Light storage and charging integrated charging station management system based on energy regulation and control algorithm

Abstract

The invention discloses a light storage and charging integrated charging station management system based on an energy regulation and control algorithm, and belongs to the technical field of charging station energy management. The invention discloses a light storage and charging integrated charging station management system based on an energy regulation and control algorithm. The system comprises a photovoltaic power generation device, an energy storage device, a charging device and an energy management model. The energy management model comprises a data acquisition module, a data analysis module, an energy control module and an energy scheduling execution module; the photovoltaic power generation device is bidirectionally connected with the energy management model, the energy storage device is bidirectionally connected with the energy management model, and the charging device is bidirectionally connected with the energy management model. The charging efficiency and the energy utilization rate of the light storage and charging integrated charging station can be greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of charging station energy management, and more specifically to a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm. Background Art

[0002] With the popularization of electric vehicles and the development of renewable energy, the optimization and intelligence of the energy management system of the integrated photovoltaic storage and charging station, as an important infrastructure connecting electric vehicles and renewable energy, has become a hot topic in current research. The traditional charging station management system has the following shortcomings: Low energy utilization efficiency, unable to accurately predict photovoltaic power generation and electric vehicle charging demand, resulting in unreasonable energy allocation and low energy utilization efficiency; Traditional control strategies are often based on fixed rules or simple threshold judgments and cannot be optimized and adjusted based on real-time data and future prediction results, further limiting the improvement of energy efficiency. Poor ability to cope with uncertainty. The uncertainty of photovoltaic power generation and electric vehicle charging demand poses challenges to the stable operation of the charging station system.

[0003] Therefore, the present invention proposes a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm to effectively improve energy utilization and stability. Summary of the invention

[0004] In view of the shortcomings of the above-mentioned technologies, such as low energy utilization and poor stability, the present invention discloses a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm, which can effectively improve energy utilization and stability.

[0005] A photovoltaic storage and charging integrated charging station management system based on energy control algorithm, comprising: Photovoltaic power generation devices, which convert solar energy into electrical energy through photovoltaic panels; An energy storage device stores the electric energy generated by the photovoltaic power generation device or the electric energy of the power grid, and manages the charging and discharging process of the energy storage device through a battery management system BMS; A charging device, providing charging services for electric vehicles; the charging device includes a DC charging terminal and an AC charging terminal; An energy management model, which realizes coordinated control of the photovoltaic power generation device, the energy storage device and the charging device through an energy control algorithm; the energy management model includes a data acquisition module, a data analysis module, an energy control module and an energy scheduling execution module; the energy control algorithm includes an improved support vector machine and model predictive control; The data acquisition module collects the operation data information of the device in real time through the sensor network model, and the operation data information at least includes current, voltage, power and the operation status of the device; The data analysis module performs data analysis through an improved support vector machine, predicts energy demand, and optimizes energy distribution; the improved support vector machine includes a data preprocessing unit, a feature selection and extraction unit, a model construction unit, a classification unit, a training optimization unit, and a prediction and evaluation unit; the signal output end of the data preprocessing unit is connected to the signal input end of the feature selection and extraction unit, the signal output end of the feature selection and extraction unit is connected to the signal input end of the model construction unit, the signal output end of the model construction unit is connected to the signal input end of the classification unit, the signal output end of the classification unit is connected to the signal input end of the training optimization unit, and the signal output end of the training optimization unit is connected to the signal input end of the prediction and evaluation unit; The energy control module performs secondary prediction of the data analysis results in real time through model predictive control according to the analysis results of the data analysis module, and formulates an optimal charging and discharging strategy according to the prediction results; The energy scheduling execution module executes the energy scheduling task according to the strategy formulated by the energy control module; The photovoltaic power generation device is bidirectionally connected to the energy management model, the energy storage device is bidirectionally connected to the energy management model, the charging device is bidirectionally connected to the energy management model, the signal output end of the data acquisition module is connected to the signal input end of the data analysis, the signal output end of the data analysis module is connected to the signal input end of the energy control module, and the signal output end of the energy control module is connected to the signal input end of the energy scheduling execution module.

