A Cooperative Optimization Method for Hybrid Energy Storage and Wind-Solar Power Prediction in Desert Areas

Abstract

The present invention discloses a collaborative optimization method for hybrid energy storage and wind-solar prediction for desert areas. First, for a multi-energy complementary system, including wind power generation, photovoltaic power generation, a hybrid energy storage system, etc., equipment modeling constraints are carried out; a wind-solar prediction model is established by using a BP neural network classification prediction optimized by a particle swarm algorithm; by using a differential creative search algorithm, the prediction models of wind energy and light are jointly optimized with the optimization model of the multi-energy complementary system with hybrid energy storage, and the prediction results of wind energy and light are used as the input of the optimization model of the multi-energy complementary system with hybrid energy storage to obtain the best energy supply and energy storage scheduling scheme. The present invention has the advantages of reducing carbon emissions, promoting the consumption of new energy, reducing the operation cost of the integrated energy system, and reducing the pressure of energy supply, etc.

Description

Technical Field

[0001] The present invention relates to a collaborative optimization method for hybrid energy storage and wind-solar power prediction, and particularly to a collaborative optimization method for hybrid energy storage and wind-solar power prediction for desert areas, belonging to the field of energy technology. Background Art

[0002] Energy resources in desert and gobi areas are rich. However, due to complex geographical environments and unstable climate conditions, traditional energy supply methods are difficult to meet the demand. Hybrid energy storage systems for desert and gobi areas have high application potential, can effectively integrate renewable energy such as wind energy and solar energy, and improve energy utilization efficiency. As a currently mature and widely used energy storage solution, the battery energy storage system (BESS) is a crucial component of the hybrid energy storage system. At the same time, the hydrogen energy storage system (HES) and the thermal energy storage system (TES) have unique advantages in desert and gobi areas, which can improve the flexibility and stability of the system. Optimizing the wind power prediction model is the key to realizing wind-solar synergy. By accurately predicting meteorological factors such as wind speed, wind direction, and air pressure, the wind power generation efficiency can be improved, and the dependence on traditional energy can be reduced. Collaborative optimization considering carbon emissions can effectively reduce carbon emissions during the energy supply process, meeting the requirements of environmental protection and sustainable development. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a collaborative optimization method for hybrid energy storage and wind-solar power prediction for desert areas.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] A collaborative optimization method for hybrid energy storage and wind-solar power prediction for desert areas, comprising the following steps:

[0006] Step S1: Establish a multi-energy complementary system model:

[0007] The multi-energy complementary system model includes a wind power generation module, a photovoltaic power generation module, a hybrid energy storage module, a user load module, a gas boiler module, a combined heat and power unit module, and a power grid power purchase and sale module. The wind power generation module and the photovoltaic power generation module convert renewable energy into electrical energy, which is directly supplied to the user load module or traded through the power grid power purchase and sale module. The gas boiler module and the combined heat and power unit module provide heat energy to meet the heat load demand of the user load module. The hybrid energy storage module includes a BESS module, an HES module, and a TES module. The hybrid energy storage module stores the remaining electricity when the electricity is in excess.

[0008] Step S2: Establish a wind-solar power prediction model: The wind-solar power prediction model consists of a wind-solar power output uncertainty module and a BP neural network; the output uncertainty generated by the wind-solar power output uncertainty model and the wind speed and light intensity are input into the BP neural network as input features;

[0009] Step S3: Cascade the wind-solar power prediction model with the multi-energy complementary system model and jointly optimize it using a differential creative search algorithm to obtain the best energy supply and energy storage scheduling scheme, including the following steps:

[0010] Step S3-1: Initialize parameters: First, set the population size and the range of decision variables, and then randomly generate an initial population , the initial population consists of more than 1 individual; the variables included in the individual include: the hydrogen production electric power of the electrolyzer in the HES , the charging power of the BESS , the electric power obtained by the electrolyzer in the HES , the hydrogen production electric power of the electrolyzer in the HES , the electric power obtained by the fuel cell in the HES , the electric power generated by the fuel cell in the HES , the heat storage power of the TES , the heat release power of the TES , the output electric power of the combined heat and power unit , the actual output power of the wind turbine , the actual output power of the photovoltaic unit , the objective function is the total operating cost of the multi-energy complementary system:

[0011] (1)

[0012] In the formula, represents the d-th parameter of the th candidate solution , and D is the number of parameters of the candidate solution; the number of candidate solutions is NP; represents a uniform distribution on the interval , and represent the lower bound and upper bound of the d-th parameter respectively;

[0013] Step S3-2: Fitness evaluation: Use the objective function value corresponding to each individual as the initial fitness value:

