Power distribution network safety assessment method and system based on optical storage and charging system

Abstract

The invention relates to the technical field of power system engineering, in particular to a power distribution network safety assessment method and system based on an optical storage and charging system, and the method comprises the steps: collecting three types of key data of the optical storage and charging system; based on the three types of key data, establishing a power generation prediction model, constructing an energy storage scheduling strategy, and generating a load characteristic curve; calculating a node voltage deviation value and a branch power loss value of the power distribution network to form a network state evaluation index; performing comparative analysis on the network state evaluation index and a preset safety threshold value, and when the node voltage deviation value or the branch power loss value exceeds the preset safety threshold value, marking an abnormal node position; and for the abnormal nodes, adjusting the charging and discharging power of the energy storage system and the operation mode of the charging facility, and outputting optimized operation parameters of the optical storage and charging system. Through cooperative operation of the photovoltaic power generation system, the energy storage system and the charging facility, accurate evaluation and dynamic regulation and control of the node voltage and the line power loss of the power distribution network are realized, and the operation safety and the energy complementation efficiency of the power distribution network are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system engineering, and in particular to a distribution network security assessment method and system based on a photovoltaic storage and charging system. Background Art

[0002] The current distribution network is facing severe challenges such as the access of new energy, complex load characteristics and uncertainty in system operation. Traditional distribution network security assessment methods mainly rely on experience judgment and static analysis, which is difficult to cope with the dynamic characteristics of diversified energy systems such as photovoltaic power generation, energy storage systems and electric vehicle charging, and cannot effectively identify potential safety risks and performance bottlenecks.

[0003] At the same time, with the rapid development of distributed energy, the distribution network system has become highly nonlinear, variable and random. The traditional single evaluation indicators and static thresholds can no longer meet the actual needs of safe operation of modern power systems. It is urgent to build a new dynamic safety assessment method based on big data and artificial intelligence. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to achieve accurate evaluation and dynamic regulation of distribution network node voltage and line power loss through the coordinated operation of photovoltaic power generation, energy storage system and charging facilities, so as to improve the operation safety and energy complementarity efficiency of the distribution network.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a distribution network security assessment method based on a photovoltaic storage and charging system, which includes collecting three types of key data of the photovoltaic storage and charging system, the three types of key data including photovoltaic power generation data, energy storage system capacity data and charging facility load data;

[0008] Establish a power generation prediction model based on photovoltaic power data, build an energy storage dispatch strategy based on energy storage system capacity data, and generate a load characteristic curve based on charging facility load data;

[0009] Based on the power generation prediction model, energy storage scheduling strategy and load characteristic curve, the voltage deviation value of the distribution network node and the power loss value of the branch are calculated to form the network status evaluation index;

[0010] Compare and analyze the network status evaluation index with the preset safety threshold. When the node voltage deviation value or branch power loss value exceeds the preset safety threshold, mark the abnormal node position;

[0011] For abnormal nodes, the charging and discharging power of the energy storage system and the operation mode of the charging facilities are adjusted, and the optimized operating parameters of the solar storage and charging system are output.

[0012] As a preferred solution of the distribution network safety assessment method based on the photovoltaic storage and charging system described in the present invention, the following steps are included in the establishment of a power generation prediction model based on photovoltaic power generation data:

[0013] A power generation prediction model is established based on photovoltaic power generation data, and the power generation prediction model is trained through a deep learning algorithm to obtain a photovoltaic power generation prediction curve;

[0014] Establish a dynamic response model for the energy storage system, calculate the upper and lower limits of the charge and discharge power based on the capacity data of the energy storage system, and formulate a time-divided energy storage scheduling strategy based on the battery state of charge and cycle life characteristics. The time-divided energy storage scheduling strategy includes peak-valley filling mode, spare capacity mode and economic optimization mode;

[0015] Perform cluster analysis on charging facility load data, extract charging period distribution characteristics and charging power variation patterns, establish a multi-time scale charging load prediction model, and generate a charging load characteristic curve;

[0016] Match the photovoltaic power prediction curve, energy storage scheduling strategy, and charging load characteristic curve in time series to establish a system operation characteristic database;

[0017] A data update mechanism is set up for the system operation characteristics database to continuously optimize the power generation prediction model parameters based on actual operation data.

