Light storage and filling integrated cabin

Abstract

The invention discloses a light storage and charging integrated cabin which comprises a light storage and charging integrated cabin body, a photovoltaic subsystem is laid on the top of the light storage and charging integrated cabin body, and a lithium battery energy storage subsystem, an alternating current power distribution cabinet, an energy management system and a temperature control fire are arranged in the light storage and charging integrated cabin body. The photovoltaic subsystem component is used for absorbing and utilizing solar energy to carry out photoelectric conversion; the lithium battery energy storage subsystem is used for electric energy generated by the lithium battery energy storage subsystem and electric energy obtained from a power grid; the alternating-current power distribution cabinet serves as a center for power distribution and control and is used for distributing the power in the lithium battery energy storage subsystem to various types of electric equipment; the energy management system belongs to a master control center and is used for controlling the photovoltaic subsystem, the energy storage subsystem, the power distribution cabinet and the charging pile to work cooperatively and establishing an objective function for operation optimization of the photovoltaic storage and charging integrated cabin according to predicted photovoltaic output and corresponding electric vehicle charging data. And continuous energy configuration optimization in the operation process of the light storage and charging integrated cabin is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to a photovoltaic storage and charging integrated cabin. Background Art

[0002] The "photovoltaic storage and charging integrated cabin" is an innovative energy solution that organically combines photovoltaic power generation, energy storage systems and electric vehicle charging facilities to form a comprehensive energy system.

[0003] The electricity generated by the photovoltaic power generation system is first supplied to the electric vehicle charging facilities. If there is excess electricity, it is stored in the energy storage device. During peak electricity consumption, the energy storage device can release the stored electricity to supply the electric vehicle charging facilities or other electrical equipment. In this way, the photovoltaic storage and charging integrated cabin can not only reduce the pressure on the power grid during peak electricity consumption, but also store electricity during low electricity consumption, realizing peak shaving and valley filling, and improving energy utilization efficiency.

[0004] The photovoltaic storage and charging integrated cabin is suitable for new energy vehicle charging and swapping stations, highway service areas, parking lots, industrial parks and other scenarios. It can not only improve the utilization rate of buildings, but also effectively solve the intermittent, unstable and consumption problems of new energy power generation, making the charging of new energy vehicles more economical and environmentally friendly. At the same time, the surplus power grid can also increase economic benefits, which is conducive to the formation of an efficient energy utilization model and provide support for energy transformation.

[0005] The efficient operation of the photovoltaic, storage and charging integrated cabin needs to take into account multiple factors such as light resources, power demand, traffic conditions, etc. Therefore, an optimization method is needed to improve the operating efficiency of the photovoltaic, storage and charging integrated cabin. Summary of the invention

[0006] The purpose of the present invention is to provide a photovoltaic, storage and charging integrated cabin, and optimize the operation of the photovoltaic, storage and charging integrated cabin by considering multiple factors such as lighting resources, power demand, and traffic conditions.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] A photovoltaic storage and charging integrated cabin, comprising: a photovoltaic storage and charging integrated cabin body, a photovoltaic subsystem laid on the top of the photovoltaic storage and charging integrated cabin body, a lithium battery energy storage subsystem arranged inside the photovoltaic storage and charging integrated cabin body, an AC power distribution cabinet, an energy management system and temperature control fire protection;

[0009] The photovoltaic subsystem includes a number of photovoltaic modules and an intelligent tracking system. The photovoltaic modules are used to absorb and utilize solar energy for photoelectric conversion. The intelligent tracking system is used to automatically adjust the angle of the photovoltaic panel according to the angle of sunlight.

[0010] The lithium battery energy storage subsystem is used for the electric energy generated by the lithium battery energy storage subsystem and the electric energy obtained from the power grid;

[0011] The AC power distribution cabinet serves as the center of power distribution and control, and is used to distribute the power in the lithium battery energy storage subsystem to various types of power-consuming equipment;

[0012] The energy management system belongs to the general control center, which is used to control the photovoltaic subsystem, energy storage subsystem, power distribution cabinet and charging pile to work together, and optimize the operation of the photovoltaic storage and charging integrated cabin to maximize energy utilization and minimize costs;

[0013] The temperature control fire fighting system includes a temperature sensor, a smoke detector, and an automatic sprinkler fire extinguishing device, which are used to monitor and warn the temperature in the cabin in real time. Once an abnormal temperature is predicted, the automatic sprinkler fire extinguishing device will be activated to extinguish the fire.

