Energy scheduling method and related equipment for a wind-solar-storage-charging-discharging integrated system

Abstract

The present application discloses an energy scheduling method and related devices for a wind-solar-storage-charging-discharging integrated system. The method includes: constructing a simulation model of the wind-solar-storage-charging-discharging integrated system; wherein the simulation model includes: a photovoltaic power generation model, a wind power generation model, a energy storage battery model, a vehicle model, and a energy storage air conditioner model; based on the simulation model and the reinforcement learning algorithm, constructing a first energy scheduling model for the wind-solar-storage-charging-discharging integrated system; combining the moment when the vehicle leaves the parking lot, and taking the minimum difference between the preset target SOC and the SOC after vehicle scheduling as the goal, constructing a second energy scheduling model for the vehicle; jointly training the first energy scheduling model and the second energy scheduling model, so as to perform energy scheduling on the wind-solar-storage-charging-discharging integrated system according to the trained first energy scheduling model and second energy scheduling model. Using the embodiments of the present application can not only simplify the modeling process, but also save the computing power required by the solution algorithm.

Description

Technical Field

[0001] This application relates to the technical field of power supply systems, and in particular, to an energy scheduling method and related equipment for a wind-solar-storage-charging-discharging integrated system. Background Art

[0002] A wind-solar-storage-charging-discharging integrated system is a power supply system that comprehensively utilizes renewable energy. It generates electricity through wind turbines and solar photovoltaic panels, and stores the generated electrical energy in various energy storage devices, such as energy storage batteries and electric vehicles.

[0003] Currently, there are two energy (i.e., electrical energy) scheduling schemes for wind-solar-storage-charging-discharging integrated systems: (1) Using traditional optimization schemes for energy scheduling. However, this scheme requires repeated and complex modeling of wind-solar-storage-charging-discharging integrated systems; (2) Using artificial intelligence schemes for energy scheduling. However, this scheme consumes a large amount of computing power. Summary of the Invention

[0004] This application provides an energy scheduling method and related equipment for a wind-solar-storage-charging-discharging integrated system to solve the problems in the prior art that require repeated and complex modeling of wind-solar-storage-charging-discharging integrated systems and consume a large amount of computing power.

[0005] To achieve the above object, an embodiment of this application provides an energy scheduling method for a wind-solar-storage-charging-discharging integrated system, including:

[0006] Construct a simulation model of the wind-solar-storage-charging-discharging integrated system; wherein, the simulation model includes: a photovoltaic power generation model, a wind power generation model, an energy storage battery model, a vehicle model, and an energy storage air conditioner model;

[0007] Based on the simulation model and the reinforcement learning algorithm, construct a first energy scheduling model of the wind-solar-storage-charging-discharging integrated system;

[0008] Combined with the moment when the vehicle leaves the parking lot, with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling, construct a second energy scheduling model for the vehicle;

[0009] Jointly train the first energy scheduling model and the second energy scheduling model to perform energy scheduling on the wind-solar-storage-charging-discharging integrated system according to the trained first energy scheduling model and the second energy scheduling model.

[0010] As an improvement to the above solution, the photovoltaic power generation model is specifically expressed as:

[0011]

[0012] Wherein, represents the power generation power of the photovoltaic panel, represents solar radiation, represents reference radiation, represents the rated power of the solar cell array, represents the temperature coefficient, represents the reference temperature, represents the temperature of the solar cell array, , represents the ambient temperature of the photovoltaic panel, represents the rated operating temperature of the solar cell array, represents the air temperature when the solar cell array is operating at rated power, represents the light irradiance on the surface of the solar cell array during rated operation;

[0013] The wind power generation model is specifically expressed as:

[0014]

[0015] Among them, represents the output power of the wind turbine generator, represents the rated power of the wind turbine generator; represents the wind speed; represents the cut-in wind speed, represents the rated wind speed, represents the cut-out wind speed; where , , are respectively:

[0016]

[0017]

[0018]

[0019] The energy storage battery model is specifically expressed as:

[0020]

[0021] Among them, represents the electric charge stored in the energy storage battery at moment, represents the electric charge stored in the energy storage battery at moment, represents the charging electric charge of the energy storage battery during the period, represents the charging efficiency of the energy storage battery, represents the discharging electric charge of the energy storage battery during the period, Indicates the discharge efficiency of the energy storage battery; the energy storage battery model satisfies the following constraints:

[0022]

[0023]

[0024]

[0025]

[0026] Among them, and are binary variables. When indicates that the energy storage battery is charging in the time period, indicates that the energy storage battery is discharging in the time period, indicates the charging power of the energy storage battery in the time period, indicates the maximum charging rate of the energy storage battery, indicates that the energy storage battery is discharging in the time period, indicates the maximum discharge rate of the energy storage battery, indicates the maximum battery capacity of the energy storage battery;

[0027] The vehicle model is specifically expressed as:

[0028]

[0029] Among them, indicates the current SOC of the vehicle, indicates the initial SOC of the vehicle, indicates the charging / discharging power of the vehicle at the time slot . If is positive, indicates the charging power of the vehicle at the time slot . If is negative, indicates the discharging power of the vehicle at the time slot , indicates the length of the time slot, indicates the vehicle battery capacity, indicates the set of available charging time slots; among them, the vehicle model satisfies the following constraints:

[0030]

[0031]

[0032] Among them, represents the maximum rechargeable power of the vehicle, represents the maximum dischargeable power of the vehicle;

[0033] The energy storage air conditioner model is specifically expressed as:

[0034]

[0035] wherein, represents the indoor temperature of the building at time represents the outdoor temperature of the building at time represents the cooling / heating capacity of the energy storage air conditioner at time. If is positive, represents the cooling capacity of the energy storage air conditioner at time. If is negative, represents the heating capacity of the energy storage air conditioner at time; represents the equivalent thermal resistance of the building; represents the equivalent heat capacity of the building, represents the differential. Among them, the cooling / heating capacity of the energy storage air conditioner is related to the power consumption of the energy storage air conditioner and the thermoelectric conversion coefficient of the energy storage air conditioner, that is:

[0036]

[0037] (1) When the set temperature is equal to the indoor temperature , the power consumption of the energy storage air conditioner is:

[0038]

[0039] (2) When the outdoor temperature is less than the set temperature , the cooling time is:

[0040]

[0041] After time, the indoor temperature and the power consumption of the energy storage air conditioner are:

[0042]

[0043]

[0044] (3) When the outdoor temperature is greater than the set temperature the refrigeration time is:

[0045]

[0046] After the moment, the indoor temperature and the power consumption of the energy storage air conditioner are:

[0047]

[0048]

[0049] Wherein, represents the maximum power of the energy storage air conditioner, represents the natural constant, represents the natural logarithm.

