Multi-energy power supply optimization control method and device, electronic equipment and medium

Abstract

The invention provides a multi-energy power supply optimization control method and device, electronic equipment and a medium, and belongs to the field of electric energy dispatching, and the method comprises the steps: carrying out the supply and demand time sequence prediction of shore power supply and demand historical data, and obtaining a power demand prediction value and a power supply prediction value of each power supply type; determining an energy storage demand according to the power demand predicted value and the power supply predicted value, and constructing a multi-energy shore power cost function and constraint conditions according to the energy storage demand; and constructing an initial charge and discharge control strategy, and performing iterative optimization on the initial charge and discharge control strategy based on a particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy. According to the invention, supply and demand time sequence prediction is carried out on the power demand and various types of power supply through the historical shore power supply and demand data to construct an accurate multi-energy shore power cost function and constraint conditions, and the charge and discharge control strategy is optimized through the particle swarm optimization genetic algorithm to obtain an efficient charge and discharge control strategy. And thus, the shore power supply cost is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy dispatching, and in particular to a multi-energy power supply optimization control method, device, electronic equipment and medium. Background Art

[0002] The power supply of the port power system is a major measure to reduce exhaust pollution from ships docked in the port. Through the multi-energy shore power system, solar energy and wind energy can be used to provide green power supply for port ships. However, since the output of solar energy and wind energy is not stable, it is necessary to combine it with energy storage technology to store the excess electricity produced by wind and solar power generation equipment through the energy storage system, and to supply energy to port ships when the output of wind and solar power generation equipment is insufficient.

[0003] However, the existing multi-energy shore power system simply stores energy when the wind and solar power generation equipment has sufficient capacity, and discharges energy when the capacity is insufficient, without considering the actual power demand for charging and discharging control strategy planning. Considering the cost of energy storage itself, the existing energy storage strategy often results in excessive energy storage, resulting in increased energy storage costs, or insufficient energy storage, resulting in the need to purchase more external grid electricity, resulting in increased electricity purchase costs, which in turn leads to increased shore power supply costs and needs to be improved.

[0004] Therefore, the existing technology has a technical problem that the multi-energy shore power system does not consider the actual electricity demand when planning the charging and discharging control strategy when controlling the charging and discharging of the energy storage system, which leads to an increase in the shore power supply cost and needs to be improved. Summary of the invention

[0005] In view of this, it is necessary to provide a multi-energy power supply optimization control method, device, electronic device and medium to solve the technical problem that the multi-energy shore power system in the prior art does not consider the actual power demand in the charging and discharging control strategy planning when controlling the charging and discharging of the energy storage system, resulting in an increase in the shore power supply cost.

[0006] In order to solve the above technical problems, on the one hand, the present invention provides a multi-energy power supply optimization control method, which is used to optimize the charging and discharging control strategy of the multi-energy shore power system, and to control the charging and discharging of each energy storage subsystem of the multi-energy shore power system to ensure the balance of power supply and demand. The method includes: Perform supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type; Determine the energy storage demand based on the power demand forecast and power supply forecast, and build a multi-energy shore power cost function and constraints based on the energy storage demand; The initial charge and discharge control strategy is constructed according to the energy storage cost objective function and constraint conditions, and the initial charge and discharge control strategy is iteratively optimized based on the particle swarm optimization genetic algorithm to obtain the optimized charge and discharge control strategy.

[0007] In a possible implementation, the power supply types include wind power supply and photovoltaic power supply, and the energy storage subsystem includes a hydrogen energy storage subsystem and a battery energy storage subsystem.

[0008] In a possible implementation, the acquired shore power supply and demand historical data is used to perform supply and demand time series forecasting to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type, including: A historical data matrix is ​​constructed based on the historical data of shore power supply and demand, and a feature matrix is ​​obtained by performing convolution feature extraction on the historical data matrix. The output of the feature matrix is ​​predicted to obtain a preliminary prediction value of power demand and a preliminary prediction value of power supply of each power supply type. Determine the time series weight of each target to be predicted according to the feature matrix; The time series weight and feature matrix are multiplied and weighted to obtain the time series weight vector; The preliminary power demand prediction value and the preliminary power supply prediction value of each power supply type are integrated with the corresponding time series weight vector to obtain the power demand prediction value and the power supply prediction value of each power supply type.

