Intelligent regulation and control system of light storage charging pile
Through quantum entangled communication and priority-benefit evaluation algorithm combined with multi-sensor monitoring and closed-loop feedback control, the shortcomings in communication and energy allocation of traditional optical storage charging pile systems are solved, and efficient, safe and flexible energy regulation is achieved to meet user needs.
Patent Information
- Application Number
- CN202510634277.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2025-08-26
AI Technical Summary
Traditional optical storage charging pile systems have insufficient transmission speed, security and stability in communication, lack accurate energy status monitoring and efficient energy allocation algorithms, which are difficult to meet real-time and efficient information interaction and energy allocation needs, and fail to comprehensively consider user needs.
The quantum entangled communication module is used to realize the instantaneous transmission of information between sites, and combined with dynamic quantum key distribution optimization algorithm to improve communication security and stability; the central control module adopts an energy allocation algorithm based on priority-benefit evaluation, combined with a multi-sensor fusion energy monitoring algorithm and a closed-loop feedback control optimization algorithm to achieve efficient and reasonable allocation of energy; introduced a hybrid prediction algorithm and reinforcement learning algorithm of long-term and short-term memory networks and gray prediction models to dynamically optimize energy regulation strategies, and incorporated into the user demand response module for regulation.
It realizes high-speed and safe information transmission between optical storage charging pile systems, accurate energy status monitoring and efficient energy allocation, which can adapt to complex environment changes, meet user needs, reduce regulation costs, and improve system flexibility and adaptability.
Smart Images
Figure CN120534232A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of energy regulation technology, and in particular to an intelligent regulation system for a photovoltaic charging pile. Background Art
[0002] With the rapid development of the new energy vehicle industry, charging piles, as important supporting facilities for electric vehicles, are becoming increasingly widespread in number and distribution. As a comprehensive facility integrating photovoltaic power generation, energy storage system and charging functions, photovoltaic charging piles can not only effectively alleviate the pressure on the power grid, but also utilize renewable energy and improve energy utilization efficiency.
[0003] Traditional photovoltaic charging pile systems have many shortcomings in energy regulation. First, in terms of communication, traditional systems mostly rely on wired or wireless communication methods, which have limitations in transmission speed, security and stability, and are difficult to meet the real-time and efficient information exchange needs between large-scale photovoltaic charging pile sites. Secondly, in terms of energy monitoring and regulation, traditional systems often lack accurate energy status monitoring and efficient energy allocation algorithms, resulting in low energy utilization efficiency and difficulty in coping with energy supply and demand imbalances. In addition, traditional systems often ignore user needs in the energy regulation process, making it difficult to achieve economical and efficient energy allocation while meeting user charging needs.
[0004] Aiming at the shortcomings of traditional photovoltaic charging pile systems in energy regulation, the present invention proposes an intelligent regulation system for photovoltaic charging piles. Summary of the Invention
[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an intelligent control system for photovoltaic charging piles. It can realize the instantaneous transmission of information between sites through the quantum entanglement communication module, and combine with the dynamic quantum key distribution optimization algorithm to effectively improve the security and stability of the communication link. At the same time, the central control module adopts an energy allocation algorithm based on priority-benefit evaluation, comprehensively considering the urgency of energy demand and the benefits of the allocation plan, and selects the optimal energy allocation plan, thereby realizing efficient and reasonable allocation of energy.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent control system for a photovoltaic charging pile, the system comprising the following components: a quantum entanglement communication module, an energy monitoring module, an energy control execution module and a central control module;
[0007] The quantum entanglement communication module is used to establish a quantum entanglement communication link between each photovoltaic charging station site, and realize the instantaneous transmission of information based on the principle of quantum entanglement;
[0008] The energy monitoring module is used to monitor the energy supply and demand status of the photovoltaic charging station in real time, determine whether there is an energy supply and demand imbalance, and send the imbalance information to the central control module;
[0009] The energy control execution module is used to receive energy control instructions issued by the central control module and execute corresponding energy control operations;
[0010] The central control module is used to generate energy control instructions based on preset energy control strategies and algorithms after receiving energy supply and demand imbalance information sent by the energy monitoring module, and send the control instructions to other related photovoltaic charging pile sites through the quantum entanglement communication module. At the same time, it receives control instructions sent by other sites, controls the energy control execution module to perform corresponding operations according to the local energy status, and realizes the coordinated allocation of energy.
