Charging pile power control method and system for photovoltaic power supply

Abstract

The invention discloses a charging pile power control method and system for photovoltaic power supply, and relates to the technical field of intelligent control. The method comprises the following steps: constructing a multi-source power supply mode; collecting photovoltaic power generation power, an energy storage SOC value, a charging pile power demand and commercial power time-of-use electricity price data in real time; pre-constructing a power distribution model, and performing dynamic matching calculation on photovoltaic power generation power, an energy storage SOC value, a charging pile power demand and commercial power time-of-use electricity price data to generate a first power supply instruction; verifying the first power supply instruction according to the economic evaluation index to generate a second power supply instruction; and based on the second power supply instruction, controlling the output power proportion of the photovoltaic direct supply mode, the energy storage peak regulation mode and the commercial power supplement mode, and executing multi-source cooperative power supply of the charging pile. The technical problem that the energy utilization efficiency is low due to the fact that the photovoltaic charging pile is difficult to distribute energy according to the real-time working condition in the prior art is solved, and the technical effect of improving the energy utilization efficiency is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and particularly to a method and system for controlling the power of a charging pile powered by photovoltaic. Background Art

[0002] With the popularization of new energy vehicles and the rapid development of photovoltaic technology, photovoltaic charging piles, as a new type of facility that combines renewable energy and the charging needs of electric vehicles, have received increasing attention. However, the power supply system of photovoltaic charging piles faces many challenges. Since photovoltaic power generation is greatly affected by factors such as weather and time, its output power has instability and intermittency. At the same time, the charging demand of electric vehicles also changes at any time, which requires the power supply system of photovoltaic charging piles to have a high degree of flexibility and intelligence. Traditional power supply control methods often cannot optimize energy distribution according to real-time conditions, resulting in low energy utilization efficiency and high operating costs. Summary of the Invention

[0003] This application provides a method and system for controlling the power of a charging pile powered by photovoltaic, which solves the technical problem that it is difficult for existing photovoltaic charging piles to perform energy distribution according to real-time working conditions, resulting in low energy utilization efficiency.

[0004] In the first aspect of this application, a method for controlling the power of a charging pile powered by photovoltaic is provided. The method includes:

[0005] Constructing a multi-source power supply mode, which includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains power supplementary mode; collecting real-time photovoltaic power generation, energy storage SOC value, charging pile power demand, and mains power time-of-use price data; pre-constructing a power distribution model, and dynamically matching and calculating the photovoltaic power generation, energy storage SOC value, charging pile power demand, and mains power time-of-use price data based on the power distribution model to generate a first power supply instruction, where the first power supply instruction includes a first photovoltaic output power, a first energy storage output power, and a first mains power output power; verifying the first power supply instruction according to an economic evaluation index to generate a second power supply instruction; and based on the second power supply instruction, controlling the output power ratio of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains power supplementary mode to perform multi-source collaborative power supply of the charging pile.

[0006] In the second aspect of this application, a power control system for a charging pile powered by photovoltaic is provided. The system includes:

[0007] A mode construction module for constructing a multi-source power supply mode, where the multi-source power supply mode includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains supplement mode; a data acquisition module for real-time acquisition of photovoltaic power generation power, energy storage SOC value, charging pile power demand, and mains time-of-use electricity price data; a matching calculation module for pre-constructing a power distribution model and performing dynamic matching calculations on the photovoltaic power generation power, energy storage SOC value, charging pile power demand, and mains time-of-use electricity price data based on the power distribution model to generate a first power supply instruction, where the first power supply instruction includes a first photovoltaic output power, a first energy storage output power, and a first mains output power; a verification module for verifying the first power supply instruction according to economic evaluation indicators to generate a second power supply instruction; and a power supply module for controlling the output power ratio of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains supplement mode based on the second power supply instruction to perform multi-source collaborative power supply for the charging pile.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] First, construct a multi-source power supply mode, which includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains supplement mode. Next, real-time collect photovoltaic power generation power, energy storage SOC value, charging pile power demand, and mains time-of-use electricity price data. Then, pre-construct a power distribution model and perform dynamic matching calculations on the photovoltaic power generation power, energy storage SOC value, charging pile power demand, and mains time-of-use electricity price data based on the power distribution model to generate a first power supply instruction, where the first power supply instruction includes a first photovoltaic output power, a first energy storage output power, and a first mains output power. Further, verify the first power supply instruction according to economic evaluation indicators to generate a second power supply instruction. Finally, based on the second power supply instruction, control the output power ratio of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains supplement mode to perform multi-source collaborative power supply for the charging pile. This solves the technical problem in the prior art that it is difficult for photovoltaic charging piles to perform energy distribution according to real-time working conditions, resulting in low energy utilization efficiency, and achieves the technical effect of improving energy utilization efficiency. Description of the Drawings