[0006] As a further embodiment of the present invention, the data acquisition module includes a first data acquisition unit, a second data acquisition unit and a third data acquisition unit; the first data acquisition unit collects data information of the photovoltaic power generation device through a first sensor network, and the data information includes at least photovoltaic power generation power, power generation, photovoltaic panel temperature and light intensity; the first sensor network includes at least a voltage sensor, a current sensor, a temperature sensor and a photoresistor; the second data acquisition unit collects data information of the energy storage device through a second sensor network, and the data information includes at least state of charge, charge and discharge current, charge and discharge voltage and temperature; the third data acquisition unit collects data information of the charging device through a third sensor network, and the data information includes at least charging power, charging time, charging current and working status of the charging device; the first sensor network, the second sensor network and the third sensor network adopt a mesh network topology, and form the sensor network model through a star network topology. As a further embodiment of the present invention, the input sample of the model construction unit is: The optimal problem of the classification hyperplane in the classification unit is expressed as: In formula (4), f is the optimal decision. As a further embodiment of the present invention, the improved support vector machine classification process is that SVM1 is used as the root node of the binary tree to determine the test samples of the first category of the data, and the samples that do not belong to the first category are classified by SVM2 until SVM The qth class of samples is decided. In formula (3), is the Lagrange multiplier, is the optimal objective function;

[0007] As a further embodiment of the present invention, the model predictive control includes a prediction unit, an optimization unit, a control unit, a feedback adjustment unit and a human-computer interaction unit; the signal output end of the prediction unit is connected to the signal input end of the optimization unit, the signal output end of the optimization unit is connected to the signal input end of the control unit, the signal output end of the control unit is connected to the signal input end of the feedback adjustment unit, and the signal output end of the control unit is connected to the signal input end of the human-computer interaction unit; the prediction unit performs long-term and short-term predictions on the future based on real-time collected data, the long-term prediction time is 1 to 7 days, and the short-term prediction time is 0.5 to 2 4h, the prediction results include photovoltaic power generation, power changes of energy storage batteries, and load requirements of charging piles; the optimization unit formulates the optimal charging and discharging strategy based on the prediction data; the control unit selects the first element as the current control input from the optimal control sequence obtained by optimization, and applies it to the model, and adjusts the output of the photovoltaic power generation system, the charging and discharging power of the energy storage system, and the load distribution of the charging pile according to the current control input; the feedback adjustment unit re-monitors the system status at the beginning of the next control cycle, collects new data, and conducts a new round of prediction and optimization; the human-computer interaction unit monitors the operating status, views the prediction results and optimization strategy through the display screen and keyboard.

[0008] As a further embodiment of the present invention, the control unit controls the energy flow of the photovoltaic power generation device, the energy storage device and the charging device; The conditions that the energy scheduling of the photovoltaic power generation device satisfies are: is the total charging power of the energy storage device; when the photovoltaic power generation power of the photovoltaic power generation device is greater than the total demand of the charging device and the energy storage device, the remaining electric energy is stored in the energy storage device or connected to the grid; when the photovoltaic power generation power of the photovoltaic power generation device is insufficient, the electric energy of the energy storage device is used to power the charging device, and the insufficient part is supplemented by the power grid; the charging device is intelligently dispatched according to the charging demand of the electric vehicle and the energy state of the current system, and the electric energy of the photovoltaic power generation and energy storage devices is used to charge the electric vehicle.

[0009] As a further embodiment of the present invention, the energy flow is that the photovoltaic power generation device converts sunlight into electrical energy, and the generated direct current is sent to the photovoltaic inverter, the photovoltaic inverter converts the direct current into alternating current, and the converted alternating current is sent to the AC bus, and the electric energy is transmitted to the power grid through the transformer, and the power grid and the AC bus are transmitted bidirectionally; the electric energy is transmitted to the energy storage device through the energy storage inverter, and the AC bus and the energy storage inverter are transmitted bidirectionally, and the energy storage inverter and the energy storage device are transmitted bidirectionally; the electric energy directly powers the charging pile.