[0018] As a preferred solution of the distribution network security assessment method based on the photovoltaic storage and charging system described in the present invention, forming the network status assessment index includes the following steps:

[0019] The power flow calculation model is used to process the photovoltaic power data output by the power generation prediction model. Combined with the energy storage power data provided by the energy storage scheduling strategy and the power load data given by the charging load characteristic curve, a power injection distribution diagram of the distribution network nodes is established. The power injection distribution diagram reflects the power balance status of each node.

[0020] Based on the node injection power distribution diagram, the node voltage sensitivity matrix is ​​established using the network topology analysis method. The node voltage sensitivity matrix describes the impact of power changes on node voltage, and the voltage deviation value of each node is calculated through a recursive algorithm.

[0021] Using branch impedance parameters and line transmission equations, a power loss calculation model for the distribution network is established to obtain the power loss value of each branch.

[0022] The node voltage deviation values ​​are weighted and normalized to form a voltage assessment index, where the weight coefficient is determined based on the node importance, user type, and load level;

[0023] Extract features of branch power loss values, calculate loss rate, loss distribution, and loss change trend, and establish loss assessment indicators based on branch importance;

[0024] The loss assessment index and the voltage assessment index together constitute the network status assessment index system.

[0025] As a preferred solution of the distribution network security assessment method based on the solar storage and charging system described in the present invention, the comparative analysis of the network status assessment index with the preset safety threshold includes the following steps:

[0026] Formulate node voltage deviation thresholds and branch power loss thresholds based on historical operating data and power system safety operation standards;

[0027] The voltage deviation assessment coefficient and power loss assessment coefficient of each monitoring point are calculated through an adaptive assessment algorithm to establish a network status assessment matrix;

[0028] The voltage deviation value of each node and the power loss value of each branch in the network status assessment matrix are compared with the corresponding preset safety thresholds. When the deviation value exceeds the first deviation threshold, the warning state is entered, and when it exceeds the second deviation threshold, the alarm state is triggered;

[0029] Mark the location of abnormal nodes based on the graph topology analysis method and establish a model of the impact range of abnormal nodes;

[0030] Abnormal nodes are graded according to their impact and an abnormal node level assessment report is generated.

[0031] As a preferred solution of the distribution network safety assessment method based on the photovoltaic storage and charging system described in the present invention, adjusting the charging and discharging power of the energy storage system and the operation mode of the charging facilities includes the following steps:

[0032] According to the abnormal node level assessment report, the distribution information of energy storage systems and charging facilities around the abnormal nodes is extracted to establish a local network response model;

[0033] The optimal charging and discharging power of the energy storage system is calculated based on the local network response model. The optimal charging and discharging power is obtained by taking into account the energy storage capacity constraint, charging and discharging efficiency, and state of charge limit, and a multi-objective optimization algorithm is used to obtain the power regulation instruction of the energy storage system.

[0034] Dynamically adjust the operation mode of charging facilities to form a coordinated control plan for charging facilities;

[0035] Coordinated optimization of the power regulation instructions of the energy storage system and the coordinated control scheme of the charging facilities to generate the operating parameters of each device in the photovoltaic storage and charging system;

[0036] Establish an optimization parameter execution feedback mechanism to monitor the recovery of abnormal node status and trigger emergency control strategies when node indicators continue to exceed the limit.

[0037] As a preferred solution of the distribution network safety assessment method based on the photovoltaic storage and charging system described in the present invention, wherein: the node voltage deviation threshold is set according to the voltage level;

[0038] The branch power loss threshold is determined based on the line capacity;

[0039] The abnormal node impact range model considers the network topology, electrical distance and load importance;

[0040] The level assessment report includes the anomaly type, impact scope, severity, and handling priority.

[0041] As a preferred solution of the distribution network security assessment method based on the photovoltaic storage and charging system described in the present invention, the local network response model includes the energy storage power regulation amount, the charging power regulation amount and the node voltage recovery characteristics;

[0042] Adjustments include charging power limits, charging sequence optimization, and time-divided charging strategies;

[0043] Operational parameters include energy storage charging and discharging power curves, charging facility load distribution plans, and photovoltaic power regulation strategies;

[0044] Emergency control strategies include emergency discharge of energy storage systems and power-limited operation of charging facilities.