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0011] Figure 1 Schematic flowchart of the charging pile power control method for photovoltaic power supply provided in the embodiments of this application;

[0012] Figure 2 Schematic structural diagram of a charging pile power control system for photovoltaic power supply provided by an embodiment of the present application.

[0013] Explanation of reference numerals: mode construction module 11, data acquisition module 12, matching calculation module 13, verification module 14, power supply module 15. Detailed implementation manners

[0014] By providing a charging pile power control method and system for photovoltaic power supply, the present application solves the technical problem in the prior art that it is difficult for a photovoltaic charging pile to perform energy distribution according to real-time working conditions, resulting in low energy utilization efficiency.

[0015] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with 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. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0016] It should be noted that the terms "include" and "have" are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0017] Embodiment 1, as Figure 1 shown, the present application provides a charging pile power control method for photovoltaic power supply, wherein the method includes:

[0018] Construct a multi-source power supply mode, and the multi-source power supply mode includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains supplement mode.

[0019] In this embodiment, constructing a multi-source power supply mode specifically includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains supplement mode. Among them, the photovoltaic direct supply mode is the highest-priority power supply mode, the energy storage peak shaving mode is the second-priority power supply mode, and the mains supplement mode is the lowest-priority mode.

[0020] Furthermore, the multi-source power supply mode includes:

[0021] Set the photovoltaic direct supply mode as the highest priority. When the real-time photovoltaic power is greater than or equal to the power demand of the charging pile, full photovoltaic power supply is executed; when the real-time photovoltaic power is insufficient, activate the energy storage peak shaving mode, generate the first power supply instruction, and execute the coordinated power supply of the photovoltaic direct supply mode and the energy storage peak shaving mode based on the first power supply instruction; when the photovoltaic direct supply mode and the energy storage peak shaving mode still cannot meet the demand, start the mains supplement mode to execute multi-source coordinated power supply.

[0022] Specifically, set the photovoltaic direct supply mode as the highest priority power supply mode, and monitor and collect the instantaneous power generation of the photovoltaic array in real time; when the collected real-time photovoltaic power generation is greater than or equal to the power demand of the current charging pile, directly supply full power to the charging pile in the photovoltaic direct supply mode, and at this time, neither the energy storage nor the mains needs to be started. When it is detected in real time that the power generation of the photovoltaic array cannot fully meet the demand of the charging pile, the energy storage peak shaving mode of the secondary priority is automatically activated. At this time, the system performs comprehensive calculations based on the pre-constructed power distribution model and the current energy storage SOC value to determine a reasonable first power supply instruction, which specifically includes the first photovoltaic output power and the first energy storage output power, so as to realize the coordinated joint power supply of the photovoltaic direct supply mode and the energy storage peak shaving mode. When the coordinated power supply of the photovoltaic direct supply mode and the energy storage peak shaving mode still cannot meet the power demand of the charging pile, the system will automatically start the mains supplement mode of the lowest priority, determine the proportion of the supplementary mains output power according to the first mains output power included in the foregoing first power supply instruction, and finally execute the multi-source power supply coordinated by the photovoltaic, energy storage and mains to ensure that the power demand of the charging pile is fully met.