[0014] (2)

[0015] Step S3-3: Select the individual corresponding to the minimum fitness value as the best individual ;

[0016] Step S3-4: Differential knowledge acquisition: Randomly select two individuals , Calculate and coefficients:

[0017] The calculation method of the η coefficient is:

[0018] (3)

[0019] (4)

[0020] The calculation method of the coefficient is:

[0021] (5)

[0022] (6)

[0023] In the formula, t is the number of iterations; the symbol represents integer calculation, is the rank of the th individual at the start of the t-th iteration; and are the d-th parameter values of the two individuals , ;

[0024] Update parameters:

[0025] (7)

[0026] (8)

[0027] In the formula: is the updated value of the d-th parameter value of the i-th individual;

[0028] Step S3-5: Knowledge integration and new solution generation:

[0029] Calculate the convergence factor:

[0030] (9)

[0031] In the formula, is the convergence factor at the t-th iteration; represents the current number of function calculations at the t-th iteration, represents the maximum number of function calculations;

[0032] Update the individual position:

[0033] (10)

[0034] Wherein, is the d-th parameter of the best individual in the current iteration;

[0035] Update the individual position by generating random numbers using the Linnik distribution:

[0036] (11)

[0037] Wherein, is the d-th parameter of the individual, represents a Linnik distribution random number generator with control parameters α and σ;

[0038] Step S3-6: Individual diversification: Randomly generate N new individuals:

[0039] (12)

[0040] Wherein, is the np-th new individual, and LB and UB are the lower and upper bounds;

[0041] Step S3-7: Retrospective evaluation: Replace the selected individuals with the new individuals:

[0042] (13)

[0043] (14)

[0044] Wherein, represents the i-th individual of X at the (t + 1)-th iteration; represents the optimal solution of X at the t-th iteration;

[0045] Step S3-8: Determine whether the maximum number of iterations is reached or the stop condition is satisfied. If so, output the final optimal solution and its corresponding optimal fitness value; otherwise, go to Step S3-7.

[0046] Furthermore, in the said Step S1, modeling the devices of the multi-energy complementary system includes the following processes:

[0047] S1-1. The multi-energy complementary system has a wind power generation module, a photovoltaic power generation module, a hybrid energy storage system module, a user load module, a gas boiler module, a combined heat and power unit module, and a power grid power purchase and sale module;

[0048] S1-2. The modeling of each module is as follows:

[0049] Modeling of wind power generation is:

[0050] (15)

[0051] Wherein, and are the actual output power and the rated output power of the wind turbine respectively; and are the actual wind speed and the rated wind speed respectively; and are the cut-in wind speed and the cut-out wind speed of the wind turbine respectively;

[0052] The photovoltaic power generation is modeled as:

[0053] (16)

[0054] (17)

[0055] Wherein, and are the actual output power and the rated output power of the photovoltaic unit respectively; is the photovoltaic derating factor. Considering the influences of dirt, snow accumulation, battery aging, etc., it is usually taken as 0.9; The light intensity under the actual environment; is the light intensity under the standard working condition, and the value is 1000 W / m²; The photovoltaic power temperature coefficient; is the temperature of the photovoltaic unit under the actual environment; is the standard test working environment temperature, and the value is 25 °C; is the actual environment temperature (°C); is the wind speed at the installation position of the photovoltaic panel (m / s); is the light intensity under the actual environment (W / m²);

[0056] The BESS is modeled as:

[0057] (18)

[0058] (19)

[0059] (20)

[0060] Wherein, , are the remaining power of the BESS at times t and t - 1; , are the self-discharge rate and the rated capacity of the BESS; , are the charging power and the discharging power of the BESS; , are the charging efficiency coefficient and discharging efficiency coefficient of the BESS; and are the maximum charging power and maximum discharging power of the BESS at time t, respectively; and are the maximum continuous charging power and maximum continuous discharging power of the BESS at time t, respectively; is the time interval;

[0061] The HES is modeled as:

[0062] (21)

[0063] (22)

[0064] (23)

[0065] (24)

[0066] (25)

[0067] In the formula, and are the electric power obtained by the electrolyzer and the hydrogen production electric power of the electrolyzer in the HES, respectively; and are the electric power obtained by the fuel cell and the generated electric power in the HES, respectively; and are the thermal powers generated by the electrolyzer and the fuel cell, respectively; and are the working efficiencies of the electrolyzer and the fuel cell; and are the upper and lower limits of the power of the electrolyzer, respectively; and are the upper and lower limits of the power of the fuel cell, respectively; and are the upper and lower limits of the energy storage state of the hydrogen storage tank in the HES, respectively;