[0045] In a second aspect, an embodiment of the present invention provides a distribution network security assessment system based on a photovoltaic storage and charging system, which includes a data acquisition module for collecting three types of key data of the photovoltaic storage and charging system;

[0046] The prediction and analysis module is used to establish a power generation prediction model based on photovoltaic power data, build an energy storage scheduling strategy based on energy storage system capacity data, and generate a load characteristic curve based on charging facility load data;

[0047] The network status assessment module is used to calculate the voltage deviation value of the distribution network node and the power loss value of the branch circuit based on the power generation prediction model, energy storage scheduling strategy and load characteristic curve to form the network status assessment index;

[0048] The threshold comparison module is used to compare and analyze the network status evaluation index with the preset safety threshold. When the node voltage deviation value or branch power loss value exceeds the preset safety threshold, the abnormal node position is marked;

[0049] The system optimization and scheduling module is used to adjust the charging and discharging power of the energy storage system and the operation mode of the charging facilities for abnormal nodes, and output the optimized operation parameters of the solar storage and charging system.

[0050] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the distribution network security assessment method based on the photovoltaic storage and charging system as described in the first aspect of the present invention are implemented.

[0051] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the distribution network security assessment method based on the photovoltaic storage and charging system as described in the first aspect of the present invention are implemented.

[0052] The beneficial effects of the present invention are as follows: the present invention establishes a power generation prediction model and a dynamic response model by accurately collecting and analyzing key data of photovoltaic power generation, energy storage systems and charging facilities, thereby realizing accurate evaluation of voltage deviations at distribution network nodes and power losses at branches, and can dynamically adjust the charging and discharging power of the energy storage system and the operation mode of the charging facilities according to the degree of influence of abnormal nodes, thereby effectively improving the safety and reliability of distribution network operation, and has important technical value for balancing grid loads, optimizing energy structure and improving the coordinated operation of photovoltaic storage and charging systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 This is a flow chart of the distribution network security assessment method based on the photovoltaic storage and charging system;

[0055] Figure 2 Computer equipment diagram of the distribution network security assessment method based on the photovoltaic storage and charging system. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Example 1

[0060] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides a distribution network security assessment method based on a photovoltaic storage and charging system, comprising:

[0061] S1: Collect three types of key data of the solar storage and charging system.

[0062] Among them, the three types of key data include photovoltaic power generation data, energy storage system capacity data and charging facility load data.

[0063] S2: Establish a power generation prediction model based on photovoltaic power data, build an energy storage scheduling strategy through energy storage system capacity data, and generate a load characteristic curve based on charging facility load data.

[0064] Specifically, the following steps are included:

[0065] S2.1: Establish a power generation prediction model based on photovoltaic power generation data, train the power generation prediction model through a deep learning algorithm, and obtain a photovoltaic power generation prediction curve.

[0066] Specifically, based on historical photovoltaic power generation data, the long short-term memory network (LSTM) neural network is selected as the power generation prediction model. In the data preprocessing stage, data normalization is first performed to standardize input features such as photovoltaic power generation power and meteorological data (such as solar irradiance and ambient temperature). The training data set is divided into training set, validation set and test set with a ratio of 7:2:1. The LSTM network design includes two hidden layers, the number of neurons in the first layer is set to 64, the number of neurons in the second layer is set to 32, and the activation function uses the ReLU function. The Adam optimizer is used, the learning rate is set to 0.001, the batch size is 32, and the training rounds are 100 rounds. The model evaluation indicators select the root mean square error (RMSE) and the mean absolute percentage error (MAPE). When the RMSE is less than 0.05 and the MAPE is less than 10%, the model is considered to have good prediction performance.

[0067] S2.2: Establish a dynamic response model for the energy storage system, calculate the upper and lower limits of the charging and discharging power based on the capacity data of the energy storage system, and formulate a time-based energy storage scheduling strategy based on the battery state of charge and cycle life characteristics.

[0068] Among them, the time-based energy storage scheduling strategies include peak-valley filling mode, backup capacity mode and economic optimization mode.

[0069] S2.3: Perform cluster analysis on the charging facility load data, extract the distribution characteristics of the charging period and the changing rules of the charging power, establish a multi-time scale charging load prediction model, and generate a charging load characteristic curve.