[0023] Collect the photovoltaic power generation, energy storage SOC value, charging pile power demand and mains time-of-use electricity price data in real time.

[0024] In this embodiment, the control system collects the real-time power generation of the photovoltaic array, the real-time SOC value of the energy storage system, the real-time power demand of the charging pile, and the mains time-of-use electricity price data provided by the power grid in real time. Among them, the photovoltaic power generation is obtained by the MPPT controller, the energy storage SOC value is collected and corrected by the battery management system (BMS), the charging pile power demand is calculated by measuring the voltage and current, and the mains time-of-use electricity price data is obtained in real time through the power grid interface, providing an accurate data basis for subsequent dynamic power optimization and distribution.

[0025] Furthermore, collect the photovoltaic power generation, energy storage SOC value, charging pile power demand and mains time-of-use electricity price data in real time. The method includes:

[0026] Obtain the real-time photovoltaic power generation of the photovoltaic array through the MPPT controller; read the energy storage SOC value of the BMS system, and use the Kalman filter algorithm to correct the state estimation of the energy storage SOC value; synchronously collect the instantaneous voltage value and current instantaneous value of the charging pile, and calculate the power demand of the charging pile based on the instantaneous voltage value and current instantaneous value; obtain the time-of-use electricity price data of the mains power from the API interface of the power grid dispatching system.

[0027] First, the power generation of the photovoltaic array is monitored in real time through the maximum power point tracking (MPPT) controller. The MPPT controller automatically optimizes the power output according to the ambient light intensity, temperature, and the working state of the photovoltaic module, and transmits the real-time collected photovoltaic power generation to the control system. Second, the state of charge (SOC) of the energy storage system is monitored in real time through the battery management system (BMS), and the SOC value is corrected by the Kalman filter algorithm to ensure that the SOC value of the energy storage system accurately reflects the actual power storage level of the battery. In addition, the instantaneous voltage and current values of the charging pile are collected in real time through the power metering device. The control system calculates the instantaneous power demand of the charging pile according to the power calculation formula P = U × I (where P is power, U is voltage, and I is current), and feeds the demand data back to the system. Finally, to achieve economic optimization, the system obtains the time-of-use electricity price data of the mains power in real time through the API interface of the power grid dispatching system, including the electricity price information during peak hours, flat hours, and off-peak hours.

[0028] Furthermore, the time-of-use electricity price data of the mains power includes peak-hour electricity price data, flat-hour electricity price data, and off-peak-hour electricity price data.

[0029] The peak-hour electricity price data reflects the electricity price during the period of high grid load, usually during the period of large demand (such as some periods during the day or on weekdays), and the electricity price is relatively high at this time; the flat-hour electricity price data is applicable to the period of medium grid load, usually during the non-peak period but the power demand is still relatively stable, and the electricity price is relatively stable; the off-peak-hour electricity price data reflects the electricity price during the period of low grid load, usually at night or during the period of low power demand, and the electricity price is relatively cheap. By obtaining these time-of-use electricity price data in real time, the system can, under the multi-source power supply mode, give priority to using the mains power during off-peak hours according to economic considerations, and reasonably adjust the mains power usage strategy between peak hours and off-peak hours, thereby reducing the power cost of the charging pile and improving the economy of the system.

[0030] Pre-construct a power distribution model, and perform dynamic matching calculations on the photovoltaic power generation, energy storage SOC value, charging pile power demand, and time-of-use electricity price data of the mains power based on the power distribution model to generate a first power supply instruction, where the first power supply instruction includes the first photovoltaic output power, the first energy storage output power, and the first mains power output.

[0031] By comprehensively analyzing the photovoltaic power generation, energy storage SOC value, charging pile power demand, and time-of-use electricity price data of the mains power, a power distribution model is constructed that can dynamically match and optimize the power supply ratio. Based on the relationships and constraints between different data, the power distribution model can calculate the optimal output power ratio of each energy source (photovoltaic, energy storage, and mains power) in real time. Input the real-time collected photovoltaic power generation, energy storage SOC value, charging pile power demand, and time-of-use electricity price data of the mains power for dynamic matching calculation to generate a first power supply instruction, which specifies the output power values of each energy source, including the first photovoltaic output power, the first energy storage output power, and the first mains power output power.