[0011] Furthermore, when establishing a quantum entanglement communication link, the quantum entanglement communication module adopts a dynamic quantum key distribution optimization algorithm. This algorithm is based on the uncertainty of quantum states and the principle of non-cloning. In the initial stage, the quantum entanglement communication module of each site generates an initial quantum key pool. The size of the key pool is determined by the number of sites N and the security requirement level S. The specific formula is K pool =α×N β ×S γ , where α, β, and γ are coefficients determined through a large number of experiments and security assessments. The experiment selected site networks of different sizes and simulated various attack scenarios. The goal was to lower the probability of key cracking to below the industry standard. Through regression analysis, we obtained α = 0.5, β = 1.2, and γ = 0.8. During the communication process, the key update period T is dynamically adjusted according to the real-time bit error rate E of the quantum channel and the communication frequency F. The formula is: Here, δ is the adjustment coefficient. By testing the stability and efficiency of quantum communication in different environments, δ=10 was determined after multiple experimental optimizations. This algorithm effectively improves the security and stability of the quantum entanglement communication link and ensures the reliability of energy control command transmission.
[0012] Furthermore, the energy monitoring module adopts a multi-sensor fusion energy status monitoring algorithm. The module integrates multiple sensors such as current sensor, voltage sensor, power sensor and environmental sensor. In the data fusion process, an adaptive weight distribution mechanism is introduced. For the data collected by different types of sensors, the historical measurement accuracy of the sensor is used to calculate the weight distribution mechanism. i , data acquisition frequency f i And the correlation coefficient r between the data ij To determine the weight w i , the specific calculation method is: Where n is the total number of sensors. The historical measurement accuracy is calculated by recording the error between the sensor measurement value and the standard value over a long period of time. The data acquisition frequency is set according to the sensor performance. The correlation coefficient is calculated using the Pearson correlation coefficient formula. Through this algorithm, the energy monitoring module can more accurately monitor the energy supply and demand status, reduce misjudgments caused by single sensor errors, and provide more reliable data support for energy regulation.
[0013] Furthermore, when generating energy control instructions, the central control module adopts an energy allocation algorithm based on priority-benefit evaluation. The algorithm divides energy demand into three levels: emergency demand, important demand and general demand, and assigns priority weights P1, P2 and P3 respectively, and P1>P2>P3. The weights are determined by expert scoring combined with hierarchical analysis method. Energy experts are invited to score the importance of different demands and construct a judgment matrix. After calculation, it is found that P1=0.6, P2=0.3, and P3=0.1. At the same time, the benefit of each allocation plan is evaluated. The benefit indicators include energy transmission loss L, allocation time t, and impact on the energy balance of other sites I. The benefit calculation formula is The central control module selects the optimal energy allocation plan based on a comprehensive assessment of priorities and benefits, and generates control instructions to achieve efficient and reasonable energy allocation.
[0014] Furthermore, when executing energy control operations, the energy control execution module adopts a closed-loop feedback control optimization algorithm. When executing energy transmission or reception operations, it monitors the actual parameters of energy transmission in real time, compares them with the target parameters in the instructions issued by the central control module, calculates the deviation value ΔX, and adjusts the operating parameters of the energy control equipment based on the deviation value and the preset adjustment coefficient λ. The response characteristics of the system under different working conditions are determined by experimental testing, and λ = 0.8. The adjustment formula is X new =X old +λ×ΔX, where X new is the adjusted operating parameter, X old To adjust the operating parameters before, through continuous feedback and adjustment, ensure that the energy control operation can accurately meet the instruction requirements and improve the accuracy and stability of energy allocation.