[0014] The energy storage system plays an important role in regulating the supply and demand of electricity and ensuring the stability of the power grid in the photovoltaic storage and charging integrated cabin. By optimizing the configuration and operation strategy of the energy storage system, such as determining the optimal energy storage power and storage duration, it can ensure that electricity is stored when there is surplus electricity and released when there is a shortage of electricity, thereby achieving efficient use of energy. At the same time, the photovoltaic storage and charging integrated cabin can charge electric vehicles during periods when electricity prices are low or photovoltaic power generation is abundant, reducing charging costs. At the same time, the energy storage system can also store electricity during the valley period when electricity prices are low, and release electricity during the peak period when electricity prices are high, realizing peak-valley electricity price arbitrage and reducing operating costs.

[0015] According to the above technical solution, the steps of optimizing the operation of the photovoltaic storage and charging integrated cabin by the energy management system include:

[0016] Obtain the predicted weather conditions and vehicle flow in the photovoltaic storage and charging integrated cabin area, and use the photovoltaic output prediction model to predict photovoltaic output by obtaining the predicted weather conditions. Use the vehicle charging prediction model to predict the electric vehicle charging data in the photovoltaic storage and charging integrated cabin area based on the vehicle flow corresponding to the predicted weather conditions.

[0017] Determine the constraints for the operation of the photovoltaic storage and charging integrated cabin;

[0018] The objective function for optimizing the operation of the photovoltaic storage and charging integrated cabin is established based on the predicted photovoltaic output and the corresponding electric vehicle charging data;

[0019] Based on the constraints of the operation of the photovoltaic, storage and charging integrated cabin, the objective function of optimizing the operation of the photovoltaic, storage and charging integrated cabin is optimized using the master-slave game model.

[0020] Photovoltaic output refers to the amount of electrical energy that a photovoltaic system can generate within a certain period of time.

[0021] According to the above technical solution, the photovoltaic output prediction model construction step includes:

[0022] Obtain historical photovoltaic output data and its corresponding weather conditions;

[0023] The acquired photovoltaic output historical data is divided into multiple sub-data sets, and the data within each sub-data set is clustered to obtain local clustering results;

[0024] At least one sub-sample is extracted from the data corresponding to the local clustering result of each sub-data set to form a secondary sample set; the sub-sample is used to represent the corresponding clustering result in the sub-data set;

[0025] According to the “elbow method”, the cluster number k of the photovoltaic output data in the secondary sample set is determined, and K cluster centers are generated;

[0026] Calculate the distance from each point in the secondary sample set to the k cluster centers, take the cluster with the smallest distance to the cluster center as the cluster to which the point belongs, and recalculate a new cluster center for each cluster until the sum of the distances from all data points to the cluster center is minimized. The result is taken as the clustering result of the secondary sample set.

[0027] The clustering result corresponding to each sub-sample in the secondary sample set is transferred to the local clustering result corresponding to the sub-sample, and the mode of the clustering result of the secondary sample set corresponding to the local clustering result is counted, and the clustering result of the secondary sample set corresponding to the mode is used as the final result of the local clustering, thereby determining the clustering result of the photovoltaic output historical data;

[0028] Calculate the average value corresponding to each cluster of photovoltaic output historical data, and divide the average value corresponding to each cluster of photovoltaic output historical data and its corresponding weather conditions into a training set and a validation set;

[0029] Based on the training set and the validation set, the photovoltaic output prediction model is trained using a neural network model;

[0030] The photovoltaic output is predicted by obtaining the predicted weather conditions and using the photovoltaic output prediction model.

[0031] The size of photovoltaic output depends on the intensity of sunlight. The photovoltaic output in different weather conditions is very different. The weather conditions of a day are more complex, and it is difficult to distinguish the photovoltaic output level directly based on the weather. In addition, there is a lot of historical data for photovoltaic output processing. In order to improve the processing speed, the photovoltaic output is clustered and analyzed.

[0032] According to the above technical solution, the formula for recalculating the new cluster center for each cluster is:

[0033]

[0034] Where D i is the cluster center of the ith cluster after update, C i is the cluster center of the ith cluster, and x is the point in the ith cluster.