[0068] The TES is modeled as:

[0069] (26)

[0070] (27)

[0071] (28)

[0072] (29)

[0073] (30)

[0074] In the formula, is the heat storage capacity of the TES at time t; is the self-heat release rate of the TES; , are the heat storage and heat release efficiencies of the TES respectively; , are the heat storage and heat release powers of the TES at time t respectively; , are the binary variables of heat storage and heat release of the TES at time t respectively; , are the maximum and minimum heat storage capacities of the TES respectively;

[0075] The gas boiler unit is modeled as:

[0076] (31)

[0077] In the formula: is the thermal power output by the gas boiler unit; is the gas consumption power of the gas boiler unit; is the thermal efficiency of the gas boiler unit;

[0078] The combined heat and power unit is modeled as:

[0079] (32)

[0080] (33)

[0081] (34)

[0082] In the formula: is the electric power output by the combined heat and power unit; is the thermal power output by the combined heat and power unit; is the natural gas power input to the combined heat and power unit; is the gas consumption of the combined heat and power unit; is the lower calorific value of natural gas; and are the electric efficiency and thermal efficiency of the combined heat and power unit respectively;

[0083] The model of the power grid's power purchase and sale module is:

[0084] (35)

[0085] (36)

[0086] In the formula, , They are the electricity purchase quantity from the superior power grid and the upper limit value of electricity purchase respectively; and are the electricity sales quantity to the superior power grid and the maximum value of electricity sales.

[0087] Furthermore, in the step S2, modeling the prediction of wind-solar energy includes the following process:

[0088] S2-1. Modeling the uncertainty of wind-solar output:

[0089] (37)

[0090] (38)

[0091] In the formula, and are uncertain parameters, and are the net output powers of the wind turbine and the photovoltaic unit; and are the predicted output values of the wind turbine unit and the photovoltaic unit; represents the uncertainty when predicting the output of the wind turbine and the photovoltaic unit, and its range is between 0 and 1; k1 and k2 are the influence degrees of the errors between the actual output and the predicted output of the wind turbine and the photovoltaic unit in the overall uncertainty respectively;

[0092] Step S2-2: Collect data: including historical power generation data of wind speed, light intensity, temperature, and the total power generation of the wind turbine unit and the photovoltaic unit, as well as the wind-solar output uncertainty factor, and perform data cleaning, normalization, and feature extraction preprocessing on the collected data; taking maximizing the wind-solar utilization rate as the objective function, use the particle swarm algorithm to optimize the connection weights and bias terms of the BP neural network;

[0093] The optimization objective function is:

[0094] (39)

[0095] In the formula, and respectively represent the power generation powers of the wind turbine generator set and the photovoltaic generator set when the wind force is and the light intensity is ; represents the predicted wind energy value when the wind force is at time t; represents the predicted light energy value when the light intensity is at time t;

[0096] S2-3: Establish an optimization model for the operating cost of the multi-energy complementary system:

[0097] (40)

[0098] The corresponding power balance constraint is as follows:

[0099] (41)

[0100] (42)

[0101] In the formula, and and and and and and and and and and and and and and respectively represent the total load power demand of the multi - energy complementary system, the total heat load demand of the system, the electric power purchased from the power grid, the thermal power output of the combined heat and power unit, the thermal power output of the gas boiler unit, the electric power output of the combined heat and power unit, the electric power obtained by the electrolyzer in the HES, the electric power for hydrogen production by the electrolyzer in the HES, the charging power of the BESS, the discharging power of the BESS, the electric power obtained by the fuel cell in the HES, the electric power generated by the fuel cell in the HES, the heat storage power of the TES, the heat release power of the TES, the actual output power of the wind turbine unit, and the actual output power of the photovoltaic unit; and are the binary variables for heat storage and heat release of the TES respectively;

[0102] Among them:

[0103] (43)

[0104] (44)

[0105] In the formula: Taking 1 represents the photovoltaic unit; Taking 2 represents the wind turbine unit; Taking 3 represents the battery energy storage system; Taking 4 represents the thermal energy storage system; Taking 5 represents the combined heat and power unit; Taking 6 represents the electrolyzer (ELC); Taking 7 represents the hydrogen storage tank; Taking 8 represents the fuel cell; Taking 9 represents the gas boiler; Taking 10 represents the absorption chiller; Take 11, representing a voltage refrigerator; is the benchmark discount rate; is the equipment 's life cycle; is the equipment 's unit investment cost; is the equipment 's unit capacity; is the equipment 's annual fixed maintenance cost, is the equipment 's unit maintenance cost;