[0010] Positive beneficial effects A photovoltaic storage and charging integrated charging station management system based on an energy control algorithm constructs an accurate energy prediction model through an improved support vector machine, realizes accurate prediction of photovoltaic power generation and electric vehicle charging demand, and provides an important reference basis for model predictive control; model predictive control calculates the optimal control strategy based on the current system state and future prediction results, realizes coordinated optimization among photovoltaic power generation, energy storage and charging, improves energy utilization efficiency, and enhances system stability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work, among which: Figure 1 This is a schematic diagram of the overall architecture of a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm of the present invention; Figure 2 This is a working principle diagram of an energy management model of a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm of the present invention; Figure 3 The working principle of the improved support vector machine of the photovoltaic storage and charging integrated charging station management system based on the energy control algorithm of the present invention; Figure 4 This is a working principle diagram of an improved support vector machine classification of a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm of the present invention; Figure 5 This is a working principle diagram of a model predictive control of a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm of the present invention; Figure 6 This is an energy flow diagram of a photovoltaic storage and charging integrated charging station management system based on an energy control algorithm of the present invention. DETAILED DESCRIPTION

[0012] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0013] A photovoltaic storage and charging integrated charging station management system based on energy control algorithm, comprising: Photovoltaic power generation devices, which convert solar energy into electrical energy through photovoltaic panels; An energy storage device stores the electric energy generated by the photovoltaic power generation device or the electric energy of the power grid, and manages the charging and discharging process of the energy storage device through a battery management system BMS; A charging device, providing charging services for electric vehicles; the charging device includes a DC charging terminal and an AC charging terminal; An energy management model, which realizes coordinated control of the photovoltaic power generation device, the energy storage device and the charging device through an energy control algorithm; the energy management model includes a data acquisition module, a data analysis module, an energy control module and an energy scheduling execution module; the energy control algorithm includes an improved support vector machine and model predictive control; The data acquisition module collects the operation data information of the device in real time through the sensor network model, and the operation data information at least includes current, voltage, power and the operation status of the device; The data analysis module performs data analysis through an improved support vector machine, predicts energy demand, and optimizes energy distribution; the improved support vector machine includes a data preprocessing unit, a feature selection and extraction unit, a model construction unit, a classification unit, a training optimization unit, and a prediction and evaluation unit; the signal output end of the data preprocessing unit is connected to the signal input end of the feature selection and extraction unit, the signal output end of the feature selection and extraction unit is connected to the signal input end of the model construction unit, the signal output end of the model construction unit is connected to the signal input end of the classification unit, the signal output end of the classification unit is connected to the signal input end of the training optimization unit, and the signal output end of the training optimization unit is connected to the signal input end of the prediction and evaluation unit; The energy control module performs secondary prediction of the data analysis results in real time through model predictive control according to the analysis results of the data analysis module, and formulates an optimal charging and discharging strategy according to the prediction results; The energy scheduling execution module executes the energy scheduling task according to the strategy formulated by the energy control module; The photovoltaic power generation device is bidirectionally connected to the energy management model, the energy storage device is bidirectionally connected to the energy management model, the charging device is bidirectionally connected to the energy management model, the signal output end of the data acquisition module is connected to the signal input end of the data analysis, the signal output end of the data analysis module is connected to the signal input end of the energy control module, and the signal output end of the energy control module is connected to the signal input end of the energy scheduling execution module.

[0014] In the present invention, the data acquisition module includes a first data acquisition unit, a second data acquisition unit and a third data acquisition unit; the first data acquisition unit collects data information of the photovoltaic power generation device through a first sensor network, and the data information at least includes photovoltaic power generation power, power generation, photovoltaic panel temperature and light intensity; the first sensor network at least includes a voltage sensor, a current sensor, a temperature sensor and a photoresistor; the second data acquisition unit collects data information of the energy storage device through a second sensor network, and the data information at least includes charge state, charge and discharge current, charge and discharge voltage and temperature; the third data acquisition unit collects data information of the charging device through a third sensor network, and the data information at least includes charging power, charging time, charging current and working status of the charging device; the first sensor network, the second sensor network and the third sensor network adopt a mesh network topology, and form the sensor network model through a star network topology.