[0070] Specifically, the K-means clustering algorithm is used to classify the charging facility load data. First, the original data is preprocessed, including outlier processing and data normalization. Clustering features select charging power, charging time, charging frequency, etc. The number of clusters K is determined by the silhouette coefficient method, and 3-5 clusters are selected after verification. When constructing a multi-time scale prediction model, the features of the three scales of hours, days, and weeks are used, and an integrated learning method is used to combine the random forest and gradient boosting decision tree (GBDT) algorithms to establish an integrated prediction model. During the model training process, the cross-validation method is used to verify the generalization ability of the model, and the prediction accuracy is not less than 85%.

[0071] S2.4: Time-series match the photovoltaic power generation prediction curve, energy storage scheduling strategy, and charging load characteristic curve to establish a system operation characteristic database.

[0072] S2.5: Set up a data update mechanism for the system operation characteristics database and continuously optimize the power generation prediction model parameters based on actual operation data.

[0073] S3: Based on the power generation prediction model, energy storage scheduling strategy and load characteristic curve, the voltage deviation value of the distribution network node and the power loss value of the branch are calculated to form the network status evaluation index.

[0074] Specifically, the following steps are included:

[0075] S3.1: Use the power flow calculation model to process the photovoltaic power data output by the power generation prediction model, combine the energy storage power data provided by the energy storage scheduling strategy and the power load data given by the charging load characteristic curve, and establish the power injection distribution diagram of the distribution network nodes.

[0076] Specifically, the injection power distribution diagram reflects the power balance state of each node. The construction process is as follows: The injection power distribution diagram construction process is based on the node current balance principle. First, the photovoltaic power generation power, energy storage system power, and charging load power are decomposed according to the node topology relationship. For each node, the injection current size and direction are calculated to establish a node injection current matrix. The symmetrical component method is used to handle unbalanced loads to ensure accurate matching of positive, negative, and zero-sequence currents. The node power balance criterion is that the algebraic sum of the injected current is close to zero, and the allowable error range does not exceed ±1%.

[0077] S3.2: Based on the node injection power distribution diagram, the node voltage sensitivity matrix is ​​established using the network topology analysis method, and the voltage deviation value of each node is calculated through a recursive algorithm.

[0078] Specifically, the node voltage sensitivity matrix describes the degree of influence of power change on node voltage, and the establishment process is as follows: The node voltage sensitivity matrix is ​​constructed using a linearization method. First, the node admittance matrix and the node voltage vector are established. By making a small perturbation to the node power, the voltage change response is calculated and the sensitivity coefficient matrix is ​​constructed. The sensitivity coefficient is defined as the ratio of the node voltage change to the power change. The recursive algorithm selects the improved Gauss-Seidel iteration method, the iteration convergence accuracy is set to 10^-5, and the maximum number of iterations is 100 times.

[0079] S3.3: Using branch impedance parameters and line transmission equations, a distribution network power loss calculation model is established to obtain the power loss value of each branch.

[0080] S3.4: Perform weighted processing on the node voltage deviation values, and normalize the weighted node voltage deviation values ​​to form a voltage evaluation index.

[0081] Among them, the weight coefficient is determined based on node importance, user type and load level.

[0082] S3.5: Extract features of branch power loss values, calculate loss rate, loss distribution, and loss change trend, and establish loss assessment indicators based on branch importance.

[0083] Furthermore, the loss assessment index and the voltage assessment index together constitute a network status assessment index system.

[0084] S4: Compare and analyze the network status evaluation index with the preset safety threshold. When the node voltage deviation value or branch power loss value exceeds the preset safety threshold, mark the abnormal node position.

[0085] Specifically, the following steps are included:

[0086] S4.1: Based on historical operating data and power system safety operation standards, establish node voltage deviation thresholds and branch power loss thresholds.

[0087] Among them, the node voltage deviation threshold is set according to the voltage level; the branch power loss threshold is determined based on the line capacity.

[0088] S4.2: Calculate the voltage deviation assessment coefficient and power loss assessment coefficient of each monitoring point through an adaptive assessment algorithm, and establish a network status assessment matrix.