[0106] Construct an operating cost model:

[0107] (45)

[0108] (46)

[0109] (47)

[0110] (48)

[0111] (49)

[0112] In the formula, is the cost of trading with the power grid, is the gas purchase cost, is the environmental cost generated by the gas turbine unit, is the penalty cost for curtailment of light and wind, is the charge-discharge loss and maintenance cost of the EES, is the heat storage and charge-discharge loss cost of the HES, is the heat storage and charge-discharge loss cost of the TES; 、 are the time-of-use electricity purchase price and the time-of-use electricity selling price for trading with the power grid at time t, respectively, 、 are the electricity purchase power and the electricity selling power at time t, respectively; is the unit purchase price of natural gas; 、 are the output powers of the combined heat and power unit and the gas boiler unit at time t, respectively; is the working efficiency of the gas boiler unit; is the environmental cost of the gas boiler unit's electricity purchase production from the power grid; 、 are the curtailment of wind and curtailment of light penalty factors, respectively; 、 are the curtailment of wind volume and curtailment of light volume at time t, respectively.

[0113] The design of the hybrid energy storage system that combines battery energy storage and hydrogen energy storage in the present invention improves the energy storage efficiency; a wind-solar prediction model is established by using a BP neural network classification prediction optimized by a particle swarm algorithm, effectively improving the accuracy and reliability of energy supply; the environmental friendliness of the integrated energy system is considered, which conforms to the goals of carbon peak and carbon neutrality advocated at the present stage; by using a differential creative search algorithm, the prediction models of wind energy and light are jointly optimized with the optimization model of the multi-energy complementary system with hybrid energy storage, which can more effectively reduce carbon emissions, make more full use of the rich wind-solar resources in the western region, and improve the reliability and economy of energy supply; at the same time, the energy management algorithm based on multi-objective optimization realizes the balance between economy and reliability. Description of the Drawings

[0114] Figure 1 It is the structure diagram of the multi-energy complementary system in the western desert area.

[0115] Figure 2 It is the flow chart of the solution method of the present invention. Detailed Embodiments

[0116] The present invention will be further described below with reference to the drawings.

[0117] Refer to Figures 1 to 2 , a collaborative optimization method for hybrid energy storage and wind-solar prediction for the western desert region. The structure diagram of the multi-energy complementary system in the western desert area studied in the invention is shown in Figure 1 . Among them, renewable energy power generation such as wind and solar is used as the main energy input. At the same time, the system can also purchase electricity from the power grid and natural gas from the gas network as external energy inputs. Through the power conversion and energy storage subsystems, the power demand is met; through hydrogen production, fuel cells, etc., electrical energy is converted into hydrogen energy to meet the hydrogen energy demand; at the same time, the remaining heat is stored through heat exchange equipment to meet the heat energy demand. The energy trading mode of the integrated energy system allows energy trading between various subsystems within the system to achieve the goal of minimizing costs. In addition, the system can also conduct energy trading with the external power grid and gas network to meet the diverse energy demands of the system. The design of this integrated energy system not only improves energy utilization efficiency but also effectively reduces carbon emissions, meeting the requirements of environmental protection and sustainable development.

[0118] A collaborative optimization method for hybrid energy storage and wind-solar prediction for the western desert region includes the following steps:

[0119] S1: Establish a multi-energy complementary system model:

[0120] The multi - energy complementary system model includes a wind power generation module, a photovoltaic power generation module, a hybrid energy storage module, a user load module, a gas boiler module, a combined heat and power unit module, and a power grid power purchase and sale module. The wind power generation module and the photovoltaic power generation module convert renewable energy into electrical energy, which is directly supplied to the user load module or traded through the power grid power purchase and sale module. The gas boiler module and the combined heat and power unit module provide heat energy that meets the heat load requirements of users; The hybrid energy storage module includes a BESS module, a HES module, and a TES module. The hybrid energy storage module stores the remaining electricity when the electricity is in excess.

[0121] In the step S1, the equipment of the multi - energy complementary system is modeled, including the following process:

[0122] S1 - 1. The multi - energy complementary system has a wind power generation, photovoltaic power generation, hybrid energy storage system, user load, gas boiler, combined heat and power unit, and a power grid power purchase and sale module;

[0123] S1 - 2. The modeling of each module is as follows:

[0124] The wind power generation is modeled as:

[0125] (1)

[0126] In the formula, and are the actual output power and the rated output power of the wind turbine respectively; and are the actual wind speed and the rated wind speed respectively; and are the cut - in wind speed and the cut - out wind speed of the wind turbine respectively;

[0127] The photovoltaic power generation is modeled as:

[0128] (2)