[0015] In a specific embodiment, the sensor network model fuses the data collected by the first data acquisition unit, the second data acquisition unit and the third data acquisition unit to provide data support for the energy control algorithm. The nodes in the mesh network topology are connected to each other through a transmission path, and each node is connected to at least two other nodes; since there are many paths between the nodes, local failures will not affect the entire network, and there are multiple communication channels between the nodes, and the information transmission can select the best path to minimize the delay; any node in the star network topology is only connected to the central node, so the media access control method is simple, resulting in a very simple access protocol, which is easy to monitor and manage the network; the central node can isolate the connection lines one by one for fault detection and positioning, and the failure of a single connection point only affects one device and will not affect the entire network; the central node provides services and network reconfiguration to each site. In the present invention, the input sample of the model construction unit is: The optimal problem of the classification hyperplane in the classification unit is expressed as: Select kernel function And penalty parameter A, construct and solve the optimization problem: Solve to get the optimal solution ,choose A positive component of less than A The final solution decision function is: . In a specific embodiment, the original expression of the optimal problem of the classification hyperplane in the classification unit is: The original expression for solving the optimization problem is: The original expression of the final decision function is: .

[0016] In a specific embodiment, the input data is used to train the improved support vector machine to solve the optimal weight vector m, bias terms a and b, and the kernel function Used to calculate the similarity between data points, so as to find the best classification hyperplane; when the improved support vector machine is trained, predict the category of new data points; use energy demand as a label and use the relevant feature vector to train the improved support vector machine; formulate an energy allocation strategy based on the predicted energy demand. If the energy demand in a certain time period is predicted to be high, the energy supply is adjusted in advance to increase the power generation or adjust the grid scheduling to meet the demand. If the energy demand is predicted to be low, the energy supply can be reduced accordingly to save costs. Adjustments are made based on real-time prediction results to achieve more efficient and sustainable energy management. In a specific embodiment, the improved support vector machine solves the machine learning problem in the case of large samples and simplifies the usual classification and regression problems; because the kernel function method overcomes the dimensionality disaster and nonlinear separability problems, the computational complexity is not increased when mapping to high-dimensional space. Since the final decision function of the support vector calculation method is determined by only a few support vectors, the computational complexity depends on the number of support vectors, not the dimension of the sample space. The support vector machine algorithm uses slack variables to allow some points to have distances from the classification plane that do not meet the original requirements, thereby avoiding the influence of these points on model learning.

[0017] In a specific embodiment, the workflow of the improved support vector machine is: The data preprocessing unit is responsible for collecting and organizing data information from the sensor network model; cleaning the collected data, removing outliers and noise, ensuring the accuracy and reliability of the data, and standardizing or normalizing the data to improve the efficiency of subsequent data analysis; Extract key features related to energy demand forecasting and energy allocation optimization from the preprocessed data. The features include at least photovoltaic power generation, energy storage device charge state, charging station historical load pattern, and weather forecast information. Use feature selection technology to select the features that have the greatest impact on the forecast results to improve the model's forecast accuracy. Build models for energy demand forecasting and optimizing energy distribution; The classification unit uses the classification capability of the improved support vector machine to classify energy demand into different categories for more refined energy allocation and management in the future; Use historical data to train the initially constructed improved support vector machine, and adjust the model parameters to optimize the model's prediction performance. During the training process, cross-validation can be used to evaluate the generalization ability of the model to avoid overfitting or underfitting. By training the optimization unit, an improved support vector machine prediction model with excellent performance can be obtained. Use the trained improved support vector machine to predict new data and evaluate the prediction accuracy and stability of the model; compare the prediction results with the actual situation, analyze the source of model errors and possible improvement directions; formulate energy allocation strategies based on the prediction results to optimize the operating efficiency of the integrated photovoltaic storage and charging station.

[0018] In a specific embodiment, the influence of different penalty parameters on the charging pile is shown in Table 1. It can be seen from Table 1 that when the value of the penalty coefficient is 10.001, the energy utilization rate is the highest and the charging efficiency reaches the highest.