[0009] In a possible implementation, the energy storage demand is determined according to the power demand forecast value and the power supply forecast value, and a multi-energy shore power cost function and constraint conditions are constructed according to the energy storage demand, including: Determine peak hours and peak-period electricity demand based on power demand forecasts, and determine energy storage requirements based on peak-period electricity demand and power supply forecasts; The multi-energy shore power cost function and constraints are constructed based on the power demand forecast, power supply forecast and energy storage demand.

[0010] In a possible implementation, the multi-energy shore power cost function includes power purchase cost, normal loss cost and penalty cost; and the constraints include power balance constraint, dynamic operation constraint and energy storage capacity constraint.

[0011] In a possible implementation, the initial charge and discharge control strategy is iteratively optimized based on a particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy, including: Construct the initial population of the genetic algorithm according to the power demand forecast value, the power supply forecast value of each power supply type, the energy storage demand and the constraint conditions; Based on the preset pointer network, the initial population is individually optimized to obtain the optimized population; The fitness of the population is determined according to the optimized population and the multi-energy shore power cost function, and the optimized population is subjected to rotational population screening and crossover combination mutation according to the population fitness to obtain a mutant population; Iteratively repeat individual optimization, rotation population screening and crossover combination mutation until the preset evolutionary number is reached, and the optimized genetic algorithm population is obtained. The optimized charge and discharge control strategy is determined based on the genetic algorithm population.

[0012] In a possible implementation, the preset pointer network is obtained by training an initial pointer network, and the training of the initial pointer network includes: The initial pointer network is iteratively trained based on the actor-critic algorithm to obtain a trained preset pointer network.

[0013] On the other hand, the present invention also provides a multi-energy power supply optimization control device, which is used to optimize the charge and discharge control strategy of the multi-energy shore power system, and to control the charge and discharge of each energy storage subsystem of the multi-energy shore power system to ensure the balance of power supply and demand. The device includes: A supply and demand forecasting unit, used to perform supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type; An energy storage analysis unit is used to determine energy storage requirements based on power demand forecast values ​​and power supply forecast values, and to construct a multi-energy shore power cost function and constraint conditions based on the energy storage requirements; The control strategy optimization unit is used to construct an initial charge and discharge control strategy according to the energy storage cost objective function and constraint conditions, and iteratively optimize the initial charge and discharge control strategy based on the particle swarm optimization genetic algorithm to obtain the optimized charge and discharge control strategy.

[0014] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: Memory for storing computer programs; The processor is coupled to the memory and is used to execute a computer program to implement the steps in the above-mentioned multi-energy power supply optimization control method.

[0015] On the other hand, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned multi-energy power supply optimization control method are implemented.

[0016] The beneficial effects of the present invention are as follows: the embodiment of the present invention provides a multi-energy power supply optimization control method, which first performs supply and demand timing forecasting on the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type; then determines the energy storage demand based on the power demand forecast value and the power supply forecast value, and constructs an energy storage cost function and constraints based on the energy storage demand; finally, constructs an initial charge and discharge control strategy based on the energy storage cost objective function and constraints, and iteratively optimizes the initial charge and discharge control strategy based on a particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy. The present invention uses shore power supply and demand historical data to perform supply and demand timing forecasting on power demand and various types of power supply, estimates energy storage demand based on the forecast results, thereby constructing an accurate multi-energy shore power cost function and constraints, and optimizes the charge and discharge control strategy through a particle swarm optimization genetic algorithm to obtain an efficient charge and discharge control strategy, thereby effectively reducing the shore power supply cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of an embodiment of a multi-energy power supply optimization control method provided by the present invention; Figure 2 A schematic diagram of a flow chart of supply and demand timing forecasting according to an embodiment of the present invention; Figure 3 A schematic diagram of a process for constructing a multi-energy shore power cost function according to an embodiment of the present invention; Figure 4 A schematic diagram of a flow chart of iterative optimization of a charge and discharge control strategy according to an embodiment of the present invention; Figure 5 A schematic structural diagram of an embodiment of a multi-energy power supply optimization control device provided by the present invention; Figure 6 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0021] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] Before presenting the embodiments, the following names are explained.

[0024] Port micro-network: refers to the information aggregation based on the historical port berthing data of the port, abstracting the berths and anchorages in the port as nodes, and abstracting the port routes as edges, and constructing a simplified representation of the port channel-berth-anchorage micro-topological network.

