A wind-solar-storage-charging microgrid distribution optimization method and system

Abstract

The application discloses a kind of wind light storage fills micro-grid distribution optimization method and system, comprising: real-time acquisition each node parameter data in micro-grid;Load demand prediction model is constructed, and according to weather type automatically adjusts the scheduling weight coefficient of wind light storage filling equipment;Based on model output result, establish the matching relationship of line impedance and load urgency, and generate power supply path set, create power path selection mechanism based on dynamic programming algorithm;Based on the equivalent resistance parameter of power supply path, calculate real-time charge-discharge efficiency, and dynamically adjust charge-discharge rate threshold according to prediction error;Obtain real-time monitoring load curve, calculate the similarity of load curve and historical data, match and identify potential mutation risk;According to distributed negotiation agreement, each node reaches scheduling consensus through priority broadcast mechanism.The application has the advantages that: through load prediction and dynamic scheduling, the optimal scheduling of wind light storage filling equipment, power fluctuation suppression and mutation risk identification are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to power grid optimization technology, in particular to a wind-solar-storage-charging micro-grid distribution optimization method and system. BACKGROUND

[0002] With the rapid development of renewable energy, the traditional power system is facing increasing pressure, and the wind-solar-storage-charging micro-grid as a new type of power system can effectively cope with the challenges of renewable energy volatility and intermittency. The wind-solar-storage-charging micro-grid distribution optimization method is based on the comprehensive application of wind energy, solar energy, energy storage system and charging facilities, and through reasonable layout and optimized scheduling, the energy utilization efficiency and power supply reliability of the micro-grid are improved.

[0003] The current market wind-solar-storage-charging micro-grid distribution optimization method fails to fully utilize the advantages of real-time data acquisition and intelligent prediction model, resulting in low response speed and scheduling efficiency of the system when facing complex weather changes and sudden load demand. Traditional methods usually rely on fixed scheduling strategies and lack the ability to dynamically adjust, resulting in the micro-grid being prone to overload or energy waste when wind power generation fluctuates greatly or load demand changes dramatically. In addition, some existing systems have weak ability to handle power fluctuations and grid stability, and cannot achieve fine power regulation through virtual impedance and other means, thereby affecting the overall stability and reliability of the system. In terms of risk identification, most methods only rely on historical data analysis, lack of real-time monitoring of load curve and dynamic matching of historical data similarity, so as to accurately identify mutation risks and make early warnings. SUMMARY

[0004] In order to improve the existing wind-solar-storage-charging micro-grid distribution optimization method and system, a wind-solar-storage-charging micro-grid distribution optimization method and system is provided, which realizes the optimized scheduling of wind-solar-storage equipment, power fluctuation suppression and mutation risk identification through real-time data acquisition, load prediction and dynamic scheduling, effectively improving the operation efficiency, stability and safety of the micro-grid.

[0005] To achieve the above purpose, the technical scheme adopted by the present application is:

[0006] A wind-solar-storage-charging micro-grid distribution optimization method, comprising:

[0007] Real-time acquisition of wind power generation data, solar power generation data, energy storage state data, charging load demand data and grid interaction constraint parameters of each node in the micro-grid;

[0008] Based on the collected data, the load demand is decomposed into a priority sequence in the time dimension and a power supply radius topology structure in the space dimension, a load demand prediction model is constructed, and the scheduling weight coefficient of the wind-solar-storage equipment is automatically adjusted according to the weather type;

[0009] Based on the output results of the load demand prediction model, the matching relationship between line impedance and load emergency is established, and the power path set is generated, and the power path selection mechanism based on dynamic programming algorithm is created;

[0010] Based on the equivalent resistance parameter calculation of the power supply path, the real-time charging and discharging efficiency is calculated, the charging and discharging rate threshold is dynamically adjusted according to the prediction error, and the power fluctuation is suppressed by adjusting the virtual impedance;

[0011] Based on the real-time monitoring of the power grid load data, the real-time monitoring load curve is obtained, the similarity of the load curve and the historical data is calculated, and the potential mutation risk is matched and identified;

[0012] Based on the obtained power supply path and load demand, according to the distributed negotiation protocol, each node reaches scheduling consensus through priority broadcast mechanism.

[0013] Preferably, based on the collected data, the load demand is decomposed into a time dimension priority sequence and a space dimension power supply radius topology, a load demand prediction model is constructed, and the dispatching weight coefficient of the wind-solar-storage-charging equipment is automatically adjusted according to the weather type, which specifically includes:

[0014] Obtain the type characteristics of the charging load, divide the priority according to the tolerance time of the load power supply interruption, and obtain the time dimension priority sequence;

[0015] Based on the microgrid node topology graph, Dijkstra algorithm is used to calculate the shortest electrical distance from each load point to the distributed power supply, start the energy storage compensation for the edge load, and obtain the space dimension power supply radius;

[0016] Based on the real-time acquisition of meteorological monitoring data, the weather type is divided, the basic weight coefficient is preset according to the equipment type, and the dynamic adjustment is based on the weather type;

[0017] Prevent weight mutation through step inertia link, trigger emergency mode under extreme weather, cancel smooth transition and directly switch to preset safety weight;

[0018] Based on the collected data, two-dimensional data of load demand and dynamic weight coefficient, the LSTM neural network model is trained to obtain the trained load demand prediction model.