[0019] In the present invention, the improved support vector machine classification process is that SVM1 is used as the root node of the binary tree to determine the test samples of the first category of data, and the samples that do not belong to the first category are classified by SVM2 until SVM The qth class of samples is decided. In a specific embodiment, the improved support vector machine is a support vector machine with a decision tree algorithm added to the original one; the decision tree algorithm includes a root node, several internal nodes and several leaf nodes, the leaf node corresponds to the decision result, and each other node corresponds to an attribute test. The sample set contained in each node is divided into child nodes according to the result of the attribute test. The root node contains the full set of samples, and the path from the root node to each leaf node corresponds to a determined test sequence. The purpose of learning the decision tree algorithm is to produce a tree with strong generalization ability; the process of making decisions using the decision tree algorithm is to start from the root node, test the corresponding feature attributes in the item to be classified, and select the output branch according to its value until the leaf node is reached, and the category stored in the leaf node is used as the decision result. The pruning of the decision tree algorithm is to prevent or reduce the occurrence of overfitting. The specific method of pruning is to remove leaf nodes that are too subdivided, make them fall back to the parent node, and change the parent node to a new leaf node; pruning includes pre-pruning and post-pruning. The pre-pruning is performed when the decision tree is constructed. The nodes are evaluated during the decision tree construction process. If the division of the node does not improve the accuracy in the verification set, then the node should not be divided further. At this time, the current node will be used as a leaf node; the post-pruning is performed after the decision tree is generated. It usually starts from the leaf node of the decision tree and evaluates each node layer by layer. If pruning the node does not make much difference or significantly improves the accuracy in the verification set, it can be pruned and replaced by a leaf node.

[0020] In the present invention, the model predictive control includes a prediction unit, an optimization unit, a control unit, a feedback adjustment unit and a human-computer interaction unit; the signal output end of the prediction unit is connected to the signal input end of the optimization unit, the signal output end of the optimization unit is connected to the signal input end of the control unit, the signal output end of the control unit is connected to the signal input end of the feedback adjustment unit, and the signal output end of the control unit is connected to the signal input end of the human-computer interaction unit; the prediction unit performs long-term and short-term predictions for the future based on real-time collected data, the long-term prediction time is 1 to 7 days, and the short-term prediction time is 0.5 to 24 hours. The prediction results include photovoltaic power generation, changes in the amount of power in the energy storage battery, and the load demand of the charging pile; the optimization unit formulates the optimal charging and discharging strategy based on the prediction data; the control unit selects the first element from the optimal control sequence obtained by optimization as the current control input, and applies it to the model, and adjusts the output of the photovoltaic power generation system, the charging and discharging power of the energy storage system, and the load distribution of the charging pile according to the current control input; the feedback adjustment unit re-monitors the system status at the beginning of the next control cycle, collects new data, and performs a new round of prediction and optimization; the human-computer interaction unit monitors the operating status, views the prediction results and optimization strategy through the display screen and keyboard. In a specific embodiment, the workflow of the model predictive control is as follows: The prediction unit collects real-time data of the photovoltaic storage and charging integrated charging station, which at least includes photovoltaic power generation, charging and discharging status of the energy storage system, charging demand of the charging pile and load status of the power grid; The optimization unit formulates the optimal charging and discharging strategy based on the prediction results provided by the prediction unit. Taking into account the volatility of photovoltaic power generation, the capacity limitation of the energy storage system, the charging efficiency of the charging piles, and the load balance of the power grid, the optimal charging and discharging strategy is solved through the improved support vector machine and model predictive control to maximize energy utilization and minimize costs. Receive the optimal charging and discharging strategy provided by the optimization unit, convert the strategy into control instructions for the photovoltaic power generation device, energy storage device and charging device, monitor the operating status of the system in real time, and ensure the accurate execution of the control instructions; Make necessary adjustments to the control strategy based on the difference between the actual operating status and the predicted results; feed back the adjusted strategy to the optimization unit and control unit to achieve continuous optimization and control of the system; The human-computer interaction unit displays the real-time status information of the system, such as photovoltaic power generation, charging and discharging status of the energy storage system, and charging status of the charging pile, receives control instructions or parameter settings input by the user, and provides a user-friendly interface and interaction method to facilitate users to monitor and manage the operation of the system.