[0015] Furthermore, the quantum entanglement communication module is also provided with an interference detection and adaptive compensation module. This module detects whether there is external interference in real time by monitoring the changes in the quantum state. When interference is detected, an adaptive compensation algorithm based on quantum state reconstruction is adopted. First, according to the type and intensity of the interference, the damage degree parameter D of the quantum state is determined. The calculation of D comprehensively considers the frequency, amplitude and duration factors of the interference signal. Then, according to the damage degree parameter D and the preset compensation coefficient table, which is established by a large number of simulated interference experiments and records the optimal compensation parameters under different interference conditions, the damaged quantum state is reconstructed. The expression of the compensated quantum state is |ψ new >=μ(D)×|ψ old >+v(D)×|Δψ>, where |ψ new > is the quantum state after compensation, |ψ old > is the quantum state before damage, |Δψ> is the modified quantum state determined according to the interference characteristics, μ(D) and v(D) are compensation coefficients related to the damage degree parameter D. This module effectively improves the anti-interference ability of the quantum entangled communication link in complex environments and ensures the accuracy of information transmission.
[0016] Furthermore, the energy monitoring module also has an energy forecasting function, which adopts a hybrid forecasting algorithm based on the combination of long short-term memory network and grey forecasting model. The LSTM network is used to learn the complex nonlinear time series characteristics of energy data, and the grey forecasting model is used to quickly predict the short-term energy change trend. In the process of model fusion, the weights w of the two are dynamically adjusted according to the prediction errors e and e2 in different time periods. LSTM and w GM , the calculation formula is w GM =1-w LSTM ,Through this hybrid prediction algorithm, the energy monitoring module ,can predict the changing trend of energy supply and demand in advance, ,providing forward-looking data for the central control module to formulate a more ,reasonable energy regulation strategy, and further improve ,the stability and flexibility of the energy network.
[0017] Furthermore, the central control module is provided with an energy control strategy dynamic optimization module, which dynamically optimizes the preset energy control strategy according to factors such as energy market price fluctuations, uncertainty of renewable energy power generation, and user charging behavior patterns, introduces a reinforcement learning algorithm, and takes minimizing energy allocation costs, maximizing user satisfaction, and maximizing energy network stability as objective functions. By continuously interacting with the environment, it learns the optimal control strategy. During the learning process, it adjusts the parameters in the control strategy according to the reward value after each control operation. After multiple iterative learning, the energy control strategy can adapt to the ever-changing external environment and realize economical and efficient energy allocation.
[0018] Furthermore, the system also includes a user demand response module, which collects user charging reservation information, charging time preference and charging price acceptance data. In the energy regulation process, the user demand factor is incorporated into the energy regulation strategy, and a regulation algorithm based on the balance of user satisfaction and energy cost is adopted to define the user satisfaction index S user and energy cost index C energy The user satisfaction index is calculated based on the difference between the user's waiting time, the charging price and the expected price. The energy cost index considers the energy procurement cost and the transmission cost. By adjusting the energy allocation plan, S user and C energy To reach equilibrium, the specific equilibrium formula is min(ω1×(1-S user )+ω2
[0019] C energy ), where ω1 and ω2 are weight coefficients, which are determined through user research and cost analysis, ω1 = 0.4, ω2 = 0.6. This module not only meets user needs, but also reduces energy regulation costs and improves the overall benefits of the system.
[0020] Compared with the existing technology, the intelligent control system of the solar energy storage charging pile has the following beneficial effects:
[0021] 1. The system uses a quantum entanglement communication module to achieve instantaneous transmission of information between sites. Combined with a dynamic quantum key distribution optimization algorithm, it effectively improves the security and stability of the communication link. At the same time, the central control module adopts an energy allocation algorithm based on priority-benefit evaluation, comprehensively considering the urgency of energy demand and the benefits of the allocation plan, and selects the optimal energy allocation plan, achieving efficient and reasonable energy allocation. In addition, the energy control execution module adopts a closed-loop feedback control optimization algorithm to monitor and adjust energy transmission parameters in real time to ensure the accuracy of the control operation, further improving the stability of energy control.
