates the discharge power of time step t, and updates the SOC and calculates the remaining power gap ΔP based on the net load and the discharge power of time step t r1 (t), if ΔP r1 (t)>0, then purchase electricity from the grid; if SOC(t)≤SOC min , then purchase electricity directly from the grid; S44, calculate and obtain the power P purchased by the system from the grid at time step t bug (t), and calculate and update the remaining power gap ΔP according to the remaining power gap and the power purchased from the grid by the system at time step t r1 (t), if ΔP r1 (t)>0, calculate the load loss rate, increase a time step, and return to step S41 for a loop; if ΔP r1 (t)≤0, then increase the time step and return to step S41 for loop; S45, if ΔP(t)≤0, determining whether the state of charge of the energy storage battery at time t is greater than the lower limit dynamic threshold of the state of charge of the energy storage battery; S46, if SOC(t) <SOC max , then the energy storage charging calculates the charging power of time step t, and updates the SOC and calculates the remaining excess power ΔP based on the net load and the charging power of time step t r2 (t), if ΔP r1 (t)>0, then sell electricity to the grid. If SOC(t)>SOC max , then sell electricity directly to the grid; S47, calculate and obtain the power P sold by the system to the grid at time step t bug (t), and calculate and update the remaining excess power ΔP according to the remaining excess power and the power sold to the grid by the system in time step t r2 (t), if ΔP r2 (t)>0, calculate the energy excess rate, increase a time step, and return to step S41 for a loop; if ΔP r2 If (t)≤0, increase the time step and return to step S41 for a loop.

8. The photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to claim 7 is characterized in that: Step S4 uses the improved whale optimization algorithm to solve the target optimization function, generates a charge and discharge power sequence based on the optimal solution obtained, and inputs it into the system for execution, including the following sub-steps: Input the predicted future electricity price, charging load demand power and light intensity data, set the number of whale individuals N, and the maximum number of iterations T max , objective function weights λ1 and λ2 and search space boundaries [X min ,X max ]; A chaotic sequence is generated using chaotic mapping, which is then mapped to the search space to obtain the initial individual whale positions. The fitness value of each individual whale is then calculated based on the target optimization function. The inertia weight and energy matrix parameters are dynamically adjusted according to the number of iterations, where: The inertia weight update expression is: Where t is the current iteration number, T max is the maximum number of iterations, ω max is the maximum value of inertia weight, ω min is the minimum value of inertia weight; The update expression of the transformable matrix is: A=2a·ra a=2-2·t / T max Where A is the energy conversion matrix, a is the convergence factor that decreases linearly from 2 to 0, and r is a random number in the interval [0,1]. Generate a random probability threshold p, p∈[0,1]. When p<0.5, determine whether the absolute value of the transformable matrix is less than 1. If |A|<1, use the shrinking and surrounding strategy to update the whale position. If |A|≥1, use the spiral approximation strategy to update the whale position. When p≥0.5, use the shrinking and surrounding strategy to update the whale position. Apply boundary constraints to the updated position, calculate the fitness values of all individuals, select the current optimal individual, and use Gaussian difference mutation to perturb the current optimal individual to obtain the current optimal solution; When the maximum number of iterations is reached, the optimal solution is output, the charging and discharging power sequence is decoded, and input into the system for execution.

9. A photovoltaic storage and charging coordinated control system based on multi-energy complementarity, implemented by the photovoltaic storage and charging coordinated control method based on multi-energy complementarity according to any one of claims 1 to 8, characterized in that: The system comprises: Modeling module, used to establish corresponding photovoltaic power generation model, energy storage system model and charging load model according to photovoltaic power generation system, energy storage system and charging system respectively; The data prediction module is used to obtain historical light intensity, charging load power demand, and electricity price information, and build a prediction model based on a neural network to predict and output future light intensity, charging load power demand, and electricity price. An objective function construction module is used to construct an objective optimization function using a linear weighted method with annual net cost and power deviation rate as optimization targets; The optimization control module formulates a photovoltaic storage and charging coordinated control strategy based on the predicted future electricity prices, charging load demand power and light intensity data. The predicted data is used as the input of the control strategy, and the improved whale optimization algorithm is used to solve the target optimization function. The charging and discharging power sequence is generated according to the optimal solution obtained and input into the system for execution.

10. A computer-readable storage medium, characterized in that The storage medium stores a program for a method for coordinated control of light, storage and charging based on multi-energy complementarity. When the program for coordinated control of light, storage and charging based on multi-energy complementarity is executed, a method for coordinated control of light, storage and charging based on multi-energy complementarity as claimed in any one of claims 1 to 8 is implemented.

Images