[0021] In the present invention, the control unit controls the energy flow of the photovoltaic power generation device, the energy storage device and the charging device; The conditions that the energy scheduling of the photovoltaic power generation device satisfies are: is the total charging power of the energy storage device; when the photovoltaic power generation power of the photovoltaic power generation device is greater than the total demand of the charging device and the energy storage device, the remaining electric energy is stored in the energy storage device or connected to the grid; when the photovoltaic power generation power of the photovoltaic power generation device is insufficient, the electric energy of the energy storage device is used to power the charging device, and the insufficient part is supplemented by the power grid; the charging device is intelligently dispatched according to the charging demand of the electric vehicle and the energy state of the current system, and the electric energy of the photovoltaic power generation and energy storage devices is used to charge the electric vehicle.

[0022] In a specific embodiment, the impact of the energy scheduling algorithm on the integrated photovoltaic storage and charging pile is shown in Table 2. It can be seen from Table 2 that the integrated photovoltaic storage and charging pile optimized by the energy scheduling algorithm greatly improves the energy utilization and charging efficiency.

[0023] In the present invention, the energy flow is that the photovoltaic power generation device converts sunlight into electrical energy, the generated direct current is sent to the photovoltaic inverter, the photovoltaic inverter converts direct current into alternating current, the converted alternating current is sent to the AC bus, the electrical energy is transmitted to the power grid through the transformer, and the power grid and the AC bus are transmitted bidirectionally; the electrical energy is transmitted to the energy storage device through the energy storage inverter, the AC bus and the energy storage inverter are transmitted bidirectionally, and the energy storage inverter and the energy storage device are transmitted bidirectionally; the electrical energy directly powers the charging pile.

[0024] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that these specific embodiments are only illustrative, and those skilled in the art may omit, replace, and change the details of the above methods and systems in various ways without departing from the principles and essence of the present invention. For example, merging the above method steps so as to perform substantially the same functions in substantially the same manner to achieve substantially the same results is within the scope of the present invention. Therefore, the scope of the present invention is limited only by the appended claims.

Claims

1. A photovoltaic storage and charging integrated charging station management system based on energy control algorithm, characterized by: Include: Photovoltaic power generation devices, which convert solar energy into electrical energy through photovoltaic panels; An energy storage device stores the electric energy generated by the photovoltaic power generation device or the electric energy of the power grid, and manages the charging and discharging process of the energy storage device through a battery management system BMS; A charging device, providing charging services for electric vehicles; the charging device includes a DC charging terminal and an AC charging terminal; An energy management model, which realizes coordinated control of the photovoltaic power generation device, the energy storage device and the charging device through an energy control algorithm; the energy management model includes a data acquisition module, a data analysis module, an energy control module and an energy scheduling execution module; the energy control algorithm includes an improved support vector machine and model predictive control; The data acquisition module collects the operation data information of the device in real time through the sensor network model, and the operation data information at least includes current, voltage, power and the operation status of the device; The data analysis module performs data analysis through an improved support vector machine, predicts energy demand, and optimizes energy distribution; the improved support vector machine includes a data preprocessing unit, a feature selection and extraction unit, a model construction unit, a classification unit, a training optimization unit, and a prediction and evaluation unit; the signal output end of the data preprocessing unit is connected to the signal input end of the feature selection and extraction unit, the signal output end of the feature selection and extraction unit is connected to the signal input end of the model construction unit, the signal output end of the model construction unit is connected to the signal input end of the classification unit, the signal output end of the classification unit is connected to the signal input end of the training optimization unit, and the signal output end of the training optimization unit is connected to the signal input end of the prediction and evaluation unit; The energy control module performs secondary prediction of the data analysis results in real time through model predictive control according to the analysis results of the data analysis module, and formulates an optimal charging and discharging strategy according to the prediction results; The energy scheduling execution module executes the energy scheduling task according to the strategy formulated by the energy control module; The photovoltaic power generation device is bidirectionally connected to the energy management model, the energy storage device is bidirectionally connected to the energy management model, the charging device is bidirectionally connected to the energy management model, the signal output end of the data acquisition module is connected to the signal input end of the data analysis, the signal output end of the data analysis module is connected to the signal input end of the energy control module, and the signal output end of the energy control module is connected to the signal input end of the energy scheduling execution module.