[0022] 2. The system uses a hybrid prediction algorithm based on the combination of long-short-term memory network and grey prediction model to predict the changing trend of energy supply and demand in advance, and provide forward-looking data for the central control module to formulate more reasonable energy regulation strategies. At the same time, the central control module is equipped with an energy regulation strategy dynamic optimization module. According to the energy market price fluctuations, the uncertainty of new energy power generation and the user charging behavior pattern factors, the preset energy regulation strategy is dynamically optimized, and the reinforcement learning algorithm is introduced to enable the energy regulation strategy to adapt to the ever-changing external environment. In addition, the system also includes a user demand response module, which incorporates user demand factors into the energy regulation strategy and adopts a regulation algorithm based on the balance of user satisfaction and energy cost. While meeting user needs, it reduces the energy regulation cost, improves the overall benefits of the system, and further enhances the flexibility and adaptability of the system.
[0023] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.
[0025] Figure 1 Provide a flow chart for the intelligent control system function of the solar-storage charging pile;
[0026] Figure 2 This is a flow chart of the overall architecture of the intelligent control system of the solar-storage charging pile. DETAILED DESCRIPTION
[0027] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.
[0028] Example 1
[0029] In a certain city's commercial district, there are multiple photovoltaic storage charging stations. During the daytime on weekdays, there is a high demand for vehicle charging in the commercial district, and the energy supply at some stations is tight. However, adjacent stations have sufficient sunlight, more photovoltaic panels generate electricity, and fewer charging vehicles, resulting in an energy surplus.
[0030] The quantum entanglement communication module of each site uses the dynamic quantum key distribution optimization algorithm to establish a communication link. Assuming that the number of sites N = 10, the security requirement level S = 3, and the coefficients α = 0.5, β = 1.2, and γ = 0.8 determined through a large number of experiments and security assessments, the initial quantum key pool size K pool =α×N β ×S γ =0.5×10 1.2 ×3 0.8 ≈13.74. During the communication process, if the quantum channel real-time bit error rate E = 0.05, the communication frequency F = 10 Hz, and the adjustment coefficient δ = 0.1, then the key update period
[0031] An energy status monitoring algorithm using multi-sensor fusion is used. Taking one of the sites as an example, the integrated current sensor, voltage sensor, power sensor and environmental sensor collect data in real time. Assuming that the site has n = 4 sensors, the historical measurement accuracy of the current sensor is A1 = 0.9, the data acquisition frequency is f1 = 20Hz, the historical measurement accuracy of the voltage sensor is A2 = 0.85, the data acquisition frequency is f2 = 15Hz, the historical measurement accuracy of the power sensor is A3 = 0.92, the data acquisition frequency is f3 = 18Hz, the historical measurement accuracy of the environmental sensor is A4 = 0.8, the data acquisition frequency is f4 = 10Hz. After calculation, the correlation coefficient r between the current sensor and the voltage sensor is 12 =0.6 Correlation coefficient r between current sensor and power sensor 13 =0.7, correlation coefficient r between current sensor and environmental sensor 14 =0.3, then the electric By fusing data from various sensors, the energy supply and demand imbalance at the site can be accurately determined, and the imbalance information can be sent to the central control module.
[0032] After receiving the information about the imbalance between energy supply and demand, an energy allocation algorithm based on priority-benefit evaluation is used to divide energy demand into three levels: emergency demand, important demand, and general demand, and assign priority weights P1 = 0.5, P2 = 0.3, and P3 = 0.2 respectively. When evaluating the benefits of the allocation plan, assuming that the energy transmission loss of a certain allocation plan is L = 0.1, the allocation time is t = 5 minutes, and the impact on the energy balance of other sites is I = 0.2, then the benefit After comprehensive evaluation, the optimal deployment plan is selected to generate control instructions, which are sent to relevant sites through the quantum entanglement communication module.
[0033] After receiving the control command, the closed-loop feedback control optimization algorithm is used to perform the energy transmission operation. Assuming that the initial operating parameters of the energy control equipment are X old=50, the target parameter is 60, the actual parameter obtained by real-time monitoring is 55, then the deviation value ΔX=55-60=-5, the preset adjustment coefficient λ=0.5, the adjusted operating parameter X new =X old +λ×ΔX=50+0.5×(-5)=47.5, and continue adjusting until the target parameters are reached to complete energy allocation.