[0032] Furthermore, to pre-construct the power distribution model, the method includes:

[0033] Retrieve the historical power supply data of the charging pile based on big data; obtain a preset sorting strategy, and split the historical power supply data based on the preset sorting strategy to obtain multiple sorted data sets; count the multiple sorted data volumes of the multiple sorted data sets, calculate the ratio of the multiple sorted data volumes to the data volume of the historical power supply data to obtain multiple sorting weights; perform supervised learning on the multiple sorted data sets to construct multiple power distribution sub-models, and use the multiple sorting weights to label the multiple power distribution sub-models; integrate the multiple power distribution sub-models to construct the power distribution model.

[0034] The pre-built power distribution model specifically includes: First, obtain the historical power supply data of the charging piles through big data retrieval technology. This data includes information such as photovoltaic power generation, energy storage SOC value, charging pile power demand, and mains power usage. These historical data provide rich samples for subsequent model training. Then, based on a preset sorting strategy, split the obtained historical power supply data according to specific conditions. For example, according to factors such as time period, electricity price level, weather conditions, or load demand, divide the data into multiple sorted data sets. Each sorted data set reflects the operating conditions of the charging piles under certain specific conditions, thus ensuring that the model can handle changes in different situations. Subsequently, count the sorted data volume of each sorted data set, and calculate the ratio of the sorted data volume of each sorted data set to the data volume of the historical power supply data to obtain multiple sorting weights. These sorting weights reflect the importance and influence of each sorted data set in the overall data, and help to assign different data sets different priorities in the learning process during subsequent model construction. Next, perform supervised learning on these multiple sorted data sets, and use supervised learning algorithms (such as regression analysis, neural networks, etc.) to construct multiple power distribution sub-models. Each sub-model is trained on a specific data set, thus forming power distribution strategies for different situations. Finally, integrate these multiple power distribution sub-models to form an overall power distribution model. This model can dynamically calculate the optimal power distribution plan based on the input real-time data (such as photovoltaic power, energy storage SOC value, charging pile power demand, and mains electricity price, etc.), ensuring that various energy sources (photovoltaic, energy storage, mains) can work together in actual operation to meet the power demand of the charging piles, while optimizing energy utilization efficiency.

[0035] Verify the first power supply instruction according to the economic evaluation index, and generate a second power supply instruction.

[0036] According to the economic evaluation index, analyze the first power supply instruction, especially the mains power output, and calculate the expected economic index based on the economic evaluation function. If the calculation result shows that the cost of using the mains power is relatively high and exceeds the set economic evaluation index, the system will postpone starting the mains power supplement mode until the next electricity price period. Based on this verification process, the system generates a second power supply instruction to adjust the output ratio of photovoltaic, energy storage, and mains power to ensure that the power demand of the charging pile is met, while optimizing the economy and reducing the electricity cost.

[0037] Furthermore, verifying the first power supply instruction according to the economic evaluation index to generate a second power supply instruction, the method includes:

[0038] Analyze the first power supply instruction to obtain the first mains power output; calculate the expected economic index for the first mains power output based on the economic evaluation function. The specific form of the economic evaluation function is as follows: Among them, E is the predicted economic indicator, ΔP is the mains power output, T remain is the predicted remaining charging time, C price is the time-of-use electricity price of the mains power, K grid-load is the grid load factor, and the grid load factor is the ratio of the current actual load of the grid to the maximum load-carrying capacity of the grid; when the predicted economic indicator is greater than the economic evaluation indicator, the mains power supplement mode is delayed until the next electricity price period, and a second power supply instruction is generated.