[0025] The present invention provides a multi-energy power supply optimization control method, device, electronic device and medium, which are described below respectively.

[0026] Figure 1 A flow chart of an embodiment of the multi-energy power supply optimization control method provided by the present invention is as follows: Figure 1 As shown, the multi-energy power supply optimization control method includes: S101, performing supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type; S102, determining energy storage demand according to the power demand forecast value and the power supply forecast value, and constructing a multi-energy shore power cost function and constraint conditions according to the energy storage demand; S103, constructing an initial charge and discharge control strategy according to the energy storage cost objective function and constraint conditions, and iteratively optimizing the initial charge and discharge control strategy based on a particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy.

[0027] Compared with the prior art, the multi-energy power supply optimization control method provided by the embodiment of the present invention first performs supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain the power demand forecast value and the power supply forecast value of each power supply type; then determines the energy storage demand based on the power demand forecast value and the power supply forecast value, and constructs the energy storage cost function and constraints based on the energy storage demand; finally, constructs the initial charge and discharge control strategy based on the energy storage cost objective function and the constraints, and iteratively optimizes the initial charge and discharge control strategy based on the particle swarm optimization genetic algorithm to obtain the optimized charge and discharge control strategy. The present invention uses the shore power supply and demand historical data to forecast the power demand and various types of power supply, estimates the energy storage demand through the forecast results, thereby constructing an accurate multi-energy shore power cost function and constraints, and optimizes the charge and discharge control strategy through the particle swarm optimization genetic algorithm to obtain an efficient charge and discharge control strategy, thereby effectively reducing the shore power supply cost.

[0028] In some embodiments of the present invention, the power supply types include wind power supply and photovoltaic power supply, and the energy storage subsystem includes a hydrogen energy storage subsystem and a battery energy storage subsystem.

[0029] Specifically, in the multi-energy shore power system of the embodiment, the power generation equipment includes wind power supply and photovoltaic power supply, and the energy storage subsystem includes a hydrogen energy storage subsystem and a battery energy storage subsystem. For the geographical environment where there is sea breeze and few obstructions in the shore port, wind power supply and photovoltaic power supply can effectively provide electricity. The energy storage subsystem uses the relatively clean hydrogen energy storage subsystem as the main energy storage method and the battery energy storage subsystem as the auxiliary energy storage method.

[0030] For wind power generation systems, according to current research on wind power generation technology, the wind turbine output power is related to the wind speed, and the wind power generation power can be approximated The mathematical model is expressed as follows:

[0031] in, is the rated power of the fan, is the rated wind speed of the fan, and Expressed as the cut-in and cut-out wind speeds of the fan, is the mechanical transmission efficiency, is the power conversion efficiency, is the air density, is the impeller area, is the wind power utilization coefficient, is the actual wind speed.

[0032] Wind power operation costs The mathematical model formula is expressed as:

[0033] in, is the unit power operation and maintenance cost of the wind turbine, for Wind power output during the period, is the loss cost coefficient of wind power equipment.

[0034] For photovoltaic power generation systems, based on the characteristics of photovoltaic arrays according to the current law and voltage law, the photovoltaic power generation mathematical model can be expressed as follows:

[0035]

[0036] Among them, due to the complex and changeable environment, the PU curve also changes accordingly. Therefore, it is necessary to find its optimal operating voltage to track the maximum power point. The maximum power point tracking is generally carried out using the MPPT (Maximum Power Point Tracking) algorithm. The purpose of maximum power point tracking is to sample the output of the solar cell and try to maintain the maximum power output under any environmental conditions. Maximum power point tracking devices are generally integrated into power conversion devices, which include voltage or current conversion and filtering, and then drive the load.

[0037] Since the light intensity is severely constrained by the environment and has a strong randomness, the production capacity of photovoltaic arrays is fluctuating and difficult to predict. The confidence evaluation method is usually used to estimate its actual production capacity and photovoltaic output power. It can be expressed by the formula:

[0038] in, It is the maximum capacity under standard test conditions. is the light intensity under standard test conditions, and its value in the embodiment is 1000 W / m. is the temperature under standard test conditions, generally 25°C, is the actual light intensity, is the power temperature coefficient, is the ambient temperature, Rated operating temperature for the component.