[0034] Example 2
[0035] A large industrial park houses many different types of factories, covering industries such as electronic manufacturing and mechanical processing. These factories are equipped with a certain number of electric vehicles for transportation within the factory and employee commuting. Every evening, when the factory finishes its day's production, a large number of electric vehicles return to the park and charge. At this time, the sun gradually sets, and the photovoltaic power generation relied on by the photovoltaic storage charging piles in the park continues to decrease as the light intensity weakens. The energy supply that can originally meet daily charging needs faces severe challenges during this period, and the problem of imbalance between energy supply and demand is becoming increasingly prominent.
[0036] The energy monitoring module integrates a variety of high-precision sensors. These sensors work closely together to conduct comprehensive, real-time monitoring of the energy status of each photovoltaic charging station in the industrial park. The current sensor accurately measures the current during the charging process, the voltage sensor provides real-time feedback on the voltage value, and the power sensor comprehensively calculates the charging power. The environmental sensor can also monitor environmental factors such as light intensity and temperature, providing more comprehensive data support for energy status analysis.
[0037] It has energy forecasting capabilities and uses a hybrid forecasting algorithm based on a combination of a long-short-term memory network and a grey forecasting model. In the period before dusk, the long-short-term memory network fully utilizes its powerful learning ability to conduct in-depth analysis of a large amount of energy data accumulated in the past, mining the complex nonlinear time series characteristics therein. It can capture differences in energy consumption patterns in different seasons, weekdays and weekends, as well as the impact of weather changes on photovoltaic power generation and vehicle charging needs.
[0038] The gray prediction model, with its advantage in quickly predicting short-term data change trends, can accurately estimate upcoming short-term energy change trends. For example, it can quickly predict the decline in photovoltaic power generation in the next few tens of minutes based on the slight changes in current light intensity and the light attenuation patterns in historical data.
[0039] Combining the prediction results of the two models, the energy monitoring module will dynamically adjust the weights of the two according to the prediction errors in different time periods. When it is found that the prediction results of the LSTM network in a certain time period are closer to the actual data and the error is smaller, its weight in the final prediction result will be increased accordingly. Conversely, if the gray prediction model performs better in a certain period of time, its weight will also increase accordingly. Through this dynamic adjustment mechanism, the accuracy and reliability of the energy forecast results are ensured. Finally, after accurately judging the imbalance between energy supply and demand, the energy monitoring module will quickly send this key information to the central control module.
[0040] After receiving the forecast information from the energy monitoring module, the central control module immediately activates the response mechanism. Given the production continuity and importance of the factories in the industrial park, the charging demand of the factory vehicles is set to the important demand level. This means that when formulating the energy allocation strategy, the charging needs of the factory vehicles will be given priority to ensure the subsequent normal operation of the factory.
[0041] The central control module fully considers the key factor of energy market price fluctuations. Assuming that in the current period, due to changes in the supply and demand relationship in the electricity market, electricity prices are at a relatively low level, in this case, in order to minimize the energy allocation cost, the central control module enables the energy regulation strategy dynamic optimization module and introduces the reinforcement learning algorithm.
[0042] The algorithm takes minimizing energy allocation costs, maximizing user satisfaction and maximizing energy network stability as its core objective functions. The central control module continuously interacts with the environment in which the energy system is located, and obtains real-time information such as the system's operating status, energy market price changes, and energy supply and demand conditions at each site. Through a large number of attempts and learning, it gradually explores the optimal regulation strategy. In this process, after each regulation operation, the system will give a reward value based on the actual effect. If a certain allocation operation successfully reduces energy costs while ensuring the user's charging needs, improving user satisfaction, and maintaining the stable operation of the energy network, then a higher reward value will be given. Conversely, if the allocation effect is not good, resulting in increased costs, user dissatisfaction or network instability, a lower reward value will be given. The central control module continuously adjusts the parameters in the regulation strategy based on these reward values. After multiple iterative learning, it determines the optimal solution for allocating energy from nearby energy-surplus sites to industrial park sites.
[0043] The quantum entanglement communication module undertakes a crucial communication task. It uses the magical properties of quantum entanglement to establish a high-speed and secure communication link between various photovoltaic charging pile sites. This communication method based on the principle of quantum entanglement can realize the instantaneous transmission of information, greatly improving the system's response speed and control efficiency.