[0035] According to the above technical solution, the steps of constructing the electric vehicle charging prediction model include:

[0036] Obtain historical electric vehicle charging data in the solar-storage-charging integrated cabin area and its corresponding weather condition data and traffic flow data;

[0037] The historical electric vehicle charging data is extracted and characterized by a hybrid autoregressive expert with one-dimensional causal convolution;

[0038] The acquired historical tram charging data is characterized by seasonality using a learnable Fourier layer;

[0039] Inputting the trend representation and the seasonal representation into the fully connected layer to obtain new electric vehicle charging data;

[0040] Based on the new electric vehicle charging data and its corresponding weather condition data and traffic flow data, a electric vehicle charging prediction model is obtained by using neural network training.

[0041] The charging speed of trams will also change with the seasons. Therefore, we explore the seasonal characteristics of tram charging data and the trend characteristics that change over time, and make tram charging data forecasts. Tram charging data includes tram charging power, tram charging capacity, etc.

[0042] According to the above technical solution, the constraints for the operation of the photovoltaic storage and charging integrated cabin include:

[0043]

[0044] SOC min ≤SOC t ≤SOC max ;

[0045]

[0046] Where P Bc,t represents the charging power of the solar-storage-charging integrated cabin during period t, P Bd,t It represents the discharge power of the energy storage in the photovoltaic storage and charging integrated cabin during period t, Indicates the maximum charging power of the photovoltaic storage and charging integrated cabin energy storage, Indicates the maximum discharge power of the photovoltaic storage and charging integrated cabin energy storage, Indicates the charging status. Indicates the state of placing a point, E max Indicates the rated capacity of the photovoltaic storage and charging integrated cabin energy storage, SOC max Indicates the maximum state of charge of the photovoltaic storage and charging integrated cabin energy storage, SOC min Indicates the minimum state of charge of the photovoltaic storage and charging integrated cabin, SOC tIndicates the state of charge of the photovoltaic storage and charging integrated cabin at the end of time period t, SOC t-1 represents the charge state of the integrated photovoltaic storage and charging cabin at the end of the storage period t-1, η c represents the charging efficiency of the photovoltaic storage and charging integrated cabin energy storage, η d It represents the discharge efficiency of the energy storage in the integrated photovoltaic storage and charging cabin, and Δt represents the time period.

[0047] According to the above technical solution, the master-slave game model is expressed as G={(O∪Z∪M); L; R};

[0048] Among them, G represents the master-slave game model, O is the leader representing the power grid system, Z is the secondary leader representing the photovoltaic storage and charging integrated cabin, M is the follower representing the electric vehicle system, L represents the strategy set, L={L O ,L Z ,L M}, L O It represents the price quoted by the power grid for purchasing electricity from the photovoltaic storage and charging integrated cabin and the price quoted for selling electricity to the photovoltaic storage and charging integrated cabin. Z The strategy is the electricity sales and purchase strategy of the photovoltaic storage and charging integrated cabin to the electric vehicle, L M It indicates the electricity purchasing strategy of the electric vehicle system towards the integrated photovoltaic storage and charging cabin;

[0049] R represents the revenue set, R O is the objective function of leader O, R Z is the objective function of the secondary leader Z, R M is the objective function of the follower. The objective function of the photovoltaic storage and charging integrated cabin operation optimization essentially refers to the objective function of the secondary leader Z.

[0050] Based on the constraints of the operation of the photovoltaic storage and charging integrated cabin, the master-slave game model is used to optimize the objective function. This can fully consider the game relationship between different stakeholders, such as photovoltaic storage and charging integrated cabin operators, electric vehicle users, etc., so as to formulate a more reasonable and fair energy scheduling strategy.

[0051] Since the price of the power grid is tiered, the photovoltaic storage and charging integrated cabin can combine the electricity price signal to optimize the charging and discharging strategy of the energy storage equipment, release the stored energy during the high electricity price period, meet the user's electricity demand, and reduce the electricity cost. The impact of different electricity price policies on operating costs can be analyzed, so as to formulate the optimal operating strategy and reduce the overall operating cost.