[0050] As an improvement to the above solution, based on the simulation model and the reinforcement learning algorithm, a first energy scheduling model of the integrated wind-solar-storage charging and discharging system is constructed, including:

[0051] Convert the energy scheduling problem of the simulation model into a Markov decision problem, and construct the observation space, action space, reward function, policy network and action value network of the first energy scheduling model.

[0052] As an improvement to the above solution, the reward function is:

[0053]

[0054] Wherein, represents the selling electricity price at time represents the selling electricity quantity of the integrated wind-solar-storage charging and discharging system at time represents the buying electricity price at time; represents the buying electricity quantity of the integrated wind-solar-storage charging and discharging system at time; represents the penalty for the SOC not meeting the travel demand when the th vehicle leaves the parking lot at time.

[0055] As an improvement to the above solution, the loss function of the action value network is:

[0056]

[0057]

[0058] Among them, represents the loss function of the action value network of represents calculating the expectation, represents the state distribution and action distribution sampled by the previous agent during environment exploration, represents the target action value network output value of represents the state adopting the action immediate reward of represents the discount rate, represents the state transition probability, represents the state value function of represents state at time represents action at time represents state at time

[0059]

[0060] Among them, is the maximum entropy objective temperature parameter of is the policy network, represents the policy network at the state outputting the action probability of represents state at time represents action at time

[0061] The loss function of the said policy network is:

[0062]

[0063] Among them, represents the loss function of the policy network of represents calculating the expectation, represents the input noise, represents the input noise subject to a normal distribution, represents the resampling of the action of

[0064] The said temperature parameter The loss function is:

[0065]

[0066] in, is the preset minimum expected entropy.

[0067] As an improvement to the above solution, the second energy scheduling model is specifically expressed as follows:

[0068]

[0069] Where, Is an identifier that indicates whether the vehicle has arrived at the parking lot. When the car arrives at the parking lot, =1, when If the car does not arrive at the parking lot, ; Indicates the preset target SOC; Indicates the time when the vehicle leaves the parking lot. Indicates the current moment; Indicates the The maximum charging capacity of the vehicle, Indicates the charging efficiency of the vehicle, Indicates the The maximum charge of the vehicle; Indicates the The SOC after vehicle dispatching, ; Indicates the The current SOC of the vehicle; Indicates the The charging capacity of the vehicle, Indicates the The discharge capacity of the vehicle; represents the discharge efficiency of the vehicle, where the charging and discharging capacities must satisfy the following constraints:

[0070]

[0071]

[0072] Where, is the total charging and discharging quota allocated by the agent to the parking lot.

[0073] To achieve the above objectives, the present application also provides an energy scheduling device for a wind-solar-storage-charging-discharging integrated system, comprising:

[0074] The first construction module is used to construct a simulation model of the integrated wind-solar-storage-charging-discharging system; wherein, the simulation model includes: a photovoltaic power generation model, a wind power generation model, a storage battery model, a vehicle model, and a storage air-conditioning model;

[0075] The second construction module is used to construct a first energy scheduling model of the integrated wind-solar-storage-charging-discharging system based on the reinforcement learning algorithm according to the simulation model;

[0076] The third construction module is used to construct a second energy scheduling model of the vehicle with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling in combination with the moment when the vehicle leaves the parking lot;

[0077] The energy scheduling module is used to jointly train the first energy scheduling model and the second energy scheduling model, so as to perform energy scheduling on the integrated wind-solar-storage-charging-discharging system according to the trained first energy scheduling model and the second energy scheduling model.

[0078] To achieve the above object, an embodiment of the present application further provides an energy scheduling device for an integrated wind-solar-storage-charging-discharging system, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the energy scheduling method of the integrated wind-solar-storage-charging-discharging system as described above.

[0079] To achieve the above object, an embodiment of the present application further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the energy scheduling method of the integrated wind-solar-storage-charging-discharging system as described above.

[0080] To achieve the above object, an embodiment of the present application further provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, they implement the energy scheduling method of the integrated wind-solar-storage-charging-discharging system as described above.

[0081] Compared with the prior art, an energy scheduling method and related devices for a wind-solar-storage-charging-discharging integrated system provided by an embodiment of the present application construct a simulation model of the wind-solar-storage-charging-discharging integrated system by considering photovoltaic power generation, wind power generation, energy storage batteries, vehicles, and energy storage air conditioners. Based on the simulation model and the reinforcement learning algorithm, a first energy scheduling model of the wind-solar-storage-charging-discharging integrated system is constructed. At the same time, in combination with the moment when the vehicle leaves the parking lot, a second energy scheduling model of the vehicle is constructed with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling. Finally, the first energy scheduling model and the second energy scheduling model are jointly trained to perform energy scheduling on the wind-solar-storage-charging-discharging integrated system according to the trained first energy scheduling model and the second energy scheduling model. It can be seen that through the reinforcement learning algorithm, the embodiment of the present application does not need to perform repeated and complex modeling on the wind-solar-storage-charging-discharging integrated system. At the same time, in combination with the second energy scheduling model constructed by the traditional optimization scheme, it can solve the problem of power allocation of electric vehicles, avoid the problem of too large action space caused by a large number of electric vehicles, greatly reduce the computing power required for training, and make the energy scheduling more comprehensive and accurate. By combining the traditional optimization scheme and the artificial intelligence scheme, the novel energy scheduling method proposed in the embodiment of the present invention not only simplifies the modeling process, saves the computing power required for the solution algorithm, but also makes the energy scheduling more comprehensive and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 is a flowchart of an energy scheduling method for a wind-solar-storage-charging-discharging integrated system provided by an embodiment of the present application;