[0039] The mathematical model formula of photovoltaic operation cost is expressed as:

[0040] in, is the unit power operation and maintenance cost of the photovoltaic generator set, for Photoelectric output power in time period, is the loss cost coefficient of optoelectronic equipment.

[0041] For the battery energy storage subsystem, the charging and discharging state formula is expressed as:

[0042]

[0043]

[0044] in, and Respectively Time and Battery capacity, is the total battery capacity, is the battery current, is the self-leakage rate, is the charge and discharge efficiency, Indicates the adjacent time difference.

[0045] For the hydrogen energy storage subsystem, the electrolysis hydrogen production power The formula is:

[0046] in, is the electrolytic cell current, is the electrolytic cell temperature, is the electrolyte ohmic resistance parameter, is the effective area of ​​the electrolytic cell, is the electrode overvoltage coefficient, is the reversible voltage.

[0047] According to the empirical model, the hydrogen production rate of water electrolysis is It can be expressed as:

[0048] in, is the number of electrolytic cell units; is the Faraday efficiency; is the Faraday constant, taken as 96485C / mol; is the number of electrons transferred per reaction.

[0049] The hydrogen produced by the alkaline electrolyzer can be stored by applying gaseous high-pressure hydrogen storage technology, and the amount of hydrogen stored in the tank can be calculated by the hydrogen storage rate. According to the Clapeyron equation, the formula for hydrogen storage is expressed as:

[0050] in, express The hydrogen storage capacity of the hydrogen storage tank at any time, is the hydrogen storage rate; and are the pressure and volume of the hydrogen storage tank, is the molar amount of hydrogen, is the ideal gas constant, is the hydrogen storage thermodynamic temperature.

[0051] For the stored hydrogen, proton exchange membrane fuel cells are used. It is mainly affected by the electrochemical characteristics. There are ohmic losses and activation losses inside the fuel cell. Therefore, the actual output voltage of the hydrogen fuel cell is and actual output power The formula is:

[0052]

[0053] in, Indicates the number of single cells. is the fuel cell output current, is the exchange current, is the internal resistance of the fuel cell.

[0054] Hydrogen energy storage subsystem operating costs The formula is:

[0055] in, represents the loss cost of the hydrogen energy storage subsystem, express The fuel cell output power during the period, is the loss cost coefficient of the hydrogen energy storage subsystem.

[0056] Fuel cell hydrogen demand It can be expressed as:

[0057] It should be noted that the above is only one type of embodiment of the present invention, and other power supply types and storage subsystems may also be included in other embodiments. For example, the power supply type may also include tidal power generation, and the energy storage subsystem may also include a pumped storage subsystem.

[0058] In some embodiments of the present invention, Figure 2 Schematic diagram of the flow of supply and demand timing forecasting according to an embodiment of the present invention. Figure 2 As shown, the obtained shore power supply and demand historical data are used for supply and demand time series forecasting to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type, including: S201, constructing a historical data matrix according to the historical data of shore power supply and demand, performing convolution feature extraction on the historical data matrix to obtain a feature matrix, and performing output prediction on the feature matrix to obtain a preliminary prediction value of power demand and a preliminary prediction value of power supply of each power supply type; S202, determining the time series weight of each target to be predicted according to the feature matrix; S203, multiplying the time series weight and the feature matrix and performing weighted summation to obtain a time series weight vector; S204, integrating the preliminary power demand prediction value and the preliminary power supply prediction value of each power supply type with the corresponding time series weight vector to obtain the power demand prediction value and the power supply prediction value of each power supply type.

[0059] Specifically, in order to accurately determine the energy storage demand, the embodiment predicts the power supply of wind power generation and photovoltaic power generation and the power supply of the network based on TPA-LSTM (Temporal Pattern Attention for Multivariate Time Series Forecasting).

[0060] For the historical data of shore power supply and demand, taking the power demand forecast as an example, the embodiment first constructs the historical data matrix of power demand according to the historical data of shore power supply and demand Then for the historical data matrix The Row features, using k CNN convolutions to extract convolution features to obtain the power load feature matrix , the formula is:

[0061] Then with It represents the preliminary forecast value of power demand obtained based on feature prediction. and power load characteristic matrix No. The power load weight is obtained by , the formula is:

[0062]

[0063] Among them, the power load weight Indicates that each row of the matrix is ​​to be predicted The strength of the effect of each time series on The strength of the impact.