[0129] (3)

[0130] In the formula, and are the actual output power and the rated output power of the photovoltaic unit respectively; is the photovoltaic derating factor, considering the effects of dirt, snow, and battery aging, etc., and usually takes a value of 0.9; The light intensity in the actual environment; is the light intensity under standard conditions, with a value of 1000 W / m²; The photovoltaic power temperature coefficient; is the temperature of the photovoltaic unit in the actual environment; is the standard test working environment temperature, with a value of 25℃; is the actual ambient temperature (°C); is the wind speed at the installation location of the PV panel (m / s); is the light intensity under the actual environment (W / m²);

[0131] The BESS is modeled as:

[0132] (4)

[0133] (5)

[0134] (6)

[0135] Wherein, , are the remaining power of the BESS at times t and t-1; , are the self-discharge rate and rated capacity of the BESS; , are the charging power and discharging power of the BESS; , are the charging efficiency coefficient and discharging efficiency coefficient of the BESS; , are the maximum charging power and maximum discharging power of the BESS at time t, respectively; , are the maximum continuous charging power and maximum continuous discharging power of the BESS at time t, respectively; is the time interval;

[0136] The HES is modeled as:

[0137] (7)

[0138] (8)

[0139] (9)

[0140] (10)

[0141] (11)

[0142] Wherein, , are the electric power obtained by the electrolyzer and the electric power for hydrogen production by the electrolyzer in the HES, respectively; , are the electric power obtained by the fuel cell and the generated electric power in the HES, respectively; , are the thermal powers generated by the electrolyzer and the fuel cell, respectively; , is the working efficiency of the electrolyzer and fuel cell; , are the upper and lower power limits of the electrolyzer respectively; , are the upper and lower power limits of the fuel cell respectively; , are the upper and lower limits of the energy storage state of the hydrogen storage tank in HES respectively;

[0143] The TES is modeled as:

[0144] (12)

[0145] (13)

[0146] (14)

[0147] (15)

[0148] (16)

[0149] In the formula, is the heat storage capacity of TES at time t; is the self-heat release rate of TES; , are the heat storage and heat release efficiencies of TES respectively; , are the heat storage and heat release powers of TES at time t respectively; , are the binary variables of heat storage and heat release of TES at time t respectively; , are the maximum and minimum heat storage capacities of TES respectively;

[0150] The gas boiler unit is modeled as:

[0151] (17)

[0152] In the formula: is the thermal power output by the gas boiler unit; is the gas consumption power of the gas boiler unit; is the thermal efficiency of the gas boiler unit;

[0153] The combined heat and power unit is modeled as:

[0154] (18)

[0155] (19)

[0156] (20)

[0157] Wherein: is the electric power output by the combined heat and power unit; is the heat power output by the combined heat and power unit; is the natural gas power input to the combined heat and power unit; is the gas consumption of the combined heat and power unit; is the lower calorific value of natural gas; and are the electric efficiency and heat efficiency of the combined heat and power unit respectively;

[0158] The model of the power grid power purchase and sale module is:

[0159] (21)

[0160] (22)

[0161] Wherein, , are the power purchase amount from the superior power grid and the upper limit of power purchase at time t respectively; , are the power sale amount to the superior power grid and the maximum value of power sale amount at time t;

[0162] S2: Establish a wind and light prediction model: The wind and light prediction model consists of a wind and light output uncertainty module and a BP neural network; The output uncertainty factor of the wind and light output uncertainty model and the wind speed and light intensity are input into the BP neural network together as input features;

[0163] In the step S2, the prediction of wind and light energy is modeled, including the following process:

[0164] S2-1. Model the uncertainty of wind and light output:

[0165] (23)

[0166] (24)

[0167] Wherein, and are uncertain parameters, which are the net output powers of the wind turbine and the photovoltaic unit; and are the predicted output values of the wind turbine unit and the photovoltaic unit; represents the uncertainty in predicting the output of the wind turbine and the photovoltaic unit, and its range is between 0 and 1; k1 and k2 are the influence degrees of the errors between the actual output and the predicted output of the wind turbine and the photovoltaic unit in the overall uncertainty respectively;

[0168] S2-2. BP Neural Network Classification Prediction Modeling Optimized by Particle Swarm Optimization Algorithm:

[0169] 1) Collect data related to wind and light, including wind speed, light intensity, temperature, and historical power generation data, and perform preprocessing tasks such as data cleaning, normalization, and feature extraction;