[0083] Figure 2 is a structural block diagram of an energy scheduling device for a wind-solar-storage-charging-discharging integrated system provided by an embodiment of the present application;

[0084] Figure 3 is a structural block diagram of an energy scheduling device for a wind-solar-storage-charging-discharging integrated system provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0085] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0086] See Figure 1 , Figure 1 is a flowchart of an energy scheduling method for a wind-solar-storage-charging-discharging integrated system provided by an embodiment of the present application. The energy scheduling method for the wind-solar-storage-charging-discharging integrated system includes:

[0087] S1. Build a simulation model of the integrated wind-solar-storage-charging-discharging system; wherein, the simulation model includes: a photovoltaic power generation model, a wind power generation model, a storage battery model, a vehicle model, and a storage air-conditioning model;

[0088] S2. Based on the simulation model and the reinforcement learning algorithm, build a first energy scheduling model for the integrated wind-solar-storage-charging-discharging system;

[0089] S3. Combining the time when the vehicle leaves the parking lot, with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling, build a second energy scheduling model for the vehicle;

[0090] S4. Jointly train the first energy scheduling model and the second energy scheduling model, so as to perform energy scheduling on the integrated wind-solar-storage-charging-discharging system according to the trained first energy scheduling model and the second energy scheduling model.

[0091] In the embodiment of the present application, first, model the photovoltaic, wind power, energy storage battery (Energy Storage System, ESS), vehicle (i.e., electric vehicle), and energy storage air-conditioning of the integrated wind-solar-storage-charging-discharging system, especially model the energy storage air-conditioning based on the preset temperature, so as to build a simulation model of the integrated wind-solar-storage-charging-discharging system. For the global energy scheduling of the integrated wind-solar-storage-charging-discharging system, based on the reinforcement learning algorithm, build a first energy scheduling model for the integrated wind-solar-storage-charging-discharging system. For the local energy scheduling of the vehicle, combining the time when the vehicle leaves the parking lot, with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling, build a second energy scheduling model for the vehicle to realize the charge and discharge energy distribution of the electric vehicle.

[0092] Next, jointly train the first energy scheduling model and the second energy scheduling model. Specifically: Incorporate the second energy scheduling model into the environment of the first energy scheduling model for training. Finally, use the trained first energy scheduling model and the second energy scheduling model to perform energy scheduling on the integrated wind-solar-storage-charging-discharging system. That is to say, incorporate the traditional optimization algorithm into the environment of the reinforcement learning for training to form an improved reinforcement learning algorithm, so as to use the improved reinforcement learning algorithm to optimize the global energy scheduling of the integrated wind-solar-storage-charging-discharging system; the traditional optimization algorithm therein is used to optimize the charge and discharge scheduling of the vehicle, and finally obtain the optimal energy scheduling scheme for the integrated wind-solar-storage-charging-discharging system to realize the energy scheduling of the integrated wind-solar-storage-charging-discharging system.

[0093] Wherein, SOC refers to the state of charge of the battery, that is, the remaining power, and its value range is 0 to 1. When SOC = 0, it means that the battery is completely discharged, and when SOC = 1, it means that the battery is completely full.

[0094] Specifically, the photovoltaic power generation model is specifically expressed as:

[0095]

[0096] wherein, represents the power generation power of the photovoltaic panel, represents the solar radiation, represents the reference radiation, represents the rated power of the solar cell array, represents the temperature coefficient, represents the reference temperature, represents the temperature of the solar cell array, , represents the ambient temperature of the photovoltaic panel, represents the rated operating temperature of the solar cell array, represents the air temperature when the solar cell array is operating at rated power, represents the light irradiance on the surface of the solar cell array during rated operation;

[0097] It can be understood that the power generation power of the photovoltaic panel depends on the ambient temperature and solar radiation. In the embodiments of the present application, a photovoltaic power generation model is constructed through the ambient temperature and solar radiation.

[0098] Specifically, the wind power generation model is specifically expressed as:

[0099]

[0100] wherein, represents the output power of the wind turbine generator set, represents the rated power of the wind turbine generator set; represents the wind speed; represents the cut-in wind speed, represents the rated wind speed, represents the cut-out wind speed; wherein , , are respectively:

[0101]

[0102]

[0103]

[0104] It can be understood that the output power of the wind turbine generator set can be determined by its power curve. In the embodiments of the present application, a wind power generation model is constructed through the power curve.

[0105] Specifically, the energy storage battery model is specifically expressed as:

[0106]

[0107] Wherein, represents the electric quantity stored by the energy storage battery at moment, represents the electric quantity stored by the energy storage battery at moment, represents the charging electric quantity of the energy storage battery during the time period of , represents the charging efficiency of the energy storage battery, represents the discharging electric quantity of the energy storage battery during the time period of , represents the discharging efficiency of the energy storage battery; the energy storage battery model satisfies the following constraint conditions:

[0108]

[0109]

[0110]

[0111]

[0112] Wherein, and are binary variables. When represents that the energy storage battery is charging during the time period of , represents that the energy storage battery is discharging during the time period of , represents the charging electric quantity of the energy storage battery during the time period of , represents the maximum charging rate of the energy storage battery, represents the discharging electric quantity of the energy storage battery during the time period of , represents the maximum discharging rate of the energy storage battery, represents the maximum battery capacity of the energy storage battery;

[0113] It can be understood that represents that the energy storage battery does not charge and discharge simultaneously in a time period; represents that the electric quantity that the energy storage battery can charge in each time interval is affected by its maximum charging efficiency; represents that the electric quantity that the energy storage battery can discharge in each time interval is affected by its maximum discharging efficiency; It is indicated that the electric quantity stored in the energy storage battery should not be greater than the maximum battery capacity of the energy storage battery. Considering the service life of the energy storage battery, the energy storage battery should not be over-discharged.