[0052] According to the above technical solution, the objective function of leader O is:

[0053] The objective function of the secondary leader Z is:

[0054]

[0055] The objective function of the follower is:

[0056] In the formula, C represents the daily income of the photovoltaic storage and charging integrated cabin, α EV P represents the unit revenue of the photovoltaic storage and charging integrated cabin selling electricity to electric vehicles, w,t Indicates that at t ev The predicted electric vehicle charging power during the time period, Δt ev Indicates that at t ev The time period is the duration of the photovoltaic storage and charging cabin charging the electric vehicle. T1 represents the predicted number of time periods for the photovoltaic storage and charging cabin to charge the electric vehicle. T2 represents the number of time periods for the photovoltaic storage and charging cabin to transmit electricity to the grid. P g,t- represents the power transmitted from the photovoltaic storage and charging integrated cabin to the grid during the time period t2, β t2 represents the unit revenue of the photovoltaic storage and charging cabin selling electricity to the grid in the time period t2, Δt2 represents the duration of the photovoltaic storage and charging cabin transmitting electricity to the grid in the time period t2, T3 represents the number of time periods when the photovoltaic storage and charging cabin purchases electricity from the grid, and γ t3 represents the unit expenditure of the photovoltaic storage and charging integrated cabin to purchase electricity from the grid during the t3 period, P g,t+ represents the electric power transmitted by the solar-storage-charging integrated cabin to the grid during the t3 period, Δt3 represents the duration of the solar-storage-charging integrated cabin purchasing electricity from the grid during the t3 period, C r Indicates the maintenance cost of the integrated photovoltaic storage and charging cabin.

[0057] Among them, the demand for electricity purchased by the photovoltaic storage and charging integrated cabin from the power grid during time period t3 is determined by calculating the difference between the predicted photovoltaic output and the energy stored in the photovoltaic storage and charging integrated cabin during time period t3 and the total energy required for charging the electric vehicle predicted during this time period.

[0058] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: by obtaining the predicted weather conditions and using the photovoltaic output prediction model, the present invention can more accurately predict the power generation capacity of the photovoltaic system in the photovoltaic storage and charging integrated cabin. This helps the photovoltaic storage and charging integrated cabin to fully consider the photovoltaic output when dispatching energy, give priority to the use of green and clean solar energy, and thus improve energy utilization efficiency. According to the predicted weather conditions and the corresponding vehicle flow, the electric vehicle charging prediction model is used to predict the electric vehicle charging data, and the charging plan of the charging station can be reasonably arranged. During the peak load period, unnecessary charging demand can be reduced and the load pressure of the power grid can be reduced; during the low load period, the charging amount can be increased to improve the utilization rate of the energy storage equipment. According to the predicted photovoltaic output and the corresponding electric vehicle charging data, the objective function of the operation optimization of the photovoltaic storage and charging integrated cabin is established, which helps the photovoltaic storage and charging integrated cabin to continuously optimize the energy configuration during the operation process and improve profitability. The present invention can obtain and predict weather conditions and vehicle flow in real time, so as to dynamically adjust the operation strategy of the photovoltaic storage and charging integrated cabin according to these changes, which helps the photovoltaic storage and charging integrated cabin to better adapt to the changing environmental conditions and improve the flexibility and reliability of the system. And through accurate prediction and optimized scheduling, energy storage equipment can be used more effectively to balance grid load and electric vehicle charging needs. This can not only reduce the idle time of energy storage equipment, but also extend its service life and improve the overall reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0060] Figure 1 This is a system topology diagram of a photovoltaic storage and charging integrated cabin of the present invention;

[0061] Figure 2 It is a flow chart of the steps of optimizing the operation of the photovoltaic storage and charging integrated cabin by the energy management system of the present invention;

[0062] In the figure: 1. Photovoltaic subsystem; 2. Energy management system; 3. Lithium battery energy storage subsystem; 4. Energy storage inverter; 5. AC distribution cabinet; 6. Construction site power distribution system interface; 7. Power grid. DETAILED DESCRIPTION

[0063] 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Embodiment 1 A photovoltaic storage and charging integrated cabin comprises: a photovoltaic storage and charging integrated cabin body, a photovoltaic subsystem laid on the top of the photovoltaic storage and charging integrated cabin body, a lithium battery energy storage subsystem arranged inside the photovoltaic storage and charging integrated cabin body, an AC power distribution cabinet, an energy management system and temperature control fire protection;

[0065] The photovoltaic subsystem includes a number of photovoltaic modules and an intelligent tracking system. The photovoltaic modules are used to absorb and utilize solar energy for photoelectric conversion. The intelligent tracking system is used to automatically adjust the angle of the photovoltaic panel according to the angle of sunlight.