[0170] 2) Incorporate the uncertainty model of wind and light output into the BP neural network. The specific steps are as follows: First, through statistical analysis of historical power generation data, identify and quantify the factors of wind speed fluctuations and light changes that affect wind and light output. Second, extract these factors as additional features and input them into the BP neural network together with wind speed and light intensity as input features. Finally, establish a classification prediction model to predict the future power generation of wind and light energy;

[0171] 3) Use the particle swarm algorithm to optimize the connection weights and bias terms of the BP neural network to maximize the objective function of wind and light utilization rate. The specific steps are as follows: First, initialize the particle swarm and randomly generate a set of possible weight and bias combinations. Then, the particle swarm evaluates the effects of each combination according to the fitness function, which takes into account the real-time data of wind energy and solar energy as well as historical power generation. Through continuous iteration, the particle swarm updates its own position according to the best fitness and gradually converges to the optimal solution;

[0172] 4) Use the optimized BP neural network model to train the training data and tune the model according to the performance on the validation set to obtain the best prediction performance;

[0173] Optimization Objective Function:

[0174] (25)

[0175] In the formula, and respectively represent the power generation of the wind turbine and the photovoltaic generator when the wind force is and the light intensity is ; represents the predicted value of wind energy when the wind force is at time t; represents the predicted value of light energy when the light intensity is at time t;

[0176] This objective function should be used in the optimization module of the prediction model. Specifically, it is used to guide the particle swarm algorithm to adjust the weights and biases when training the BP neural network. By maximizing this objective function, the model can effectively integrate the predicted data of wind energy and light energy, thereby achieving the optimal scheduling of renewable energy power generation capacity and improving the overall energy efficiency of the system.

[0177] S2-3. Build a model for the cost during the operation of the multi-energy complementary system and the corresponding constraint conditions, the process is as follows:

[0178] Build an investment and maintenance cost model for the multi-energy complementary system:

[0179] (26)

[0180] The corresponding power balance constraint conditions are:

[0181] (27)

[0182] (28)

[0183] In the formula, 、 、 、 、 、 、 、 、 、 、 、 、 、 、 respectively represent the total load power demand of the multi-energy complementary system, the total heat load demand of the system, the electric power purchased from the power grid, the thermal power output by the combined heat and power unit, the thermal power output by the gas boiler unit, the electric power output by the combined heat and power unit, the electric power obtained by the electrolyzer in the HES, the electric power for hydrogen production by the electrolyzer in the HES, the charging power of the BESS, the discharging power of the BESS, the electric power obtained by the fuel cell in the HES, the electric power generated by the fuel cell in the HES, the heat storage power of the TES, the heat release power of the TES, the actual output power of the wind turbine unit, and the actual output power of the photovoltaic unit; 、 are the binary variables for heat storage and heat release of the TES respectively;

[0184] Where:

[0185] (29)

[0186] (30)

[0187] In the formula: Taking 1 represents the photovoltaic unit; Taking 2 represents the wind turbine unit; Taking 3 represents the battery energy storage system; Taking 4 represents the thermal energy storage system; Take 5, representing a combined heat and power unit; Take 6, representing an electrolyzer (ELC); Take 7, representing a hydrogen storage tank; Take 8, representing a fuel cell; Take 9, representing a gas boiler; Take 10, representing an absorption chiller; Take 11, representing a voltage chiller; is the benchmark discount rate; is the equipment life cycle; is the equipment unit investment cost; is the equipment unit capacity; is the equipment annual fixed maintenance cost, is the equipment unit maintenance cost;

[0188] (31)

[0189] (32)

[0190] (33)

[0191] (34)

[0192] (35)

[0193] In the formula, is the transaction cost with the power grid, is the gas purchase cost, is the environmental cost generated by the gas turbine unit, is the penalty cost for curtailment of solar and wind power, is the charge-discharge loss and maintenance cost of the EES, is the heat storage and charge-discharge loss cost of the HES, is the heat storage and charge-discharge loss cost of the TES; , are the electricity purchase price and electricity selling price for trading with the power grid at time t, , are the electricity purchase quantity and electricity selling quantity to the superior power grid at time t; is the unit purchase price of natural gas; is the lower heating value of natural gas; , are the output powers of the combined heat and power unit and the gas boiler unit at time t; is the working efficiency of the gas boiler unit; is the environmental cost of the gas boiler unit and the electricity purchased from the power grid; and are the curtailment of wind and curtailment of light penalty factors respectively; and are the curtailment of wind volume and curtailment of light volume at time t respectively.