[0114] The vehicle model is specifically expressed as:

[0115]

[0116] Among them, represents the current SOC of the vehicle, represents the initial SOC of the vehicle, represents the charging / discharging power of the vehicle at time slot If is a positive value, represents the charging power of the vehicle at time slot If is a negative value, represents the discharging power of the vehicle at time slot < / represents the length of the time slot, represents the vehicle battery capacity, represents the set of available charging time slots; among them, the vehicle model satisfies the following constraints:

[0117]

[0118]

[0119] Among them, represents the maximum rechargeable power of the vehicle, represents the maximum dischargeable power of the vehicle;

[0120] It can be understood that represents that the charging / discharging power of the vehicle is not greater than its maximum rechargeable / dischargeable power; in addition, to protect the service life of the vehicle battery, the vehicle battery should not be over-discharged, that is .

[0121] Specifically, the energy storage air conditioner model is specifically expressed as:

[0122]

[0123] Among them, represents the indoor temperature of the building at time represents the outdoor temperature of the building at time represents the cooling / heating capacity of the energy storage air conditioner at If is a positive value, represents the cooling capacity of the energy storage air conditioner at The cooling capacity at a certain moment. If is negative, it represents the heating capacity of the energy storage air conditioner at the moment; represents the equivalent thermal resistance of the building; represents the equivalent heat capacity of the building, represents differentiation. Among them, the cooling / heating capacity of the energy storage air conditioner is related to the power consumption of the energy storage air conditioner and the thermoelectric conversion coefficient

[0124]

[0125] (1) When the set temperature is equal to the indoor temperature , the power consumption of the energy storage air conditioner is:

[0126]

[0127] (2) When the outdoor temperature is lower than the set temperature , the cooling time is:

[0128]

[0129] After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are:

[0130]

[0131]

[0132] (3) When the outdoor temperature is higher than the set temperature , the cooling time is:

[0133]

[0134] After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are:

[0135]

[0136]

[0137] Among them, Indicates the maximum power of the energy storage air conditioner, Indicates the natural constant, Indicates the natural logarithm.

[0138] In the embodiments of the present application, an equivalent thermal parameter model is adopted to describe the thermodynamic process of the energy storage air conditioner, so as to construct an energy storage air conditioner model.

[0139] In an alternative embodiment, based on the simulation model and the reinforcement learning algorithm, constructing the first energy scheduling model of the integrated wind-solar-storage-charge-discharge system includes:

[0140] Converting the energy scheduling problem of the simulation model into a Markov decision problem, and constructing the observation space, action space, reward function, policy network and action value network of the first energy scheduling model.

[0141] Specifically, the observation space includes: time (e.g., month, day, hour, minute, second), outdoor temperature, indoor temperature, energy storage air conditioner power, park electricity consumption, wind power generation, photovoltaic power generation, vehicle battery capacity, number of vehicles, number of unmet vehicles (i.e., number of vehicles less than ), unmet capacity (i.e., sum of vehicle battery capacities less than ), number of overflow vehicles (i.e., number of vehicles greater than ), overflow capacity (i.e., sum of vehicle battery capacities greater than ), electricity price.

[0142] The action space includes: charging and discharging of energy storage batteries, charging and discharging amount of vehicles (i.e., total charging and discharging quota of the parking lot), and set temperature of the energy storage air conditioner.

[0143] The goal of the embodiments of the present application is to minimize the electricity cost of the integrated wind-solar-storage-charge-discharge system (park) and maximize the benefits. Therefore, only the electricity cost, electricity selling revenue of the integrated wind-solar-storage-charge-discharge and the compensation of the parking lot are concerned. Specifically, the reward function is:

[0144]

[0145] Wherein, Indicates The electricity selling price at time Indicates The electricity selling amount of the integrated wind-solar-storage-charge-discharge system at time Indicates The electricity buying price at time Indicates The electricity buying amount of the integrated wind-solar-storage-charge-discharge system at time Indicates At time Penalty for the SOC of a vehicle not meeting the travel demand when leaving the parking lot.

[0146] To meet the user's demand, it is necessary to ensure that the SOC of each vehicle (electric vehicle) when leaving the parking lot is greater than the preset target SOC, i.e., , Preferably 0.8. Calculate the mileage compensation of the th vehicle at the moment through the difference between the preset target SOC and the SOC of the vehicle when leaving the parking lot. The formula is as follows:

[0147]

[0148] Where, represents the SOC of the vehicle when leaving the parking lot, represents the preset target SOC, is the number of kilometers the vehicle can travel per degree of electricity; is the battery capacity of the vehicle. is the th vehicle's departure time.

[0149] According to the mileage compensation Combined with the taxi fare charging method in a certain city, calculate the compensation amount for the user's insufficient power as a penalty. The taxi charging method is a segmented charging method, which is calculated by combining the driving time and driving mileage. For the convenience of calculation, this application converts the driving time into distance according to the average driving speed in a certain city and calculates them uniformly. The charging formula is as follows:

[0150]

[0151] Where, is the th vehicle's penalty for the SOC not meeting the travel demand when leaving the parking lot at the moment, is the th vehicle's mileage compensation at the moment, is the starting price, is the mileage price, is the time price, is the first long-distance fee, is the second long-distance fee, is the third long-distance fee; is the mileage starting distance, is the time starting distance, is the first long-distance distance, is the second long-distance distance, is the third long-distance distance; The conversion factor representing time and distance can be preset or calculated based on the average speed of vehicle travel in a certain city.

[0152] According to this formula, the penalty for the SOC not meeting the travel demand when the vehicle leaves the parking lot can be calculated.