[0066] The lithium battery energy storage subsystem is used for the electric energy generated by the lithium battery energy storage subsystem and the electric energy obtained from the power grid;

[0067] As the center of power distribution and control, the AC power distribution cabinet is used to distribute the power in the lithium battery energy storage subsystem to various power-consuming devices;

[0068] The energy management system belongs to the general control center, which is used to control the photovoltaic subsystem, energy storage subsystem, power distribution cabinet and charging pile to work together, and optimize the operation of the photovoltaic storage and charging integrated cabin to maximize energy utilization and minimize costs;

[0069] The temperature control fire protection system includes temperature sensors, smoke detectors, and automatic sprinkler fire extinguishing devices, which are used to monitor and warn the temperature in the cabin in real time. Once an abnormal temperature is predicted, the automatic sprinkler fire extinguishing device will be activated to extinguish the fire.

[0070] The energy management system optimizes the operation of the photovoltaic storage and charging integrated cabin in the following steps:

[0071] Obtain the predicted weather conditions and traffic flow in the photovoltaic-storage-charging integrated cabin area, and use the photovoltaic output prediction model to predict the photovoltaic output by obtaining the predicted weather conditions. Use the electric vehicle charging prediction model to predict the electric vehicle charging data in the photovoltaic-storage-charging integrated cabin area based on the traffic flow corresponding to the predicted weather conditions.

[0072] Determine the constraints for the operation of the photovoltaic storage and charging integrated cabin. The constraints for the operation of the photovoltaic storage and charging integrated cabin include:

[0073]

[0074] SOC min ≤SOC t ≤SOC max ;

[0075]

[0076] Where P Bc,t represents the charging power of the solar-storage-charging integrated cabin during period t, P Bd,t It represents the discharge power of the energy storage in the photovoltaic storage and charging integrated cabin during period t, Indicates the maximum charging power of the photovoltaic storage and charging integrated cabin energy storage, Indicates the maximum discharge power of the photovoltaic storage and charging integrated cabin energy storage, Indicates the charging status. Indicates the state of placing a point, E max Indicates the rated capacity of the photovoltaic storage and charging integrated cabin energy storage, SOC max Indicates the maximum state of charge of the photovoltaic storage and charging integrated cabin energy storage, SOC min Indicates the minimum state of charge of the photovoltaic storage and charging integrated cabin, SOC t Indicates the state of charge of the photovoltaic storage and charging integrated cabin at the end of time period t, SOC t-1 represents the charge state of the integrated photovoltaic storage and charging cabin at the end of the storage period t-1, η c represents the charging efficiency of the photovoltaic storage and charging integrated cabin energy storage, η d It represents the discharge efficiency of the energy storage in the integrated photovoltaic storage and charging cabin, and Δt represents the time period.

[0077] According to the predicted photovoltaic output and the corresponding electric vehicle charging data, the objective function of the photovoltaic storage and charging integrated cabin operation optimization (the objective function of the second-level leader Z) is established:

[0078]

[0079] Based on the constraints of the operation of the photovoltaic, storage and charging integrated cabin, the objective function of optimizing the operation of the photovoltaic, storage and charging integrated cabin is optimized using the master-slave game model.

[0080] The master-slave game model is represented by G = {(O∪Z∪M); L; R};

[0081] Among them, G represents the master-slave game model, O is the leader representing the power grid system, Z is the secondary leader representing the photovoltaic storage and charging integrated cabin, M is the follower representing the electric vehicle system, L represents the strategy set, L={L O ,L Z ,L M}, L O It represents the price quoted by the power grid for purchasing electricity from the photovoltaic storage and charging integrated cabin and the price quoted for selling electricity to the photovoltaic storage and charging integrated cabin. Z The strategy is the electricity sales and purchase strategy of the photovoltaic storage and charging integrated cabin to the electric vehicle, L M represents the electricity purchasing strategy of the electric vehicle system towards the photovoltaic storage and charging integrated cabin; R represents the revenue set, R O is the objective function of leader O, R Z is the objective function of the secondary leader Z, R M is the objective function of the follower.