2. According to claim 1, a photovoltaic storage and charging integrated charging station management system based on energy control algorithm is characterized by: The data acquisition module includes a first data acquisition unit, a second data acquisition unit and a third data acquisition unit; the first data acquisition unit collects data information of the photovoltaic power generation device through a first sensor network, and the data information at least includes photovoltaic power generation power, power generation, photovoltaic panel temperature and light intensity; the first sensor network at least includes a voltage sensor, a current sensor, a temperature sensor and a photoresistor; the second data acquisition unit collects data information of the energy storage device through a second sensor network, and the data information at least includes charge state, charge and discharge current, charge and discharge voltage and temperature; the third data acquisition unit collects data information of the charging device through a third sensor network, and the data information at least includes charging power, charging time, charging current and working status of the charging device; the first sensor network, the second sensor network and the third sensor network adopt a mesh network topology structure, and the sensor network model is formed by a star network topology structure.

3. According to claim 1, a photovoltaic storage and charging integrated charging station management system based on energy control algorithm is characterized by: The input samples of the model building unit are: The optimal problem of the classification hyperplane in the classification unit is expressed as: In formula (3), is the Lagrange multiplier, is the optimal objective function; In formula (4), For the best decision.

4. According to claim 1, a photovoltaic storage and charging integrated charging station management system based on energy control algorithm is characterized by: The improved support vector machine classification process is that SVM1 is used as the root node of the binary tree to determine the test samples of the first category of data, and the samples that do not belong to the first category are classified by SVM2 until SVM Decision is made on the qth class of samples.

5. According to claim 1, a photovoltaic storage and charging integrated charging station management system based on energy control algorithm is characterized in that: The model predictive control includes a prediction unit, an optimization unit, a control unit, a feedback adjustment unit and a human-computer interaction unit; the signal output end of the prediction unit is connected to the signal input end of the optimization unit, the signal output end of the optimization unit is connected to the signal input end of the control unit, the signal output end of the control unit is connected to the signal input end of the feedback adjustment unit, and the signal output end of the control unit is connected to the signal input end of the human-computer interaction unit; the prediction unit performs long-term and short-term predictions for the future based on real-time collected data, the long-term prediction time is 1 to 7 days, the short-term prediction time is 0.5 to 24 hours, and the prediction results are The results include photovoltaic power generation, power changes of energy storage batteries, and load requirements of charging piles; the optimization unit formulates an optimal charging and discharging strategy based on the predicted data; the control unit selects the first element as the current control input from the optimal control sequence obtained by optimization, and applies it to the model, and adjusts the output of the photovoltaic power generation system, the charging and discharging power of the energy storage system, and the load distribution of the charging pile according to the current control input; the feedback adjustment unit re-monitors the system status at the beginning of the next control cycle, collects new data, and performs a new round of prediction and optimization; the human-computer interaction unit monitors the operating status, views the prediction results and optimization strategy through the display screen and keyboard.

6. The photovoltaic storage and charging integrated charging station management system based on energy control algorithm according to claim 1 is characterized by: The control unit controls the energy flow of the photovoltaic power generation device, the energy storage device and the charging device; The conditions that the energy scheduling of the photovoltaic power generation device satisfies are: is the total charging power of the energy storage device; when the photovoltaic power generation power of the photovoltaic power generation device is greater than the total demand of the charging device and the energy storage device, the remaining electric energy is stored in the energy storage device or connected to the grid; when the photovoltaic power generation power of the photovoltaic power generation device is insufficient, the electric energy of the energy storage device is used to power the charging device, and the insufficient part is supplemented by the power grid; the charging device is intelligently dispatched according to the charging demand of the electric vehicle and the energy state of the current system, and the electric energy of the photovoltaic power generation and energy storage devices is used to charge the electric vehicle.

7. The photovoltaic storage and charging integrated charging station management system based on energy control algorithm according to claim 6 is characterized by: The energy flow is that the photovoltaic power generation device converts sunlight into electrical energy, and the generated direct current is sent to the photovoltaic inverter. The photovoltaic inverter converts direct current into alternating current, and the converted alternating current is sent to the AC bus. The electrical energy is transmitted to the power grid through the transformer, and the power grid and the AC bus are transmitted bidirectionally; the electrical energy is transmitted to the energy storage device through the energy storage inverter, and the AC bus and the energy storage inverter are transmitted bidirectionally, and the energy storage inverter and the energy storage device are transmitted bidirectionally; the electrical energy directly powers the charging pile.

Images