[0153] In the embodiment of this application, by training a policy network (whose parameters are ) and two action-value networks (whose parameters are respectively and , uniformly represented by ), the training of the energy scheduling model is completed.

[0154] Specifically, the loss function of the action-value network is:

[0155]

[0156]

[0157] Among them, represents the loss function of the action-value network , represents calculating the expectation, represents the state distribution and action distribution sampled by the previous agent in environment exploration, represents the value output by the target action-value network , represents the state adopting the immediate reward of the action , represents the discount rate, represents the state transition probability, represents the state value function: represents the state at time; represents the action at time, represents the state at time.

[0158] This value function can be estimated by the target action-value network . Each network corresponds to a network. Specifically, ; among them, is the temperature parameter of the maximum entropy target , is the policy network, represents the policy network outputting the action in the state ​ The probability; Indicates The state at time Indicates The action at time. Finally, the policy network is learned by minimizing the expected KL divergence.

[0159] Specifically, the loss function of the policy network is:

[0160]

[0161] Where Indicates the policy network The loss function of Indicates calculating the expectation, Indicates the input noise, Indicates the input noise Follows a normal distribution, Indicates resampling the action Of

[0162] Specifically, the loss function of the temperature parameter Is:

[0163]

[0164] Where Indicates the preset minimum expected entropy.

[0165] In an alternative embodiment, the second energy scheduling model is specifically expressed as:

[0166]

[0167] In the formula, Is an identifier indicating whether the vehicle has arrived at the parking lot. When the th vehicle arrives at the parking lot, = 1. When the th vehicle has not arrived at the parking lot, ; Indicates the preset target SOC; Indicates the moment when the vehicle leaves the parking lot, Indicates the current moment; Indicates the th vehicle's maximum charging power, Indicates the vehicle's charging efficiency, Indicates the th vehicle's maximum power; Indicates the th vehicle's SOC after scheduling, ; Indicates the the current SOC of a vehicle; indicating the charging power of the indicating the discharging power of the indicating the discharging efficiency of the vehicle, where the charging power and the discharging power need to satisfy the following constraints:

[0168]

[0169]

[0170] In the formula, is the total charging and discharging quota allocated by the agent to the parking lot.

[0171] In the embodiments of the present application, the agent trained by reinforcement learning decides the total charging and discharging quota of the parking lot, and intelligently schedules various energy storages (energy storage batteries, vehicles, energy storage air conditioners) to store the energy generated by photovoltaic and wind power. Then, according to the second energy scheduling model of the vehicle, the total charging and discharging quota is subdivided into each vehicle, so that the SOC of all vehicles when leaving the parking lot meets to further realize the optimization of the energy scheduling of the vehicle.

[0172] In the embodiments of the present application, through the reinforcement learning algorithm, there is no need to repeatedly and complexly model the integrated wind-solar-storage-charging-discharging system. At the same time, combined with the second energy scheduling model constructed by the traditional optimization scheme, it can solve the problem of the power distribution of electric vehicles, avoid the problem of too large action space caused by a large number of electric vehicles, greatly reduce the computing power required for training, and make the energy scheduling more comprehensive and accurate. Through the combination of the traditional optimization scheme and the artificial intelligence scheme, the novel energy scheduling method proposed in the embodiments of the present invention not only simplifies the modeling process, saves the computing power required by the solution algorithm, but also makes the energy scheduling more comprehensive and accurate.

[0173] See Figure 2 , Figure 2 is the structural block diagram of an energy scheduling device 10 of an integrated wind-solar-storage-charging-discharging system provided by the embodiments of the present application. The energy scheduling device 10 of the integrated wind-solar-storage-charging-discharging system includes:

[0174] The first construction module 11 is used to construct a simulation model of the integrated wind-solar-storage-charging-discharging system; wherein, the simulation model includes: a photovoltaic power generation model, a wind power generation model, an energy storage battery model, a vehicle model, and an energy storage air conditioner model;

[0175] The second construction module 12 is used to construct the first energy scheduling model of the integrated wind-solar-storage-charging-discharging system based on the reinforcement learning algorithm according to the simulation model;

[0176] The third construction module 13 is used to construct a second energy scheduling model of the vehicle with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling when the vehicle leaves the parking lot;

[0177] The energy scheduling module is used to jointly train the first energy scheduling model and the second energy scheduling model, so as to perform energy scheduling on the wind-solar-storage-charge-discharge integrated system according to the trained first energy scheduling model and the second energy scheduling model.

[0178] Optionally, the photovoltaic power generation model is specifically expressed as:

[0179]

[0180] Where, represents the power generation power of the photovoltaic panel, represents the solar radiation, represents the reference radiation, represents the rated power of the solar cell array, represents the temperature coefficient, represents the reference temperature, represents the temperature of the solar cell array, , represents the ambient temperature of the photovoltaic panel, represents the rated operating temperature of the solar cell array, represents the air temperature when the solar cell array operates at rated power, represents the illumination irradiance on the surface of the solar cell array when operating at rated power;

[0181] The wind power generation model is specifically expressed as:

[0182]

[0183] Where, represents the output power of the wind turbine generator, represents the rated power of the wind turbine generator; represents the wind speed; represents the cut-in wind speed, represents the rated wind speed, represents the cut-out wind speed; where , , are respectively:

[0184]

[0185]

[0186]

[0187] The energy storage battery model is specifically expressed as:

[0188]

[0189] Wherein, represents the electric quantity stored in the energy storage battery at moment, represents the electric quantity stored in the energy storage battery at moment, represents the charging electric quantity of the energy storage battery in the time period , represents the charging efficiency of the energy storage battery, represents the discharging electric quantity of the energy storage battery in the time period , represents the discharging efficiency of the energy storage battery; The energy storage battery model satisfies the following constraint conditions:

[0190]

[0191]

[0192]

[0193]