[0064] Then the power load characteristic matrix Each row of is multiplied by the corresponding weight and weighted summed to obtain the time series weight vector of the power load , the formula is:

[0065] Finally, the time series weight vector of the power load is and preliminary forecast of power demand Perform integral operation to obtain the power demand forecast value, which is expressed as follows:

[0066]

[0067] In addition, for the power supply forecast values ​​of wind power generation and photovoltaic power generation, the forecasting method is the same as the steps of the power demand forecast value, which will not be repeated here.

[0068] In some embodiments of the present invention, Figure 3 FIG. 1 is a flow chart of constructing a multi-energy shore power cost function according to an embodiment of the present invention. Figure 3 As shown in the figure, the energy storage demand is determined according to the power demand forecast value and the power supply forecast value, and the multi-energy shore power cost function and constraint conditions are constructed according to the energy storage demand, including: S301, determine the peak period and the power demand during the peak period according to the power demand forecast value, and determine the energy storage demand according to the power demand during the peak period and the power supply forecast value; S302: Construct a multi-energy shore power cost function and constraints based on the power demand forecast value, power supply forecast value and energy storage demand.

[0069] In some embodiments of the present invention, the multi-energy shore power cost function includes power purchase cost, normal loss cost and penalty cost; and the constraint conditions include power balance constraint, dynamic operation constraint and energy storage capacity constraint.

[0070] Specifically, after obtaining the electricity demand forecast value and the power supply forecast value of each power supply type, it is necessary to determine the peak hours and peak electricity demand, and conduct energy storage demand analysis. For multi-energy shore power systems, the operating status can be divided into wind-solar power supply status, wind-solar power storage status and wind-solar hydrogen storage power supply status.

[0071] For wind and solar power supply, When the multi-energy shore power system is in the wind-solar power supply state. At this time, the power load is completely met by the wind-solar fusion power generation, and the excess electricity can be stored in the form of electrolysis of water to produce ammonia, or directly stored by the energy storage subsystem. When, the energy storage subsystem When , and the energy storage subsystem When the power is turned on, the state is converted to wind-solar-hydrogen storage power supply state.

[0072] For wind, solar and storage power supply, , but the energy storage subsystem When , the system is in the wind, solar and storage power supply state. When , and the energy storage subsystem When the power is turned off, the state changes to wind-solar-hydrogen storage power supply state.

[0073] For wind and solar hydrogen storage power supply, if , the system is in the wind-solar-hydrogen storage power supply state; if , energy storage system charging, , the energy storage system discharges.

[0074] In the real-time adjustment control optimization, the embodiment determines the energy storage demand through operation status analysis, and constructs a multi-energy shore power cost function and constraint conditions based on the energy storage demand, power demand forecast value and power supply forecast value.

[0075] The multi-energy shore power cost includes three parts: system power purchase cost, normal operation loss cost and penalty cost. Indicates the cost of electricity that needs to be purchased when wind and solar power generation is insufficient, and the normal operation loss cost Represents the operating loss cost and penalty cost of wind and solar power generation and energy storage subsystems Indicates the cost caused by possible errors in the model. The target multi-energy shore power cost function formula is expressed as:

[0076] For system power purchase cost , which can be expressed as:

[0077] in, and They are The electricity purchase cost of the electrolyzer and battery at the moment, and They are The amount of electricity provided by the power grid to the electrolyzer and battery at any given moment. for The time-of-use electricity price of the power grid at the moment, for When the wind, solar and hydrogen storage power is insufficient, the grid output power is Small, power imbalance eliminated, if If it is larger, the power will be internally unstable.

[0078] Cost of normal operation loss and penalty costs , which can be expressed as:

[0079]

[0080]

[0081] in, Indicates the target value of SOC at termination; is the weight factor of the deviation between the battery SOC and the preset value, The weighting factor between hydrogen storage capacity, and They are The hydrogen storage capacity at the moment and the initial hydrogen storage capacity.

[0082] At the same time, in order to ensure the safe and stable operation of the system, it is also necessary to establish constraints for the multi-energy shore power system, including power balance constraints, dynamic motion constraints and energy storage capacity constraints.