[0039] Specifically, the first power supply instruction is parsed to extract the first mains power output therein. The first mains power output reflects the supplementary power from the grid when the photovoltaic and energy storage cannot fully meet the power demand of the charging pile; the predicted economic indicator is calculated for the first mains power output by using a preset economic evaluation function; in the economic evaluation function, E is the predicted economic indicator, ΔP is the mains power output, T remain is the predicted remaining charging time, C price is the time-of-use electricity price of the mains power, K grid-load is the grid load factor, representing the ratio of the current actual load of the grid to the maximum load-carrying capacity of the grid. The economic indicator E calculated can be used to evaluate the economy of the current mains power usage.

[0040] If the calculated economic indicator E is greater than the set economic evaluation indicator (i.e., the cost threshold), it indicates that the usage cost of the current mains power supplement mode is too high and does not meet the economic requirements. At this time, the system will postpone starting the mains power supplement mode until the next electricity price period, or adjust the timing of supplementing grid power under other conditions. Finally, the system generates a second power supply instruction according to the economic evaluation result, and the second power supply instruction will readjust the output power ratio of photovoltaic direct supply, energy storage peak shaving, and mains power supplement to ensure that the power demand of the charging pile can be fully met without exceeding the economic threshold.

[0041] Based on the second power supply instruction, control the output power ratio of the photovoltaic direct supply mode, energy storage peak shaving mode, and mains power supplement mode, and perform multi-source collaborative power supply for the charging pile.

[0042] The system dynamically adjusts the output ratios of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains supplement mode according to the respective output powers of the photovoltaic, energy storage, and mains power determined in the second power supply instruction. The photovoltaic direct supply mode preferentially meets the power demand of the charging pile. When the photovoltaic power is sufficient, the system will maximize the use of photovoltaic power generation to reduce the system's dependence on the mains power. If the photovoltaic power is insufficient to meet the power demand of the charging pile, the system will start the energy storage peak shaving mode according to the second power supply instruction, and supplement the insufficient power by adjusting the charge and discharge behavior of the energy storage battery to ensure that the charging pile continuously obtains stable power supply. When the photovoltaic direct supply and energy storage peak shaving modes still cannot meet the power demand of the charging pile, the system will enable the mains supplement mode according to the second power supply instruction to supplement the remaining required power. Through this multi-source collaborative power supply mechanism, the system can flexibly adjust the output power ratios of the three power supply modes, not only effectively allocate power according to the real-time photovoltaic power generation situation and the SOC value of the energy storage battery, but also dynamically optimize the use of the mains power according to the electricity price changes of the power grid.

[0043] Furthermore, after implementing the multi-source collaborative power supply for the charging pile, the method further includes:

[0044] Real-time monitor the actual power demand and power supply situation of the charging pile, and collect feedback data; according to the feedback data, compare it with the prediction result of the power distribution model, and calculate the power supply deviation index; when the power supply deviation index exceeds the preset deviation threshold, generate a feedback training sample based on the power supply deviation index; adopt incremental learning to update the power distribution model based on the feedback training sample.

[0045] After the multi-source collaborative power supply of the charging pile is implemented, the system monitors the actual power demand and power supply situation of the charging pile in real time, and continuously collects relevant feedback data. These feedback data include the change of power demand at each moment of the charging pile, the change of the actual power supply source (photovoltaic, energy storage, mains power), etc. Then, the system compares the feedback data collected in real time with the prediction results of the power distribution model, and calculates the power supply deviation index. The power supply deviation index reflects the difference between the actual power supply and the model-predicted power distribution, and can help the system identify whether there are errors or optimization spaces. For example, if the actual power demand of the charging pile is much higher than the prediction, or the photovoltaic power generation is insufficient, resulting in the system relying more on the mains power, it will cause a power supply deviation. When the calculated power supply deviation index exceeds the preset deviation threshold, it means that the power distribution model fails to accurately predict and meet the actual demand of the charging pile under the current working conditions. At this time, the system generates a feedback training sample based on the power supply deviation index. This feedback training sample contains the power supply deviation data that appears in the actual operation, and records the sources and natures of these deviations, which are used as further learning materials for the model. Finally, an incremental learning method is used to update the power distribution model. Incremental learning enables the system to continuously adjust and optimize the model according to the newly collected feedback data, without having to retrain the entire model from scratch every time. Specifically, the system inputs the generated feedback training sample into the incremental learning algorithm, and the incremental learning algorithm adjusts and optimizes the parameters in the power distribution model according to the input feedback sample. As more feedback data is collected and more feedback training samples are continuously generated, the incremental learning method will continue to dynamically adjust the model, enabling the model to perform more accurate and efficient power distribution when facing different working conditions. Through continuous incremental learning, the power distribution model evolves continuously, and can perform more precise dynamic matching between photovoltaic power generation, energy storage discharge, and mains power supplementation, improving the overall efficiency and economy of multi-source collaborative power supply.