[0194] Wherein, and are binary variables. When represents that the energy storage battery is charging in the time period , represents that the energy storage battery is discharging in the time period , represents the charging electric quantity of the energy storage battery in the time period , represents the maximum charging rate of the energy storage battery, represents the discharging electric quantity of the energy storage battery in the time period , represents the maximum discharging rate of the energy storage battery, represents the maximum battery capacity of the energy storage battery;

[0195] The vehicle model is specifically expressed as:

[0196]

[0197] Wherein, represents the current SOC of the vehicle, represents the initial SOC of the vehicle, represents the charging / discharging power of the vehicle at the time slot If is a positive value, indicating the charging power of the vehicle at time slot . If is a negative value, it indicates the discharging power of the vehicle at time slot . represents the length of the time slot, represents the capacity of the vehicle battery, represents the set of available charging time slots; among them, the vehicle model satisfies the following constraints:

[0198]

[0199]

[0200] Among them, represents the maximum chargeable power of the vehicle, represents the maximum dischargeable power of the vehicle;

[0201] The energy storage air conditioner model is specifically expressed as:

[0202]

[0203] Among them, represents the indoor temperature of the building at time represents the outdoor temperature of the building at time represents the cooling / heating capacity of the energy storage air conditioner at time. If is a positive value, it represents the cooling capacity of the energy storage air conditioner at time. If is a negative value, it represents the heating capacity of the energy storage air conditioner at time; represents the equivalent thermal resistance of the building; represents the equivalent heat capacity of the building, represents the differential. Among them, the cooling / heating capacity of the energy storage air conditioner is related to the power consumption of the energy storage air conditioner and the thermoelectric conversion coefficient of the energy storage air conditioner, that is:

[0204]

[0205] (1) When the set temperature is equal to the indoor temperature , the power consumption of the energy storage air conditioner is:

[0206]

[0207] (2) When the outdoor temperature is less than the set temperature at that time, the refrigeration time is:

[0208]

[0209] After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are:

[0210]

[0211]

[0212] (3) When the outdoor temperature is greater than the set temperature at that time, the refrigeration time is:

[0213]

[0214] After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are:

[0215]

[0216]

[0217] Among them, represents the maximum power of the energy storage air conditioner, represents the natural constant, represents the natural logarithm.

[0218] Optionally, based on the simulation model and the reinforcement learning algorithm, the first energy scheduling model of the integrated wind-solar-storage charging and discharging system is constructed, including:

[0219] Convert the energy scheduling problem of the simulation model into a Markov decision problem, and construct the observation space, action space, reward function, policy network and action value network of the first energy scheduling model.

[0220] Optionally, the reward function is:

[0221]

[0222] Among them, represents the selling electricity price at time represents the electricity selling quantity of the integrated wind-solar-storage-charging-discharging system at time represents the electricity buying price at time represents the electricity buying quantity of the integrated wind-solar-storage-charging-discharging system at time represents at time the penalty for the SOC of the

[0223] Optionally, the loss function of the action value network is:

[0224]

[0225]

[0226] where represents the loss function of the action value network represents calculating the expectation represents the state distribution and action distribution sampled by the previous agent during environment exploration represents the target action value network the value output represents the state adopting the action the immediate reward represents the discount rate represents the state transition probability represents the state value function: represents the state at time represents the action at time represents the state at time

[0227]

[0228] where is the temperature parameter of the maximum entropy objective is the policy network represents the policy network at the state outputting the action probability represents the state at time represents the action at time ​​

[0229] The loss function of the policy network is as follows:

[0230]

[0231] where, represents the loss function of the policy network , represents the calculation of expectation, represents the input noise, represents the input noise obeys the normal distribution, represents the resampling of the action ;

[0232] The loss function of the temperature parameter is as follows:

[0233]

[0234] where, represents the preset minimum expected entropy.

[0235] Optionally, the second energy scheduling model is specifically expressed as:

[0236]

[0237] In the formula, is an identifier indicating whether the vehicle has arrived at the parking lot. When the th vehicle arrives at the parking lot, = 1; when the th vehicle has not arrived at the parking lot, ; represents the preset target SOC; represents the moment when the vehicle leaves the parking lot, represents the current moment; represents the th vehicle's maximum charging power, represents the vehicle's charging efficiency, represents the th vehicle's maximum power; represents the SOC of the th vehicle after scheduling, ; represents the current SOC of the th vehicle; represents the charging power of the th vehicle, represents the discharging power of the th vehicle; represents the vehicle's discharging efficiency, where the charging power and discharging power need to satisfy the following constraints:

[0238]

[0239]

[0240] In the formula, is the total charge-discharge quota allocated by the agent to the parking lot.

[0241] It should be noted that the working processes of the various modules in the energy scheduling device 10 of the integrated wind-solar-storage-charge-discharge system described in the embodiments of the present application can refer to the working process of the energy scheduling method of the integrated wind-solar-storage-charge-discharge system described in the above embodiments, and will not be elaborated here.

[0242] The energy scheduling device 10 of the integrated wind-solar-storage-charge-discharge system provided by the embodiments of the present application constructs a simulation model of the integrated wind-solar-storage-charge-discharge system by considering photovoltaic power generation, wind power generation, energy storage batteries, vehicles, and energy storage air conditioners. Based on the simulation model and the reinforcement learning algorithm, a first energy scheduling model of the integrated wind-solar-storage-charge-discharge system is constructed. At the same time, in combination with the moment when the vehicle leaves the parking lot, with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling, a second energy scheduling model of the vehicle is constructed; finally, the first energy scheduling model and the second energy scheduling model are jointly trained to perform energy scheduling on the integrated wind-solar-storage-charge-discharge system according to the trained first energy scheduling model and the second energy scheduling model. It can be seen that through the reinforcement learning algorithm, the embodiments of the present application do not need to perform repeated and complex modeling on the integrated wind-solar-storage-charge-discharge system. At the same time, combined with the second energy scheduling model constructed by the traditional optimization scheme, it can solve the problem of power allocation of electric vehicles, avoid the problem of too large action space caused by a large number of electric vehicles, greatly reduce the computing power required for training, and make the energy scheduling more comprehensive and accurate. The embodiments of the present invention propose a new energy scheduling method by combining the traditional optimization scheme and the artificial intelligence scheme, which not only simplifies the modeling process, saves the computing power required by the solution algorithm, but also makes the energy scheduling more comprehensive and accurate.