[0044] To ensure the security and stability of communication, the quantum entanglement communication module adopts a series of advanced technologies and algorithms. When establishing a quantum entanglement communication link, strict quantum key distribution will be carried out. Through a complex encryption mechanism, it is guaranteed that information will not be stolen or tampered with during transmission. At the same time, the module also has strong anti-interference capabilities and can monitor the status of the quantum channel in real time. Once external interference is detected, corresponding measures will be taken immediately to compensate and repair it to ensure smooth communication. In the energy allocation of this industrial park, the quantum entanglement communication module will quickly and accurately send the control instructions generated by the central control module to the relevant sites, providing a strong guarantee for the timely allocation of energy.
[0045] After receiving the control instructions issued by the central control module, the energy control execution module responds quickly and executes the energy receiving operation. During the execution process, it adopts a closed-loop feedback control optimization algorithm to monitor the actual parameters of energy transmission in real time. For example, it obtains the voltage, current, and power parameters in the energy transmission process through sensors in real time, and carefully compares these actual parameters with the target parameters in the instructions issued by the central control module.
[0046] Once a deviation is found between the actual parameters and the target parameters, the energy control execution module will immediately calculate the deviation value and accurately adjust the operating parameters of the energy control equipment according to the preset adjustment coefficient. Through continuous monitoring, comparison and adjustment, it ensures that energy can be stably and efficiently transmitted to the photovoltaic storage charging station in the industrial park to meet the charging needs of factory vehicles, effectively alleviate the problem of energy supply and demand imbalance, and ensure the normal operation of the industrial park.
[0047] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.
Claims
1. The intelligent control system of the solar energy storage charging pile is characterized by: The system includes the following components: quantum entanglement communication module, energy monitoring module, energy regulation execution module and central control module; The quantum entanglement communication module is used to establish a quantum entanglement communication link between each photovoltaic charging station site, and realize the instantaneous transmission of information based on the principle of quantum entanglement; The energy monitoring module is used to monitor the energy supply and demand status of the photovoltaic charging station in real time, determine whether there is an energy supply and demand imbalance, and send the imbalance information to the central control module; The energy control execution module is used to receive energy control instructions issued by the central control module and execute corresponding energy control operations; The central control module is used to generate energy control instructions based on preset energy control strategies and algorithms after receiving energy supply and demand imbalance information sent by the energy monitoring module, and send the control instructions to other related photovoltaic charging pile sites through the quantum entanglement communication module. At the same time, it receives control instructions sent by other sites and controls the energy control execution module to perform corresponding operations according to the local energy status.
2. The intelligent control system for the photovoltaic charging pile according to claim 1 is characterized in that: When establishing a quantum entanglement communication link, the quantum entanglement communication module adopts a dynamic quantum key distribution optimization algorithm. This algorithm is based on the uncertainty of quantum states and the principle of non-cloning. In the initial stage, the quantum entanglement communication module of each site generates an initial quantum key pool. The size of the key pool is determined by the number of sites N and the security requirement level S. The specific formula is K pool =α×N β ×S γ , where α, β, and γ are coefficients determined through a large number of experiments and security assessments. During the communication process, the key update period T is dynamically adjusted according to the real-time bit error rate E of the quantum channel and the communication frequency F. The formula is: Where δ is the adjustment coefficient.
3. The intelligent control system for the photovoltaic charging pile according to claim 1 is characterized in that: The energy monitoring module adopts the energy status monitoring algorithm of multi-sensor fusion. The module integrates multiple sensors such as current sensor, voltage sensor, power sensor and environmental sensor. In the data fusion process, an adaptive weight distribution mechanism is introduced. For the data collected by different types of sensors, the historical measurement accuracy of the sensor is used to calculate the weight distribution of the data. i , data acquisition frequency f i And the correlation coefficient r between the data ij To determine the weight w i , the specific calculation method is: Where n is the total number of sensors. The historical measurement accuracy is calculated by recording the error between the sensor measurement value and the standard value over a long period of time. The data collection frequency is set according to the sensor performance, and the correlation coefficient is calculated using the Pearson correlation coefficient formula.