[0083] Among them, the purpose of the power balance constraint is to ensure that the power supplied by the integrated system and the power grid should be equal to the user's power load at that moment. The formula is expressed as:

[0084]

[0085] in, and express The power required by the ship and the battery charging power at all times, express The power provided by energy storage to ship users at all times, , and Respectively expressed as The power provided by wind energy, solar energy and hydrogen fuel cells to energy storage at all times.

[0086] The purpose of dynamic operation constraint is to ensure the safe operation of fuel cells and alkaline electrolyzers, and to constrain the operating range of the operating power of fuel cells and alkaline electrolyzers. The formula is expressed as:

[0087] in, and Represent the operating power of the fuel cell and alkaline electrolyzer respectively.

[0088] The purpose of energy storage capacity constraint is to ensure that energy and hydrogen storage are within the maximum allowable capacity range of the battery and hydrogen storage tank equipment. The formula is expressed as:

[0089] in, and They represent the battery charge and the hydrogen pressure of the hydrogen storage tank respectively. Indicates the upper limit of the hydrogen pressure status of the hydrogen tank.

[0090] In some embodiments of the present invention, Figure 4 FIG. 1 is a flow chart of iterative optimization of the charge and discharge control strategy according to an embodiment of the present invention. Figure 4 As shown, the initial charge and discharge control strategy is iteratively optimized based on the particle swarm optimization genetic algorithm to obtain the optimized charge and discharge control strategy, including: S401, constructing an initial population of a genetic algorithm according to power demand forecast values, power supply forecast values ​​of each power supply type, energy storage requirements and constraint conditions; S402, performing individual optimization on the initial population based on a preset pointer network to obtain an optimized population; S403, determining the population fitness according to the optimized population and the multi-energy shore power cost function, and performing rotation population screening and crossover combination mutation on the optimized population according to the population fitness to obtain a mutant population; S404, iteratively repeat individual optimization, round-robin population screening and crossover combination mutation until a preset evolutionary number is reached to obtain an optimized genetic algorithm population, and determine an optimized charge and discharge control strategy based on the genetic algorithm population.

[0091] Specifically, after constructing multiple energy shore power cost functions and constraints, in order to obtain an efficient charging and discharging control strategy, the embodiment uses a particle swarm optimization genetic algorithm to iteratively optimize the charging and discharging control strategy.

[0092] First, the embodiment sets the evolutionary number Gen=1, and constructs the initial population of the genetic algorithm based on the power demand forecast value, the power supply forecast value of each power supply type, the energy storage demand and the constraint conditions. Then the embodiment optimizes and selects the individuals in the initial population through the trained pointer network to obtain the optimized population. Then, the fitness value of the population is calculated based on the multi-energy shore power cost function, and the formula is expressed as:

[0093] in, represents fitness, Indicates The cost function of the part is ,in Indicates the population size.

[0094] Then, the embodiment performs population screening through a new population screening algorithm based on the round-robin method, and selects a new population with a probability proportional to the fitness. The probability formula is expressed as:

[0095] Then the embodiment adopts a standardized crossover method to perform multiple sequences on the individuals of the population to obtain intersections, take the smaller ones as independent variables, and use the rest as dependent variables to complete an iterative evolution of the genetic algorithm.

[0096] Finally, by repeating the above iterative evolution process until the preset evolutionary number is reached, the optimized genetic algorithm population is obtained, and the optimal charge and discharge control strategy is determined to calculate the charge and discharge power of the energy storage and fuel cell.

[0097] Compared with the existing direct use of genetic algorithms, the particle swarm optimization genetic algorithm of the embodiment can effectively accelerate the evolution speed of the genetic algorithm and improve the optimization effect by adding a trained pointer network to optimize the individuals in the initial population.

[0098] In some embodiments of the present invention, the preset pointer network is obtained by training the initial pointer network, and the training of the initial pointer network includes: The initial pointer network is iteratively trained based on the actor-critic algorithm to obtain a trained preset pointer network.

[0099] Specifically, for the pointer network used to optimize the population individuals, the embodiment trains the network through the actor-critic algorithm. First, the embodiment constructs an initial evaluation model, and then uses the initial evaluation model to score the optimization effect of the population individuals input into the initial evaluation model and the population individuals output by the initial pointer network; Then, the embodiment adjusts the parameters of the initial pointer network according to the optimization effect score, determines the actual optimization effect according to the input and output population individuals and the multi-energy shore power cost function, and adjusts the parameters of the initial evaluation model according to the actual optimization effect. In the iterative process, the parameters of the pointer network are continuously adjusted through the evaluation model, and the parameters of the evaluation model are adjusted according to the actual optimization effect. This allows the evaluation model to give a more accurate optimization effect score, and the pointer network can obtain a better optimization effect.