[0082] Among them, the objective function of leader O is:

[0083] The objective function of the secondary leader Z is:

[0084]

[0085] The objective function of the follower is:

[0086] In the formula, C represents the daily income of the photovoltaic storage and charging integrated cabin, α EV P represents the unit revenue of the photovoltaic storage and charging integrated cabin selling electricity to electric vehicles, w,t Indicates that at t ev The predicted electric vehicle charging power during the time period, Δt ev Indicates that at t ev The time period is the duration of the photovoltaic storage and charging cabin charging the electric vehicle. T1 represents the predicted number of time periods for the photovoltaic storage and charging cabin to charge the electric vehicle. T2 represents the number of time periods for the photovoltaic storage and charging cabin to transmit electricity to the grid. P g,t- represents the power transmitted from the photovoltaic storage and charging integrated cabin to the grid during the time period t2, β t2 represents the unit revenue of the photovoltaic storage and charging cabin selling electricity to the grid in the time period t2, Δt2 represents the duration of the photovoltaic storage and charging cabin transmitting electricity to the grid in the time period t2, T3 represents the number of time periods when the photovoltaic storage and charging cabin purchases electricity from the grid, and γ t3 represents the unit expenditure of the photovoltaic storage and charging integrated cabin to purchase electricity from the grid during the t3 period, P g,t+ represents the electric power transmitted by the solar-storage-charging integrated cabin to the grid during the t3 period, Δt3 represents the duration of the solar-storage-charging integrated cabin purchasing electricity from the grid during the t3 period, C r Indicates the maintenance cost of the integrated photovoltaic storage and charging cabin.

[0087] If the difference between the predicted photovoltaic output in time period t3 and the sum of the energy stored in the photovoltaic storage and charging integrated cabin in time period t3 and the total energy required for charging the electric vehicle predicted in this time period is less than 0, it is determined that there is a demand for the photovoltaic storage and charging integrated cabin to purchase electricity from the power grid.

[0088] The energy converted by the photovoltaic subsystem is used preferentially in the transmission process to the tram.

[0089] Embodiment 2 The photovoltaic output prediction model construction steps include:

[0090] Obtain historical PV output data and its corresponding weather conditions.

[0091] The acquired photovoltaic output historical data is divided into multiple sub-datasets, and the data within each sub-dataset is clustered to obtain local clustering results.

[0092] At least one sub-sample is extracted from the data corresponding to the local clustering result of each sub-data set to form a secondary sample set; and the sub-sample is used to represent the corresponding clustering result in the sub-data set.

[0093] According to the “elbow method”, the cluster number k of the photovoltaic output data in the secondary sample set is confirmed, and K cluster centers are generated.

[0094] Calculate the distance from each point in the secondary sample set to the k cluster centers, take the cluster with the smallest distance to the cluster center as the cluster to which the point belongs, recalculate the new cluster center for each cluster until the sum of the distances from all data points to the cluster center is minimized, and the result is taken as the clustering result of the secondary sample set; the formula for recalculating the new cluster center for each cluster is:

[0095]

[0096] Where D i is the cluster center of the ith cluster after update, C i is the cluster center of the ith cluster, and x is the point in the ith cluster.

[0097] The clustering result corresponding to each sub-sample in the secondary sample set is transferred to the local clustering result corresponding to the sub-sample, and the mode of the clustering result of the secondary sample set corresponding to the local clustering result is counted. The clustering result of the secondary sample set corresponding to the mode is taken as the final result of the local clustering, and then the clustering result of the historical photovoltaic output data is determined.

[0098] The average value corresponding to each cluster of photovoltaic output historical data is calculated, and the average value corresponding to each cluster of photovoltaic output historical data and its corresponding weather conditions are divided into a training set and a validation set.

[0099] The photovoltaic output prediction model is trained using a neural network model based on the training set and the validation set.

[0100] The photovoltaic output is predicted by obtaining the predicted weather conditions and using the photovoltaic output prediction model.

[0101] Embodiment 3 The steps of constructing the electric vehicle charging prediction model include:

[0102] Obtain historical electric vehicle charging data in the solar-storage-charging integrated cabin area and its corresponding weather condition data and traffic flow data;

[0103] The historical electric vehicle charging data is extracted and characterized by a hybrid autoregressive expert with one-dimensional causal convolution;

[0104] The acquired historical tram charging data is characterized by seasonality using a learnable Fourier layer;

[0105] Inputting the trend representation and the seasonal representation into the fully connected layer to obtain new electric vehicle charging data;

[0106] Based on the new electric vehicle charging data and its corresponding weather condition data and traffic flow data, a electric vehicle charging prediction model is obtained by using neural network training.