[0243] In addition, the embodiments of the present application also provide a computer-readable storage medium, and the computer-readable storage medium includes a stored computer program; wherein, the computer program controls the device where the computer-readable storage medium is located to execute the energy scheduling method of the integrated wind-solar-storage-charge-discharge system as described in any one of the above embodiments when running.

[0244] In addition, the embodiments of the present application also provide a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, they implement the energy scheduling method of the integrated wind-solar-storage-charge-discharge system as described in any one of the above embodiments.

[0245] See Figure 3 , Figure 3 is a structural block diagram of an energy scheduling device 20 of an integrated wind-solar-storage-charging-discharging system provided in an embodiment of the present application. The energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the embodiment of the energy scheduling method of the above integrated wind-solar-storage-charging-discharging system are implemented. Alternatively, when the processor 21 executes the computer program, the functions of each module / unit in the above device embodiments are implemented.

[0246] Exemplarily, the computer program may be divided into one or more modules / units. The one or more modules / units are stored in the memory 22 and executed by the processor 21 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system.

[0247] The energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art can understand that the schematic diagram is only an example of the energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system, and does not constitute a limitation on the energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system may further include input / output devices, network access devices, buses, etc.

[0248] The processor 21 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The processor 21 is the control center of the energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system, and connects various parts of the entire energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system through various interfaces and lines.

[0249] The memory 22 can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory 22, and invoking the data stored in the memory 22, the processor 21 realizes various functions of the energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system. The memory 22 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0250] Among them, if the modules / units integrated in the energy scheduling device 20 of the integrated wind-solar-storage-charging-discharging system are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 21, the steps of the above-mentioned various method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0251] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0252] The above is the preferred embodiment of this application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements are also regarded as the protection scope of this application.

Claims

1. An energy scheduling method for an integrated system of wind power, photovoltaics, energy storage, charging and discharging, characterized in that, Including: Constructing a simulation model of an integrated wind-solar-storage-charging-discharging system; wherein, the simulation model includes: a photovoltaic power generation model, a wind power generation model, a storage battery model, a vehicle model, and a storage air-conditioning model; Based on the simulation model and the reinforcement learning algorithm, constructing a first energy scheduling model of the integrated wind-solar-storage-charging-discharging system; Combined with the moment when the vehicle leaves the parking lot, with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling, constructing a second energy scheduling model for the vehicle; Jointly training the first energy scheduling model and the second energy scheduling model, so as to perform energy scheduling on the integrated wind-solar-storage-charging-discharging system according to the trained first energy scheduling model and the second energy scheduling model; Wherein, the storage air-conditioning model is specifically expressed as: Among them, represents the indoor temperature of the building at time represents the outdoor temperature of the building at time represents the cooling / heating capacity of the energy storage air conditioner at time. If is positive, it represents the cooling capacity of the energy storage air conditioner at time. If is negative, it represents the heating capacity of the energy storage air conditioner at time; represents the equivalent thermal resistance of the building; represents the equivalent heat capacity of the building, represents differentiation. Among them, the cooling / heating capacity of the energy storage air conditioner is related to the power consumption of the energy storage air conditioner and the thermoelectric conversion coefficient, that is: (1)When the set temperature is equal to the indoor temperature the power consumption of the energy storage air conditioner is as follows: (2) When the outdoor temperature is less than the set temperature the refrigeration time After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are as follows: (3) When the outdoor temperature is greater than the set temperature , the refrigeration time After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are as follows: Among them, represents the maximum power of the energy storage air conditioner, represents the natural constant, represents the natural logarithm; The second energy scheduling model is specifically expressed as: In the formula, is an identifier indicating whether the vehicle has arrived at the parking lot. When the th vehicle arrives at the parking lot, = 1; when the th vehicle has not arrived at the parking lot, ; represents the preset target SOC; represents the moment when the vehicle leaves the parking lot, represents the current moment; represents the maximum charging power of the th vehicle, represents the charging efficiency of the vehicle, represents the th vehicle's maximum power; represents the SOC of the th vehicle after scheduling, ; represents the current SOC of the th vehicle; represents the charging power of the th vehicle, represents the th vehicle's discharging power; represents the discharging efficiency of the vehicle, where the charging power and discharging power need to satisfy the following constraints: In the formula, is the total charge-discharge quota assigned by the agent to the parking lot.

2. The energy scheduling method of the integrated wind-solar-storage-charging-discharging system according to claim 1, wherein the photovoltaic power generation model is specifically expressed as: Among them, represents the power generation of the photovoltaic power generation panel, represents the solar radiation, represents the reference radiation, represents the rated power of the solar cell array, represents the temperature coefficient, represents the reference temperature, represents the temperature of the solar cell array, , represents the ambient temperature of the photovoltaic power generation panel, represents the rated operating temperature of the solar cell array, represents the air temperature when the solar cell array operates at rated power, represents the light irradiance on the surface of the solar cell array during rated operation; The wind power generation model is specifically expressed as: Among them, represents the output power of the wind turbine generator; represents the rated power of the wind turbine generator; represents the wind speed; represents the cut-in wind speed, represents the rated wind speed, represents the cut-out wind speed; among them , , are respectively: The storage battery model is specifically expressed as: Among them, represents the stored electricity of the energy storage battery at moment, represents the stored electricity of the energy storage battery at moment, represents the charging electricity of the energy storage battery during the period, represents the charging efficiency of the energy storage battery, represents the discharging electricity of the energy storage battery during the period, represents the discharging efficiency of the energy storage battery; the energy storage battery model satisfies the following constraint conditions: Among them, and are binary variables. When indicates that the energy storage battery is charged during the time period, indicates that the energy storage battery is discharged during the time period, indicates the charging power of the energy storage battery during the time period, indicates the maximum charging rate of the energy storage battery, indicates that the energy storage battery is discharged during the time period, indicates the maximum discharge rate of the energy storage battery, indicates the maximum battery capacity of the energy storage battery; The vehicle model is specifically expressed as: wherein, represents the current SOC of the vehicle, represents the initial SOC of the vehicle, represents the charging / discharging power of the vehicle at time slot ; if is positive, it represents the charging power of the vehicle at time slot ; if is negative, it represents the discharging power of the vehicle at time slot . represents the length of the time slot, represents the capacity of the vehicle battery, represents the set of available charging time slots; wherein, the vehicle model satisfies the following constraints: Among them, represents the maximum rechargeable power of the vehicle, represents the maximum dischargeable power of the vehicle.