[0100] In summary, in order to reasonably plan the charging and discharging control strategy and reduce the cost of shore power supply, the present invention first performs supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain the power demand forecast value and the power supply forecast value of each power supply type; then the energy storage demand is determined according to the power demand forecast value and the power supply forecast value, and the energy storage cost function and constraints are constructed according to the energy storage demand; finally, the initial charging and discharging control strategy is constructed according to the energy storage cost objective function and the constraints, and the initial charging and discharging control strategy is iteratively optimized based on the particle swarm optimization genetic algorithm to obtain the optimized charging and discharging control strategy. The present invention uses the shore power supply and demand historical data to perform supply and demand time series forecasting on the power demand and each type of power supply, estimates the energy storage demand through the forecast results, thereby constructing an accurate multi-energy shore power cost function and constraints, and optimizes the charging and discharging control strategy through the particle swarm optimization genetic algorithm to obtain an efficient charging and discharging control strategy, thereby effectively reducing the cost of shore power supply.

[0101] At the same time, in the process of finding the optimal charge and discharge control strategy, the particle swarm optimization genetic algorithm provided by the present invention can optimize the selection of individuals in the initial population by adding a trained pointer network, which can effectively accelerate the evolution speed of the genetic algorithm and improve the optimization effect.

[0102] In order to better implement the multi-energy power supply optimization control method in the embodiment of the present invention, based on the multi-energy power supply optimization control method, correspondingly, Figure 5 As shown, the present invention also provides a multi-energy power supply optimization control device, and the multi-energy power supply optimization control device 500 includes: The supply and demand prediction unit 501 is used to perform supply and demand time series prediction on the acquired shore power supply and demand historical data to obtain a power demand prediction value and a power supply prediction value of each power supply type; The energy storage analysis unit 502 is used to determine the energy storage demand according to the power demand prediction value and the power supply prediction value, and to construct a multi-energy shore power cost function and constraint conditions according to the energy storage demand; The control strategy optimization unit 503 is used to construct an initial charge and discharge control strategy according to the energy storage cost objective function and the constraint conditions, and iteratively optimize the initial charge and discharge control strategy based on the particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy.

[0103] The multi-energy power supply optimization control device 500 provided in the above embodiment can implement the technical solution described in the above multi-energy power supply optimization control method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above multi-energy power supply optimization control method embodiment, which will not be repeated here.

[0104] like Figure 6As shown, the present invention also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602 and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0105] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 602, such as the multi-energy power supply optimization control method of the present invention.

[0106] In some embodiments, the processor 601 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 601 may be local or remote. In some embodiments, the processor 601 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0107] In some embodiments, the memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. In other embodiments, the memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 600.

[0108] Furthermore, the memory 602 may include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store application software installed in the electronic device 600 and various data.

[0109] In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 603 is used to display information of the electronic device 600 and to display a visual user interface. The components 601-603 of the electronic device 600 communicate with each other through a system bus.

[0110] In one embodiment, when the processor 601 executes the multi-energy power supply optimization control program in the memory 602, the following steps may be implemented: Perform supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type; Determine the energy storage demand based on the power demand forecast and power supply forecast, and build a multi-energy shore power cost function and constraints based on the energy storage demand; The initial charge and discharge control strategy is constructed according to the energy storage cost objective function and constraint conditions, and the initial charge and discharge control strategy is iteratively optimized based on the particle swarm optimization genetic algorithm to obtain the optimized charge and discharge control strategy.

[0111] It should be understood that: when the processor 601 executes the multi-energy power supply optimization control program in the memory 602, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0112] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 600 mentioned, and the electronic device 600 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 600 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0113] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the multi-energy power supply optimization control method provided in the above-mentioned method embodiments.