[0107] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0108] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A photovoltaic storage and charging integrated cabin, characterized in that: include: The photovoltaic subsystem is laid on the top of the photovoltaic storage and charging integrated cabin body, and the lithium battery energy storage subsystem, AC power distribution cabinet, energy management system and temperature control fire protection are arranged inside the photovoltaic storage and charging integrated cabin body; The photovoltaic subsystem includes a number of photovoltaic modules and an intelligent tracking system. The photovoltaic modules are used to absorb and utilize solar energy for photoelectric conversion. The intelligent tracking system is used to automatically adjust the angle of the photovoltaic panel according to the angle of sunlight. The lithium battery energy storage subsystem is used for the electric energy generated by the lithium battery energy storage subsystem and the electric energy obtained from the power grid; The AC power distribution cabinet serves as the center of power distribution and control, and is used to distribute the power in the lithium battery energy storage subsystem to various types of power-consuming equipment; The energy management system belongs to the general control center, which is used to control the photovoltaic subsystem, energy storage subsystem, power distribution cabinet and charging pile to work together, and optimize the operation of the photovoltaic storage and charging integrated cabin to maximize energy utilization and minimize costs; The temperature control fire fighting system includes a temperature sensor, a smoke detector, and an automatic sprinkler fire extinguishing device, which are used to monitor and warn the temperature in the cabin in real time. Once an abnormal temperature is predicted, the automatic sprinkler fire extinguishing device will be activated to extinguish the fire.

2. The integrated photovoltaic storage and charging cabin according to claim 1, characterized in that: The steps of optimizing the operation of the photovoltaic storage and charging integrated cabin by the energy management system include: Obtain the predicted weather conditions and vehicle flow in the photovoltaic storage and charging integrated cabin area, and use the photovoltaic output prediction model to predict photovoltaic output by obtaining the predicted weather conditions. Use the vehicle charging prediction model to predict the electric vehicle charging data in the photovoltaic storage and charging integrated cabin area based on the vehicle flow corresponding to the predicted weather conditions. Determine the constraints for the operation of the photovoltaic storage and charging integrated cabin; The objective function for optimizing the operation of the photovoltaic storage and charging integrated cabin is established based on the predicted photovoltaic output and the corresponding electric vehicle charging data; Based on the constraints of the operation of the photovoltaic, storage and charging integrated cabin, the objective function of optimizing the operation of the photovoltaic, storage and charging integrated cabin is optimized using the master-slave game model.

3. The integrated photovoltaic storage and charging cabin according to claim 2, characterized in that: The photovoltaic output prediction model construction step includes: Obtain historical photovoltaic output data and its corresponding weather conditions; The acquired photovoltaic output historical data is divided into multiple sub-data sets, and the data within each sub-data set is clustered to obtain local clustering results; At least one sub-sample is extracted from the data corresponding to the local clustering result of each sub-data set to form a secondary sample set; the sub-sample is used to represent the corresponding clustering result in the sub-data set; According to the "elbow method", the cluster number k of photovoltaic output data in the secondary sample set is determined, and K cluster centers are generated; Calculate the distance from each point in the secondary sample set to the k cluster centers, take the cluster with the smallest distance to the cluster center as the cluster to which the point belongs, and recalculate a new cluster center for each cluster until the sum of the distances from all data points to the cluster center is minimized. The result is taken as the clustering result of the secondary sample set. The clustering result corresponding to each sub-sample in the secondary sample set is transferred to the local clustering result corresponding to the sub-sample, and the mode of the clustering result of the secondary sample set corresponding to the local clustering result is counted, and the clustering result of the secondary sample set corresponding to the mode is used as the final result of the local clustering, thereby determining the clustering result of the photovoltaic output historical data; Calculate the average value corresponding to each cluster of photovoltaic output historical data, and divide the average value corresponding to each cluster of photovoltaic output historical data and its corresponding weather conditions into a training set and a validation set; Based on the training set and the validation set, the photovoltaic output prediction model is trained using a neural network model; The photovoltaic output is predicted by obtaining the predicted weather conditions and using the photovoltaic output prediction model.

4. The integrated photovoltaic storage and charging cabin according to claim 3, characterized in that: The formula for recalculating the new cluster center for each cluster is: Where D i is the cluster center of the i-th cluster after update, C i is the cluster center of the ith cluster, and x is the point in the ith cluster.