[0089] Specifically, the adaptive evaluation algorithm is based on the fuzzy comprehensive evaluation method. First, the evaluation factor weight matrix is ​​constructed, including indicators such as voltage deviation, power loss, and load importance. The entropy weight method is used to determine the weight of each factor, and the weight coefficient is calculated by information entropy. In the process of constructing the evaluation matrix, the fuzzy membership function is introduced to convert the quantitative indicators into fuzzy membership values. Finally, the comprehensive evaluation score is obtained by weighted summation, with a score range of 0-100. The higher the score, the more serious the network status.

[0090] S4.3: Compare the voltage deviation value of each node and the branch power loss value in the network status assessment matrix with the corresponding preset safety threshold. When the deviation value exceeds the first deviation threshold, it enters the warning state, and when it exceeds the second deviation threshold, it triggers the alarm state.

[0091] Among them, for low voltage (0.4kV), medium voltage (10kV) and high voltage (35kV) distribution networks, the first deviation thresholds are ±5%, ±3% and ±2% respectively; the second deviation thresholds are ±8%, ±5% and ±3% respectively. The first threshold of branch power loss does not exceed 5% of the rated capacity of the line, and the second threshold does not exceed 8%. The threshold is determined by the time-weighted accumulation method, and it can be determined as an abnormal state only when the threshold is exceeded for 15 consecutive minutes.

[0092] S4.4: Mark the locations of abnormal nodes based on the graph topology analysis method and establish a model of the impact range of abnormal nodes.

[0093] Specifically, the abnormal node impact range model considers the network topology, electrical distance and load importance.

[0094] S4.5: Classify abnormal nodes according to their impact and generate an abnormal node level assessment report.

[0095] Among them, the level assessment report includes the type of anomaly, scope of impact, severity and processing priority.

[0096] S5: For abnormal nodes, adjust the charging and discharging power of the energy storage system and the operation mode of the charging facilities, and output the optimized operation parameters of the solar energy storage and charging system.

[0097] Specifically, the following steps are included:

[0098] S5.1: Based on the abnormal node level assessment report, extract the energy storage system distribution information and charging facility distribution information around the abnormal node and establish a local network response model.

[0099] Among them, the local network response model includes energy storage power regulation, charging power regulation and node voltage recovery characteristics. The construction of the local network response model considers the multi-dimensional decoupling method. The energy storage power regulation is calculated by a predictive control algorithm, taking into account constraints such as battery state of charge, charging and discharging efficiency, and system stability. The charging power regulation is based on load forecasting and grid load characteristics, and adopts a time-division dynamic regulation strategy. The node voltage recovery characteristic model introduces the theory of anti-disturbance control to establish a voltage regulation closed-loop control system based on disturbance observation and compensation.

[0100] S5.2: The optimal charging and discharging power of the energy storage system is calculated based on the local network response model. The optimal charging and discharging power is obtained by considering the energy storage capacity constraints, charging and discharging efficiency, and charge state limit, and a multi-objective optimization algorithm is used to obtain the power regulation instructions of the energy storage system.

[0101] S5.3: Dynamically adjust the operation mode of charging facilities to form a coordinated control plan for charging facilities.

[0102] Among them, the adjustments include charging power limitation, charging timing optimization, and time-divided charging strategy.

[0103] S5.4: Coordinated optimization of the power regulation instructions of the energy storage system and the coordinated control scheme of the charging facilities to generate the operating parameters of each device in the photovoltaic storage and charging system.

[0104] Among them, the operating parameters include energy storage charging and discharging power curve, charging facility load distribution plan, and photovoltaic power regulation strategy.

[0105] S5.5: Establish an optimization parameter execution feedback mechanism to monitor the recovery of abnormal node status and trigger emergency control strategies when node indicators continue to exceed the limit.

[0106] Among them, emergency control strategies include emergency discharge of energy storage systems and power-limited operation of charging facilities.

[0107] Furthermore, this embodiment also provides a distribution network safety assessment system based on a photovoltaic storage and charging system, including a data acquisition module for collecting three types of key data of the photovoltaic storage and charging system; a prediction and analysis module for establishing a power generation prediction model based on photovoltaic power generation data, building an energy storage scheduling strategy through energy storage system capacity data, and generating a load characteristic curve based on charging facility load data; a network status assessment module for calculating the voltage deviation value of the distribution network node and the branch power loss value based on the power generation prediction model, energy storage scheduling strategy and load characteristic curve to form a network status assessment index; a threshold comparison module for comparing and analyzing the network status assessment index with a preset safety threshold, and marking the abnormal node position when the node voltage deviation value or the branch power loss value exceeds the preset safety threshold; a system optimization scheduling module for adjusting the charging and discharging power of the energy storage system and the operation mode of the charging facility for abnormal nodes, and outputting the optimized operation parameters of the photovoltaic storage and charging system.