[0194] Step S3: Cascade the wind and light prediction model and the multi - energy complementary system model, and jointly optimize them using the differential creative search algorithm to obtain the optimal energy supply and energy storage scheduling plan, including the following steps:

[0195] Step S3 - 1: Initialize parameters: First, set the population size and the range of decision variables, and then randomly generate the initial population , the initial population consists of more than 1 individual; the variables included in the individual are: the hydrogen production electric power of the electrolyzer in the HES , the charging power of the BESS , the electric power obtained by the electrolyzer in the HES , the hydrogen production electric power of the electrolyzer in the HES , the electric power obtained by the fuel cell in the HES , the electric power generated by the fuel cell in the HES , the heat storage power of the TES , the heat release power of the TES , the output electric power of the combined heat and power unit , the actual output power of the wind turbine unit , the actual output power of the photovoltaic unit , the objective function is the total operating cost of the multi - energy complementary system:

[0196] (36)

[0197] In the formula, represents the d - th parameter of the -th candidate solution, D is the number of parameters of the candidate solution; the number of candidate solutions is NP; represents a uniform distribution on the interval , and and represent the lower bound and upper bound of the d - th parameter respectively;

[0198] Step S3 - 2: Fitness evaluation: Use the objective function value corresponding to each individual as the initial fitness value:

[0199] (37)

[0200] Step S3-3: Select the individual corresponding to the minimum fitness value as the best individual ;

[0201] Step S3-4: Differential knowledge acquisition: Randomly select two individuals , Calculate η and Coefficient:

[0202] The calculation method of the η coefficient is:

[0203] (38)

[0204] (39)

[0205] The calculation method of the coefficient is:

[0206] (40)

[0207] (41)

[0208] In the formula, t is the number of iterations; the symbol represents rounding calculation, is the rank of the th individual at the beginning of the t-th iteration; and are the d-th parameter values of the two individuals , ;

[0209] Update parameters:

[0210] (42)

[0211] (43)

[0212] In the formula: is the updated value of the d-th parameter value of the i-th individual;

[0213] Step S3-5: Knowledge integration and new solution generation:

[0214] Calculate the convergence factor:

[0215] (44)

[0216] In the formula, is the convergence factor at the t-th iteration; represents the current number of function calculations at the t-th iteration, represents the maximum number of function calculations;

[0217] Update the individual position:

[0218] (45)

[0219] wherein, is the d-th parameter of the best individual in the current iteration;

[0220] Update the individual position by generating random numbers using the Linnik distribution:

[0221] (46)

[0222] wherein, is the d-th parameter of the individual, represents a Linnik distribution random number generator with control parameters α and σ;

[0223] Step S3-6: Individual diversification: Randomly generate N new individuals:

[0224] (47)

[0225] wherein, is the np-th new individual, and LB and UB are the lower and upper bounds;

[0226] Step S3-7: Retrospective evaluation: Replace the selected individuals with the new individuals:

[0227] (48)

[0228] (49)

[0229] wherein, represents the i-th individual in X at the (t + 1)-th iteration; represents the optimal solution of X at the t-th iteration;

[0230] Step S3-8: Determine whether the maximum number of iterations is reached or the stopping condition is satisfied. If so, output the final optimal solution and its corresponding optimal fitness value; otherwise, go to Step S3-7.