5. The integrated photovoltaic storage and charging cabin according to claim 2, characterized in that: The electric vehicle charging prediction model construction step includes: Obtain historical electric vehicle charging data in the solar-storage-charging integrated cabin area and its corresponding weather condition data and traffic flow data; The historical electric vehicle charging data is extracted and characterized by a hybrid autoregressive expert with one-dimensional causal convolution; The acquired historical tram charging data is characterized by seasonality using a learnable Fourier layer; Inputting the trend representation and the seasonal representation into the fully connected layer to obtain new electric vehicle charging data; Based on the new electric vehicle charging data and its corresponding weather condition data and traffic flow data, a electric vehicle charging prediction model is obtained by using neural network training.

6. The integrated photovoltaic storage and charging cabin according to claim 2, characterized in that: The constraints for the operation of the photovoltaic storage and charging integrated cabin include: SOC min ≤SOC t ≤SOC max ; Where P Bc，t represents the charging power of the solar-storage-charging integrated cabin during period t, P Bd，t It represents the discharge power of the energy storage in the photovoltaic storage and charging integrated cabin during period t, Indicates the maximum charging power of the photovoltaic storage and charging integrated cabin energy storage, Indicates the maximum discharge power of the photovoltaic storage and charging integrated cabin energy storage, Indicates the charging status. Indicates the state of placing a point, E max Indicates the rated capacity of the photovoltaic storage and charging integrated cabin energy storage, SOC max Indicates the maximum state of charge of the photovoltaic storage and charging integrated cabin energy storage, SOC min Indicates the minimum state of charge of the photovoltaic storage and charging integrated cabin, SOC t Indicates the state of charge of the photovoltaic storage and charging integrated cabin at the end of time period t, SOC t-1 represents the charge state of the integrated photovoltaic storage and charging cabin at the end of the storage period t-1, η c represents the charging efficiency of the photovoltaic storage and charging integrated cabin energy storage, η d It represents the discharge efficiency of the energy storage in the photovoltaic storage and charging integrated cabin, and △t represents the time period.

7. The integrated photovoltaic storage and charging cabin according to claim 2, characterized in that: The master-slave game model is expressed as G={(O∪Z∪M); L; R}; Among them, G represents the master-slave game model, O is the leader representing the power grid system, Z is the secondary leader representing the photovoltaic storage and charging integrated cabin, M is the follower representing the electric vehicle system, L represents the strategy set, L={L O , L Z , L M }, L O It represents the price quoted by the power grid for purchasing electricity from the photovoltaic storage and charging integrated cabin and the price quoted for selling electricity to the photovoltaic storage and charging integrated cabin. Z The strategy is the electricity sales and purchase strategy of the photovoltaic storage and charging integrated cabin to the electric vehicle, L M It indicates the electricity purchasing strategy of the electric vehicle system towards the integrated photovoltaic storage and charging cabin; R represents the revenue set, R O is the objective function of leader O, R Z is the objective function of the secondary leader Z, R M is the objective function of the follower.

8. The integrated photovoltaic storage and charging cabin according to claim 1, characterized in that: The objective function of leader 0 is: The objective function of the secondary leader Z is: The objective function of the follower is: In the formula, C represents the daily income of the photovoltaic storage and charging integrated cabin, α EV P represents the unit revenue of the photovoltaic storage and charging integrated cabin selling electricity to electric vehicles, w，t Indicates that at t ev The predicted electric vehicle charging power in the time period, △t ev Indicates that at t ev The time period is the duration of the photovoltaic storage and charging cabin charging the electric vehicle. T1 represents the predicted number of time periods for the photovoltaic storage and charging cabin to charge the electric vehicle. T2 represents the number of time periods for the photovoltaic storage and charging cabin to transmit electricity to the grid. P g，t- represents the power transmitted from the photovoltaic storage and charging integrated cabin to the grid during the time period t2, β t2 represents the unit revenue of the photovoltaic storage and charging cabin selling electricity to the grid in the t2 period, △t2 represents the duration of the photovoltaic storage and charging cabin transmitting electricity to the grid in the t2 period, T3 represents the number of time periods when the photovoltaic storage and charging cabin purchases electricity from the grid, and Y t3 represents the unit expenditure of the photovoltaic storage and charging integrated cabin to purchase electricity from the grid during the t3 period, P g，t+ represents the electric power transmitted by the photovoltaic storage and charging integrated cabin to the grid during the t3 period, △t3 represents the duration of the photovoltaic storage and charging integrated cabin purchasing electricity from the grid during the t3 period, C r Indicates the maintenance cost of the integrated photovoltaic storage and charging cabin.

Images