[0108] In summary, the present invention establishes a power generation prediction model and a dynamic response model by accurately collecting and analyzing key data of photovoltaic power generation, energy storage systems and charging facilities, so as to achieve accurate evaluation of voltage deviations at distribution network nodes and power losses at branches, and dynamically adjust the charging and discharging power of the energy storage system and the operation mode of the charging facilities according to the degree of influence of abnormal nodes, thereby effectively improving the safety and reliability of distribution network operation, and has important technical value for balancing grid loads, optimizing energy structure and improving the coordinated operation of photovoltaic storage and charging systems.

[0109] Example 2

[0110] This embodiment also provides a computer device, which is applicable to a distribution network security assessment method based on a solar-storage-charging system, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement a distribution network security assessment method based on a solar-storage-charging system as proposed in the above embodiment.

[0111] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a distribution network security assessment method based on a solar-storage-charging system is implemented as proposed in the above embodiment.

[0112] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0113] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0114] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0115] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0116] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A distribution network security assessment method based on a solar energy storage and charging system, characterized by: include, Collect three types of key data of the photovoltaic storage and charging system, including photovoltaic power generation data, energy storage system capacity data and charging facility load data; Establishing a power generation prediction model based on the photovoltaic power generation data, building an energy storage scheduling strategy based on the energy storage system capacity data, and generating a load characteristic curve based on the charging facility load data; Based on the power generation prediction model, the energy storage scheduling strategy and the load characteristic curve, the voltage deviation value of the distribution network node and the branch power loss value are calculated to form a network status evaluation index; Compare and analyze the network status evaluation index with the preset safety threshold, and mark the abnormal node position when the node voltage deviation value or the branch power loss value exceeds the preset safety threshold; For the abnormal nodes, the charging and discharging power of the energy storage system and the operation mode of the charging facilities are adjusted, and the optimized operation parameters of the solar storage and charging system are output.

2. A distribution network security assessment method based on a solar energy storage and charging system as claimed in claim 1, characterized in that: The step of establishing a power generation prediction model according to the photovoltaic power generation data comprises the following steps: Establishing a power generation prediction model based on photovoltaic power generation data, and training the power generation prediction model through a deep learning algorithm to obtain a photovoltaic power generation prediction curve; Establish a dynamic response model for the energy storage system, calculate the upper and lower limits of the charge and discharge power based on the capacity data of the energy storage system, and formulate a time-divided energy storage scheduling strategy based on the battery state of charge and cycle life characteristics. The time-divided energy storage scheduling strategy includes a peak-valley filling mode, a spare capacity mode, and an economic optimization mode; Perform cluster analysis on charging facility load data, extract charging period distribution characteristics and charging power variation patterns, establish a multi-time scale charging load prediction model, and generate a charging load characteristic curve; Perform time-series matching on the photovoltaic power prediction curve, energy storage scheduling strategy, and charging load characteristic curve to establish a system operation characteristic database; A data update mechanism is set for the system operation characteristic database to continuously optimize the power generation prediction model parameters based on actual operation data.

3. A distribution network security assessment method based on a solar energy storage and charging system as claimed in claim 1, characterized in that: The forming of the network status evaluation index comprises the following steps: The power flow calculation model is used to process the photovoltaic power data output by the power generation prediction model. The power storage data provided by the energy storage scheduling strategy and the power load data given by the charging load characteristic curve are combined to establish the power injection distribution diagram of the distribution network nodes. Based on the node injection power distribution diagram, a node voltage sensitivity matrix is ​​established using a network topology analysis method. The node voltage sensitivity matrix describes the influence of power changes on node voltages, and the voltage deviation value of each node is calculated using a recursive algorithm. Using branch impedance parameters and line transmission equations, a power loss calculation model for the distribution network is established to obtain the power loss value of each branch. The node voltage deviation values ​​are weighted and normalized to form a voltage evaluation index, wherein the weight coefficient is determined based on the node importance, user type, and load level; Extract features of the power loss value of the branch, calculate the loss rate, loss distribution, and loss change trend, and establish a loss assessment index based on the importance of the branch; The loss assessment index and the voltage assessment index together constitute a network status assessment index system.