[0046] In summary, the embodiments of the present application have at least the following technical effects:

[0047] First, a multi-source power supply mode is constructed. The multi-source power supply mode includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains power supplementary mode. Next, the photovoltaic power generation power, the energy storage SOC value, the charging pile power demand, and the mains power time-of-use price data are collected in real time. Then, a power distribution model is pre-constructed, and based on the power distribution model, dynamic matching calculations are performed on the photovoltaic power generation power, the energy storage SOC value, the charging pile power demand, and the mains power time-of-use price data to generate a first power supply instruction. The first power supply instruction includes a first photovoltaic output power, a first energy storage output power, and a first mains power output power. Further, the first power supply instruction is verified according to the economic evaluation index to generate a second power supply instruction. Finally, based on the second power supply instruction, the output power ratios of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains power supplementary mode are controlled to perform multi-source collaborative power supply for the charging pile. This solves the technical problem in the prior art that it is difficult for a photovoltaic charging pile to perform energy distribution according to real-time working conditions, resulting in low energy utilization efficiency, and achieves the technical effect of improving energy utilization efficiency.

[0048] Embodiment 2, based on the same inventive concept as the method for controlling the power of a charging pile for photovoltaic power supply in the foregoing embodiment, as Figure 2 shown, the present application provides a power control system for a charging pile for photovoltaic power supply, wherein the system includes:

[0049] A mode construction module 11, configured to construct a multi-source power supply mode, where the multi-source power supply mode includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains power supplementary mode; a data collection module 12, configured to collect the photovoltaic power generation power, the energy storage SOC value, the charging pile power demand, and the mains power time-of-use price data in real time; a matching calculation module 13, configured to pre-construct a power distribution model, and perform dynamic matching calculations on the photovoltaic power generation power, the energy storage SOC value, the charging pile power demand, and the mains power time-of-use price data based on the power distribution model to generate a first power supply instruction, where the first power supply instruction includes a first photovoltaic output power, a first energy storage output power, and a first mains power output power; a verification module 14, configured to verify the first power supply instruction according to the economic evaluation index to generate a second power supply instruction; a power supply module 15, configured to control the output power ratios of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains power supplementary mode based on the second power supply instruction to perform multi-source collaborative power supply for the charging pile.

[0050] Further, the mode construction module 11 is configured to execute the following method:

[0051] Set the photovoltaic direct supply mode as the highest priority. When the real-time photovoltaic power is greater than or equal to the power demand of the charging pile, full photovoltaic power supply is executed; when the real-time photovoltaic power is insufficient, the energy storage peak shaving mode is activated to generate the first power supply instruction, and coordinated power supply of the photovoltaic direct supply mode and the energy storage peak shaving mode is executed based on the first power supply instruction; when the photovoltaic direct supply mode and the energy storage peak shaving mode still cannot meet the demand, the mains supplement mode is started to execute multi-source coordinated power supply.