Claims

1. A collaborative optimization method for hybrid energy storage and wind-solar forecasting in desert areas, characterized in that Including the following steps: Step S1: Establish a multi-energy complementary system model: The multi-energy complementary system model includes a wind power generation module, a photovoltaic power generation module, a hybrid energy storage module, a user load module, a gas boiler module, a combined heat and power unit module, and a power grid power purchase and sale module. The wind power generation module and the photovoltaic power generation module convert renewable energy into electrical energy, which is directly supplied to the user load module or traded through the power grid power purchase and sale module. The gas boiler module and the combined heat and power unit module provide heat energy to meet the heat load demand of the user load module. The hybrid energy storage module includes a BESS module, a HES module, and a TES module. The hybrid energy storage module stores the surplus power when the electrical energy is in excess. Step S2: Establish a wind and light prediction model: The wind and light prediction model consists of a wind and light output uncertainty module and a BP neural network. The output uncertainty generated by the wind and light output uncertainty model and the wind speed and light intensity are input into the BP neural network together as input features. Modeling of wind and light output uncertainty （1） （2） In the formula, and are uncertain parameters, and are the net output powers of the wind turbine and the photovoltaic unit; and are the predicted output values of the wind turbine unit and the photovoltaic unit; represents the uncertainty in predicting the output of the wind turbine and the photovoltaic unit, and its range is between 0 and 1; k1 and k2 are the influence degrees of the errors between the actual output and the predicted output of the wind turbine and the photovoltaic unit in the overall uncertainty respectively; Step S3: Cascade the wind and light prediction model and the multi-energy complementary system model, and jointly optimize them using a differential creative search algorithm, obtaining the optimal energy supply and energy storage scheduling scheme, including the following steps: Step S3-1: Initialize parameters: First, set the population size and the range of decision variables, and then randomly generate the initial population , the initial population consists of more than 1 individual; the variables included in the individual are: the hydrogen production electric power of the electrolyzer in HES , the charging power of BESS , the electric power obtained by the electrolyzer in HES , the hydrogen production electric power of the electrolyzer in HES , the electric power obtained by the fuel cell in HES , the electric power generated by the fuel cell in HES , the heat storage power of TES , the heat release power of TES , the output electric power of the combined heat and power unit , the actual output power of the wind turbine unit , the actual output power of the photovoltaic unit , the objective function is the total operating cost of the multi-energy complementary system: （3） In the formula, represents the d-th parameter of the n-th candidate solution, where D is the number of parameters of the candidate solution; the number of candidate solutions is NP; represents a uniform distribution on the interval , and represent the lower bound and upper bound of the d-th parameter, respectively; Step S3-2: Fitness evaluation: Use the objective function value corresponding to each individual as the initial fitness value: （4） Step S3-3: Select the individual corresponding to the minimum fitness value as the best individual ; Step S3-4: Differential knowledge acquisition: Randomly select two individuals , Calculate and Coefficient: The calculation method of the η coefficient is as follows: （5） （6） The calculation method of the coefficient is as follows: （7） （8） where \(t\) is the number of iterations; the symbol represents rounding calculation, is the rank of the -th individual at the beginning of the \(t\)-th iteration; Update parameters: （9） （10） In the formula: and are the d-th parameter values of two individuals , ; is the updated value of the d-th parameter value of the i-th individual; Step S3-5: Knowledge integration and new solution generation: Calculate the convergence factor: （11） wherein, is the convergence factor at the t-th iteration; represents the current number of function calculations at the t-th iteration, represents the maximum number of function calculations; Update the individual position: （12） Wherein, is the d-th parameter of the best individual in the current iteration; Use the Linnik distribution to generate random numbers to update the individual position: （13） wherein, is the d-th parameter of the individual, represents a Linnik distribution random number generator with control parameters α and σ; Step S3-6: Individual diversification: Randomly generate N new individuals: （14） where is the np-th new individual, and LB and UB are the lower and upper bounds; Step S3-7: Retrospective evaluation: Replace the selected individuals with the new individuals: （15） （16） In the formula, represents the i-th individual of X at the (t + 1)-th iteration; represents the optimal solution of X at the t-th iteration; Step S3-8: Determine whether the maximum number of iterations is reached or the stop condition is satisfied. If so, output the final optimal solution and its corresponding optimal fitness value; otherwise, go to Step S3-7.

2. The collaborative optimization method for hybrid energy storage and wind and light prediction for desert areas according to claim 1, wherein: In the said Step S1: Model the BESS as: （17） （18） （19） Wherein, and are the remaining power of the BESS at times t and t-1; and are the self-discharge rate and rated capacity of the BESS; and are the charging power and discharging power of the BESS; and are the charging efficiency coefficient and discharging efficiency coefficient of the BESS; and are respectively the maximum charging power and maximum discharging power of the BESS at time t; and are respectively the maximum continuous charging power and maximum continuous discharging power of the BESS at time t; is the time interval; Model the HES as: （20） （21） （22） （23） （24） Wherein, and are the electric power obtained by the electrolyzer and the electric power for hydrogen production by the electrolyzer in the HES, respectively; and are the electric power obtained by the fuel cell and the generated electric power in the HES, respectively; and are the thermal powers generated by the electrolyzer and the fuel cell, respectively; and are the working efficiencies of the electrolyzer and the fuel cell; and are the upper and lower limits of the power of the electrolyzer, respectively; and are the upper and lower limits of the power of the fuel cell, respectively; and are the upper and lower limits of the energy storage state of the hydrogen storage tank in the HES, respectively; Model the TES as: （25） （26） （27） （28） （29） In the formula, is the heat storage capacity of the TES at time t; is the self - heat release rate of the TES; , are the heat storage and heat release efficiencies of the TES respectively; , are the heat storage and heat release powers of the TES at time t respectively; , are the binary variables of heat storage and heat release of the TES at time t respectively; , are the maximum and minimum heat storage capacities of the TES respectively; The model of the power grid power purchase and sale module is: （30） （31） Wherein, and are respectively the electricity purchase quantity from the superior power grid and the upper limit value of electricity purchase; and are the electricity sales quantity to the superior power grid and the maximum value of electricity sales.

Images