4. A distribution network security assessment method based on a solar-storage-charging system as claimed in claim 1, characterized in that: The comparing and analyzing the network status evaluation index with the preset security threshold comprises the following steps: Formulate node voltage deviation thresholds and branch power loss thresholds based on historical operating data and power system safety operation standards; The voltage deviation assessment coefficient and power loss assessment coefficient of each monitoring point are calculated through an adaptive assessment algorithm to establish a network status assessment matrix; Compare the voltage deviation value of each node and the branch power loss value in the network status assessment matrix with the corresponding preset safety threshold, and enter the early warning state when the deviation value exceeds the first deviation threshold, and trigger the alarm state when it exceeds the second deviation threshold; Mark the location of abnormal nodes based on the graph topology analysis method and establish a model of the impact range of abnormal nodes; The abnormal nodes are graded according to their impact levels, and an abnormal node grade assessment report is generated.

5. A distribution network security assessment method based on a solar-storage-charging system as claimed in claim 1, characterized in that: The adjustment of the energy storage system charging and discharging power and the charging facility operation mode comprises the following steps: According to the abnormal node level assessment report, the distribution information of energy storage systems and charging facilities around the abnormal nodes is extracted to establish a local network response model; Calculate the optimal charging and discharging power of the energy storage system based on the local network response model, wherein the optimal charging and discharging power is obtained by taking into account the energy storage capacity constraint, charging and discharging efficiency, and state of charge limit, and adopting a multi-objective optimization algorithm to obtain the power regulation instruction of the energy storage system; Dynamically adjust the operation mode of charging facilities to form a coordinated control plan for charging facilities; Coordinated optimization of the energy storage system power regulation instructions and the charging facility coordination control scheme to generate operating parameters of each device in the solar energy storage and charging system; Establish an optimization parameter execution feedback mechanism to monitor the recovery of abnormal node status and trigger emergency control strategies when node indicators continue to exceed the limit.

6. A distribution network security assessment method based on a solar energy storage and charging system as claimed in claim 4, characterized in that: The node voltage deviation threshold is set according to the voltage level; The branch power loss threshold is determined based on the line capacity; The abnormal node impact range model considers network topology, electrical distance and load importance; The level assessment report includes the anomaly type, impact scope, severity, and processing priority.

7. A distribution network security assessment method based on a solar energy storage and charging system as claimed in claim 5, characterized in that: The local network response model includes energy storage power regulation, charging power regulation and node voltage recovery characteristics; The adjustment includes charging power limitation, charging timing optimization, and time-divided charging strategy; The operating parameters include energy storage charging and discharging power curves, charging facility load distribution plans, and photovoltaic power regulation strategies; The emergency control strategy includes emergency discharge of the energy storage system and power-limited operation of the charging facilities.

8. A distribution network security assessment system based on a photovoltaic storage and charging system, based on the distribution network security assessment method based on a photovoltaic storage and charging system according to any one of claims 1 to 7, characterized in that: Also includes, Data collection module, used to collect three types of key data of the solar storage and charging system; A prediction and analysis module, used to establish a power generation prediction model based on the photovoltaic power generation data, build an energy storage scheduling strategy through the energy storage system capacity data, and generate a load characteristic curve based on the charging facility load data; A network status evaluation module, used to calculate the voltage deviation value of the distribution network node and the power loss value of the branch circuit based on the power generation prediction model, the energy storage scheduling strategy and the load characteristic curve, so as to form a network status evaluation index; A threshold comparison module is used to compare and analyze the network status evaluation index with a preset safety threshold, and mark the abnormal node position when the node voltage deviation value or the branch power loss value exceeds the preset safety threshold; The system optimization and scheduling module is used to adjust the charging and discharging power of the energy storage system and the operation mode of the charging facilities for the abnormal nodes, and output the optimized operation parameters of the solar energy storage and charging system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the distribution network security assessment method based on the solar-storage-charging system according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the distribution network security assessment method based on a solar-storage-charging system according to any one of claims 1 to 7 are implemented.

Images