[0114] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0115] The multi-energy power supply optimization control method, device, electronic device and storage medium provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A multi-energy power supply optimization control method, characterized in that: The method is used to optimize the charging and discharging control strategy of the multi-energy shore power system, and to control the charging and discharging of each energy storage subsystem of the multi-energy shore power system to ensure the balance of power supply and demand. Perform supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type; Determine energy storage demand according to the power demand forecast value and the power supply forecast value, and construct a multi-energy shore power cost function and constraint conditions according to the energy storage demand; An initial charge and discharge control strategy is constructed according to the energy storage cost objective function and constraint conditions, and the initial charge and discharge control strategy is iteratively optimized based on a particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy.

2. The multi-energy power supply optimization control method according to claim 1, characterized in that: The power supply types include wind power supply and photovoltaic power supply, and the energy storage subsystem includes a hydrogen energy storage subsystem and a battery energy storage subsystem.

3. The multi-energy power supply optimization control method according to claim 1, characterized in that: The supply and demand time series forecasting of the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​of each power supply type includes: Constructing a historical data matrix according to the historical data of shore power supply and demand, performing convolution feature extraction on the historical data matrix to obtain a feature matrix, and performing output prediction on the feature matrix to obtain a preliminary prediction value of power demand and a preliminary prediction value of power supply of each power supply type; Determine the time series weight of each target to be predicted according to the feature matrix; The timing weight and the feature matrix are multiplied and weighted to obtain a timing weight vector; The preliminary power demand prediction value and the preliminary power supply prediction value of each power supply type are integrated with the corresponding timing weight vector to obtain the power demand prediction value and the power supply prediction value of each power supply type.

4. The multi-energy power supply optimization control method according to claim 1, characterized in that: The determining of the energy storage demand according to the power demand forecast value and the power supply forecast value, and constructing a multi-energy shore power cost function and constraint conditions according to the energy storage demand, include: Determine the peak period and the power demand during the peak period according to the power demand forecast value, and determine the energy storage demand according to the power demand during the peak period and the power supply forecast value; A multi-energy shore power cost function and constraint conditions are constructed according to the power demand forecast value, the power supply forecast value and the energy storage demand.

5. The multi-energy power supply optimization control method according to claim 4 is characterized in that: The multi-energy shore power cost function includes power purchase cost, normal loss cost and penalty cost; the constraint conditions include power balance constraint, dynamic operation constraint and energy storage capacity constraint.

6. The multi-energy power supply optimization control method according to claim 1, characterized in that: The iterative optimization of the initial charge and discharge control strategy based on the particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy includes: Constructing an initial population of a genetic algorithm according to the power demand forecast value, the power supply forecast value of each power supply type, the energy storage demand and the constraint condition; Performing individual optimization on the initial population based on a preset pointer network to obtain an optimized population; Determine the population fitness according to the optimized population and the multi-energy shore power cost function, and perform rotation population screening and crossover combination mutation on the optimized population according to the population fitness to obtain a mutant population; The individual optimization, the round-robin population screening and the crossover combination mutation are iteratively repeated until a preset evolutionary number is reached to obtain an optimized genetic algorithm population, and an optimized charge and discharge control strategy is determined based on the genetic algorithm population.

7. The multi-energy power supply optimization control method according to claim 6, characterized in that: The preset pointer network is obtained by training an initial pointer network, and the training initial pointer network includes: The initial pointer network is iteratively trained based on the actor-critic algorithm to obtain the trained preset pointer network.

8. A multi-energy power supply optimization control device, characterized in that: The device is used to optimize the charging and discharging control strategy of the multi-energy shore power system, and to control the charging and discharging of each energy storage subsystem of the multi-energy shore power system to ensure the balance of power supply and demand. The device includes: A supply and demand forecasting unit, used to perform supply and demand time series forecasting on the acquired shore power supply and demand historical data to obtain power demand forecast values ​​and power supply forecast values ​​for each power supply type; An energy storage analysis unit, configured to determine energy storage demand according to the power demand forecast value and the power supply forecast value, and construct a multi-energy shore power cost function and constraint conditions according to the energy storage demand; The control strategy optimization unit is used to construct an initial charge and discharge control strategy according to the energy storage cost objective function and constraint conditions, and iteratively optimize the initial charge and discharge control strategy based on a particle swarm optimization genetic algorithm to obtain an optimized charge and discharge control strategy.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor, coupled to the memory, is used to execute a computer program to implement the steps in the multi-energy power supply optimization control method described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the multi-energy power supply optimization control method described in any one of claims 1 to 7 are implemented.

Images