[0052] Further, the data acquisition module 12 is used to execute the following method:

[0053] Obtain the real-time photovoltaic power generation power of the photovoltaic array through the MPPT controller; read the energy storage SOC value of the BMS system, and use the Kalman filter algorithm to correct the state estimation of the energy storage SOC value; synchronously collect the instantaneous voltage value and instantaneous current value of the charging pile, and calculate the power demand of the charging pile based on the instantaneous voltage value and instantaneous current value; obtain the time-of-use electricity price data of the mains from the API interface of the power grid dispatching system.

[0054] Further, the matching calculation module 13 is used to execute the following method:

[0055] Obtain the historical power supply data of the charging pile through big data retrieval; obtain the preset sorting strategy, and split the historical power supply data based on the preset sorting strategy to obtain multiple sorted data sets; count the multiple sorted data volumes of the multiple sorted data sets, and calculate the ratio of the multiple sorted data volumes to the data volume of the historical power supply data to obtain multiple sorted weights; perform supervised learning on the multiple sorted data sets to construct multiple power distribution sub-models, and use the multiple sorted weights to identify the multiple power distribution sub-models; integrate the multiple power distribution sub-models to construct the power distribution model.

[0056] Further, the verification module 14 is used to execute the following method:

[0057] Parse the first power supply instruction to obtain the first mains output power; calculate the expected economic index of the first mains output power based on the economic evaluation function. The specific form of the economic evaluation function is as follows: Where E is the expected economic index, ΔP is the mains output power, T remain is the expected remaining charging time, C price is the time-of-use electricity price of the mains, K grid-load is the power grid load factor, and the power grid load factor is the ratio of the current actual load of the power grid to the maximum carrying capacity of the power grid; when the expected economic index is greater than the economic evaluation index, delay starting the mains supplement mode until the next electricity price period to generate the second power supply instruction.

[0058] Further, the data acquisition module 12 is used to execute the following method:

[0059] The time-of-use electricity price data of the mains power includes peak period electricity price data, flat period electricity price data, and off-peak period electricity price data.

[0060] Further, the power supply module 15 is used to execute the following method:

[0061] Monitor the actual power demand and power supply situation of the charging pile in real time, and collect feedback data; compare the feedback data with the prediction result of the power distribution model to calculate the power supply deviation index; when the power supply deviation index exceeds the preset deviation threshold, generate a feedback training sample based on the power supply deviation index; use incremental learning to update the power distribution model based on the feedback training sample.

[0062] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0063] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0064] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A power control method for a charging pile powered by photovoltaic, characterized in that, The method includes: Constructing a multi-source power supply mode, which includes a photovoltaic direct supply mode, an energy storage peak shaving mode, and a mains power supplementary mode; Real-time collecting photovoltaic power generation, energy storage SOC value, charging pile power demand, and mains power time-of-use price data; Pre-constructing a power distribution model, and dynamically matching and calculating the photovoltaic power generation, energy storage SOC value, charging pile power demand, and mains power time-of-use price data based on the power distribution model to generate a first power supply instruction, where the first power supply instruction includes a first photovoltaic output power, a first energy storage output power, and a first mains power output power; Verifying the first power supply instruction according to the economic evaluation index to generate a second power supply instruction; Based on the second power supply instruction, controlling the output power ratio of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains power supplementary mode, and performing multi-source collaborative power supply for the charging pile.

2. The power control method of the charging pile for photovoltaic power supply according to claim 1, wherein The multi-source power supply mode includes: Setting the photovoltaic direct supply mode as the highest priority. When the real-time photovoltaic power is greater than or equal to the charging pile power demand, full photovoltaic power supply is executed; Activating the energy storage peak shaving mode when the real-time photovoltaic power is insufficient, generating the first power supply instruction, and performing collaborative power supply of the photovoltaic direct supply mode and the energy storage peak shaving mode based on the first power supply instruction; When the photovoltaic direct supply mode and the energy storage peak shaving mode still cannot meet the demand, start the mains power supplementary mode to perform multi-source collaborative power supply.