4. The intelligent control system for the photovoltaic charging pile according to claim 1 is characterized in that: When generating energy control instructions, the central control module adopts an energy allocation algorithm based on priority-benefit evaluation. This algorithm divides energy demand into three levels: emergency demand, important demand, and general demand, and assigns priority weights P1, P2, and P3 respectively, with P1>P2>P3. At the same time, the benefit of each allocation plan is evaluated. The benefit indicators include energy transmission loss L, allocation time t, and impact on the energy balance of other sites I. The benefit calculation formula is: The central control module selects the optimal energy allocation plan and generates control instructions based on a comprehensive assessment of priorities and benefits.
5. The intelligent control system for the photovoltaic charging pile according to claim 1 is characterized in that: The energy control execution module uses a closed-loop feedback control optimization algorithm when performing energy control operations. When performing energy transmission or reception operations, it monitors the actual parameters of energy transmission in real time, compares them with the target parameters in the instructions issued by the central control module, calculates the deviation value ΔX, and adjusts the operating parameters of the energy control equipment according to the deviation value and the preset adjustment coefficient λ. The adjustment formula is X new =X old +λ×ΔX, where X new is the adjusted operating parameter, X old are the operating parameters before adjustment.
6. The intelligent control system for the photovoltaic charging pile according to claim 1 is characterized in that: The quantum entanglement communication module is also equipped with an interference detection and adaptive compensation module. This module detects whether there is external interference in real time by monitoring the changes in the quantum state. When interference is detected, an adaptive compensation algorithm based on quantum state reconstruction is adopted. First, the damage degree parameter D of the quantum state is determined according to the type and intensity of the interference. The calculation of D comprehensively considers the frequency, amplitude and duration factors of the interference signal. Then, based on the damage degree parameter D and a preset compensation coefficient table, which is established through a large number of simulated interference experiments and records the optimal compensation parameters under different interference conditions, the damaged quantum state is reconstructed. The expression of the compensated quantum state is |ψ new >=μ(D)×|ψ old >+ν(D)×|Δψ>, where |ψ new > is the quantum state after compensation, |ψ old > is the quantum state before damage, |Δψ> is the corrected quantum state determined according to the interference characteristics, and μ(D) and v(D) are compensation coefficients related to the damage degree parameter D.
7. The intelligent control system for the photovoltaic charging pile according to claim 1 is characterized in that: The energy monitoring module also has an energy forecasting function, which adopts a hybrid forecasting algorithm based on the combination of long short-term memory network and grey forecasting model. LSTM network is used to learn the complex nonlinear time series characteristics of energy data, and grey forecasting model is used to quickly predict the short-term energy change trend. In the process of model fusion, the weights w of the two are dynamically adjusted according to the forecast errors e1 and e2 in different time periods. LSTM and w GM , the calculation formula is w GM =1-w LSTM .
8. The intelligent control system for photovoltaic charging piles according to claim 1 is characterized in that: The central control module is provided with an energy regulation strategy dynamic optimization module, which dynamically optimizes the preset energy regulation strategy based on factors such as energy market price fluctuations, uncertainty in renewable energy power generation, and user charging behavior patterns. It introduces a reinforcement learning algorithm, with minimizing energy allocation costs, maximizing user satisfaction, and maximizing energy network stability as objective functions. By continuously interacting with the environment, it learns the optimal regulation strategy. During the learning process, the parameters in the regulation strategy are adjusted according to the reward value after each regulation operation. After multiple iterative learning, the energy regulation strategy can adapt to the ever-changing external environment.
9. The intelligent control system for photovoltaic charging piles according to claim 1, characterized in that: The system also includes a user demand response module, which collects user charging reservation information, charging time preferences, and charging price acceptance data. In the energy regulation process, user demand factors are incorporated into the energy regulation strategy, and a regulation algorithm based on the balance between user satisfaction and energy cost is adopted to define the user satisfaction index S. user and energy cost index C energy The user satisfaction index is calculated based on the difference between the user's waiting time, the charging price and the expected price. The energy cost index considers the energy procurement cost and the transmission cost. By adjusting the energy allocation plan, S user and C energy To reach equilibrium, the specific equilibrium formula is min(ω1×(1-S user )+ω2×C energy ), where ω1 and ω2 are weight coefficients.