3. The energy scheduling method of the integrated wind-solar-storage-charging-discharging system according to claim 1, characterized in that The constructing the first energy scheduling model of the integrated wind-solar-storage-charging-discharging system based on the simulation model and the reinforcement learning algorithm includes: Converting the energy scheduling problem of the simulation model into a Markov decision problem, and constructing the observation space, action space, reward function, policy network, and action value network of the first energy scheduling model.

4. The energy scheduling method of the integrated wind-solar-storage-charging-discharging system according to claim 3, characterized in that, The reward function is: Among them, represents the selling electricity price at time represents the selling electricity quantity of the wind-solar-storage-charging / discharging integrated system at time represents the buying electricity price at time represents the buying electricity quantity of the wind-solar-storage-charging / discharging integrated system at time represents the penalty for the SOC of the th vehicle not meeting the travel demand when leaving the parking lot at time 5. The energy scheduling method of the integrated wind-solar-storage-charging-discharging system according to claim 4, characterized in that, The loss function of the action value network is: Among them, represents the loss function of the action value network, represents calculating the expectation, represents the state distribution and action distribution sampled by the previous agent during environment exploration, represents the target action value network output value, represents the state adopts the action immediate reward, represents the discount rate, represents the state transition probability, represents the state value function: represents the state at time; represents the action at time, represents the state at time; Among them, is the maximum entropy objective temperature parameter, is the policy network, represents the policy network outputs the action at the state with probability; represents the state at time represents the action at time; The loss function of the policy network is: Among them, represents the loss function of the policy network , represents the calculation of expectation represents the input noise represents the input noise obeys the normal distribution represents the resampling of the action . The temperature parameter has a loss function of: Among them, represents the preset minimum expected entropy.

6. An energy scheduling device for a wind-solar-storage-charging-discharging integrated system, characterized in that, Including: A first construction module for constructing a simulation model of an integrated wind-solar-storage-charging-discharging system; wherein, the simulation model includes: a photovoltaic power generation model, a wind power generation model, a storage battery model, a vehicle model, and a storage air-conditioning model; A second construction module for constructing a first energy scheduling model of the integrated wind-solar-storage-charging-discharging system based on the simulation model and the reinforcement learning algorithm; A third construction module for constructing a second energy scheduling model for the vehicle in combination with the moment when the vehicle leaves the parking lot, with the goal of minimizing the difference between the preset target SOC and the SOC after vehicle scheduling; An energy scheduling module for jointly training the first energy scheduling model and the second energy scheduling model, so as to perform energy scheduling on the integrated wind-solar-storage-charging-discharging system according to the trained first energy scheduling model and the second energy scheduling model; Wherein, the storage air-conditioning model is specifically expressed as: Among them, represents the indoor temperature of the building at time represents the outdoor temperature of the building at time represents the cooling / heating capacity of the energy storage air conditioner at time. If is positive, it represents the cooling capacity of the energy storage air conditioner at time. If is negative, it represents the heating capacity of the energy storage air conditioner at time; represents the equivalent thermal resistance of the building; represents the equivalent heat capacity of the building, represents differentiation. Among them, the cooling / heating capacity of the energy storage air conditioner is related to the power consumption of the energy storage air conditioner and the thermoelectric conversion coefficient of the energy storage air conditioner, that is: (1)When the set temperature is equal to the indoor temperature , the power consumption of the energy storage air conditioner is as follows: (2)When the outdoor temperature is less than the set temperature the refrigeration time is as follows: After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are as follows: (3) When the outdoor temperature is greater than the set temperature the refrigeration time is: After a certain moment, the indoor temperature and the power consumption of the energy storage air conditioner are as follows: Among them, represents the maximum power of the energy storage air conditioner, represents the natural constant, represents the natural logarithm; The second energy scheduling model is specifically expressed as: Wherein, is an identifier indicating whether the vehicle has arrived at the parking lot. When the th vehicle arrives at the parking lot, = 1. When the th vehicle has not arrived at the parking lot, ; represents the preset target SOC; represents the moment when the vehicle leaves the parking lot, represents the current moment; represents the maximum charging power of the th vehicle, represents the charging efficiency of the vehicle, represents the th vehicle's maximum power; represents the SOC of the th vehicle after scheduling, ; represents the current SOC of the th vehicle; represents the charging power of the th vehicle, represents the discharging power of the th vehicle; represents the discharging efficiency of the vehicle. The charging power and discharging power need to satisfy the following constraints: In the formula, is the total charge-discharge quota allocated by the agent to the parking lot.

7. An energy scheduling device for a wind-solar-storage-charging-discharging integrated system, characterized in that, Including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the energy scheduling method of the integrated wind-solar-storage-charging-discharging system according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program; wherein, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the energy scheduling method of the integrated wind-solar-storage-charging-discharging system according to any one of claims 1 to 5.

9. A computer program product, characterized in that, Comprising a computer program / instructions, which when executed by a processor implement the energy scheduling method of the integrated wind-solar-storage-charging-discharging system according to any one of claims 1 to 5.

Images