3. The power control method of the charging pile for photovoltaic power supply according to claim 1, wherein Real-time collecting photovoltaic power generation, energy storage SOC value, charging pile power demand, and mains power time-of-use price data, the method includes: Obtaining the real-time photovoltaic power generation of the photovoltaic array through an MPPT controller; Reading the energy storage SOC value of the BMS system and using the Kalman filter algorithm to correct the state estimation of the energy storage SOC value; Synchronously collecting the instantaneous voltage value and instantaneous current value of the charging pile, and calculating the charging pile power demand based on the instantaneous voltage value and instantaneous current value; Obtaining the mains power time-of-use price data from the API interface of the power grid dispatching system.

4. The power control method for a charging pile powered by photovoltaics according to claim 3, wherein, Pre-constructing a power distribution model, the method includes: Obtaining the historical power supply data of the charging pile based on big data retrieval; Obtaining a preset sorting strategy, and splitting the historical power supply data based on the preset sorting strategy to obtain multiple sorted data sets; Counting the multiple sorted data amounts of the multiple sorted data sets, calculating the ratio of the multiple sorted data amounts to the data amount of the historical power supply data to obtain multiple sorting weights; Performing supervised learning on the multiple sorted data sets, constructing multiple power distribution sub-models, and using the multiple sorting weights to label the multiple power distribution sub-models; Integrating the multiple power distribution sub-models to construct the power distribution model.

5. The power control method for a charging pile powered by photovoltaic as described in claim 4, characterized in that, Verifying the first power supply instruction according to the economic evaluation index to generate a second power supply instruction, the method includes: Parsing the first power supply instruction to obtain the first mains power output power; Calculating the expected economic index of the first mains power output power based on the economic evaluation function, and the specific economic evaluation function is as follows: Among them, E is the expected economic indicator, ΔP is the mains power output, T remain is the expected remaining charging time, C price is the time-of-use electricity price of the mains power, K grid-load is the grid load factor, and the grid load factor is the ratio of the current actual load of the grid to the maximum carrying capacity of the grid; When the expected economic index is greater than the economic evaluation index, delaying the start of the mains power supplementary mode until the next electricity price period to generate a second power supply instruction.

6. The method for controlling the power of a charging pile for photovoltaic power supply according to claim 3, wherein, The time-of-use electricity price data of the mains power supply includes peak period electricity price data, flat period electricity price data, and off-peak period electricity price data.

7. The power control method of the charging pile for photovoltaic power supply according to claim 1, wherein After implementing the multi-source collaborative power supply of the charging pile, the method further includes: Real-time monitoring of the actual power demand and power supply situation of the charging pile, and collecting feedback data; According to the feedback data, comparing with the prediction result of the power distribution model, and calculating the power supply deviation index; When the power supply deviation index exceeds the preset deviation threshold, generating a feedback training sample based on the power supply deviation index; Adopting incremental learning, and updating the power distribution model based on the feedback training sample.

8. A power control system for a charging pile powered by photovoltaics, characterized in that, For implementing the charging pile power control method for photovoltaic power supply according to any one of claims 1-7, the system includes: A mode construction module for constructing a multi-source power supply mode, the multi-source power supply mode including a photovoltaic direct supply mode, a energy storage peak shaving mode, and a mains power supply supplement mode; A data acquisition module for real-time collecting photovoltaic power generation, energy storage SOC value, charging pile power demand, and time-of-use electricity price data of the mains power supply; A matching calculation module for pre-constructing a power distribution model, and dynamically matching and calculating the photovoltaic power generation, energy storage SOC value, charging pile power demand, and time-of-use electricity price data of the mains power supply based on the power distribution model, and generating a first power supply instruction, the first power supply instruction including a first photovoltaic output power, a first energy storage output power, and a first mains power supply output power; A verification module for verifying the first power supply instruction according to the economic evaluation index, and generating a second power supply instruction; A power supply module for controlling the output power ratio of the photovoltaic direct supply mode, the energy storage peak shaving mode, and the mains power supply supplement mode based on the second power supply instruction, and implementing the multi-source collaborative power supply of the charging pile.

Images