[0019] Preferably, based on the output results of the load demand prediction model, the matching relationship between line impedance and load emergency is established, and the power supply path set is generated, and the power path selection mechanism based on dynamic programming algorithm is created, which specifically includes:

[0020] Based on the output results of the load demand prediction model, the parameters of each branch of the microgrid are collected, the line impedance matrix is constructed, and the equivalent impedance covering all possible power supply paths is calculated;

[0021] The load emergency degree index is quantified by an emergency degree comprehensive score, and emergency degree normalization processing is performed;

[0022] The micro-grid is abstracted as a weighted directed graph, the grid nodes are taken as the vertices of the directed graph, and the electrical connection lines are taken as the edges of the directed graph. An initial path is generated by a Prim algorithm, and a candidate power supply path set is output;

[0023] State variables are defined based on the current node position and the real-time state of charge of the energy storage, and a power supply recursive equation is designed;

[0024] By initializing the boundary conditions, the optimal path is solved by reverse iteration to generate a global optimal power supply path.

[0025] Preferably, the equivalent resistance parameter calculation based on the power supply path calculates the real-time charging and discharging efficiency, dynamically adjusts the charging and discharging rate threshold according to the prediction error, and realizes power fluctuation suppression through adjusting the virtual impedance, which specifically includes:

[0026] Based on the obtained global optimal power supply path, the resistance of the line, the transformer loss resistance and the contact resistance are extracted, and the total equivalent resistance is calculated;

[0027] The real-time charging and discharging efficiency is calculated by defining the comprehensive efficiency of the energy storage system, and the efficiency value is updated by synchronous phasor measurement;

[0028] Based on the prediction error value between the real-time load demand and the predicted load demand, an error adaptive adjustment rule is set, the charging and discharging rate change rate is controlled by a ramp function, and the upper limit of the charging rate and the lower limit of the discharging rate are constrained;

[0029] Based on the equivalent resistance of the power supply path, the virtual resistance, inductance and capacitance values are selected, the virtual impedance is adjusted through the feedback state data, and the power fluctuation is responded.

[0030] Preferably, based on the real-time monitoring of the grid load data, the real-time monitoring load curve is obtained, the similarity between the load curve and the historical data is calculated, and the potential mutation risk is matched and identified, which specifically includes:

[0031] Based on the real-time monitoring of the grid load data, time-frequency domain key feature extraction is performed to construct a feature vector set;

[0032] The mutation load mode in the historical data is divided and labeled with a risk label;

[0033] The similarity between the real-time grid load data and the historical data is calculated by dynamic time warping similarity, and a mutation probability distribution is obtained;

[0034] Based on the type of mutation, a hierarchical early warning is performed.

[0035] Preferably, the scheduling consensus of each node is reached through a priority broadcast mechanism according to a distributed negotiation protocol based on the obtained power supply path and load demand, and specifically comprises the following steps:

[0036] generating scheduling data of each node based on the obtained power supply path and load demand;

[0037] setting a dynamic weight based on the energy sufficiency and historical packet loss rate to obtain a node priority;

[0038] based on the obtained node priority, eliminating conflicts through an iterative negotiation process and broadcasting in descending order.

[0039] Further, a wind-solar storage micro-grid distribution optimization system is provided, comprising:

[0040] a data acquisition module: the data acquisition module is mainly used for real-time acquisition of wind-solar power generation power, energy storage state, charging load demand data and grid interaction constraint parameters of each node in the micro-grid, and provides basic data support;

[0041] a load demand prediction module: the load demand prediction module is mainly used for the acquired data, decomposes the load demand, constructs a prediction model in time and space dimensions, and dynamically adjusts the equipment scheduling weight according to the weather type;

[0042] a path selection module: the path selection module is mainly used for calculating equivalent resistance parameters based on the power supply path, adjusting the charging and discharging efficiency in real time, and realizing power fluctuation suppression through virtual impedance adjustment;

[0043] a risk identification module: the risk identification module is mainly used for matching and identifying potential mutation risks by monitoring the similarity of the load curve and the historical data in real time, and performing hierarchical early warning of the mutation type;

[0044] a scheduling consensus module: the scheduling consensus module is mainly used for reaching a scheduling consensus of each node through a priority broadcast mechanism according to a distributed negotiation protocol, and ensuring the coordination and efficiency of the micro-grid scheduling;

[0045] a processor: the processor is mainly used for the calculation process of each formula and the construction and calculation process of each model.

[0046] Compared with the prior art, the advantages of the present application are:

[0047] By collecting real-time data such as wind and light power generation, energy storage status and load demand, and combining dynamic prediction model and weather type adjustment, accurate load demand prediction and equipment scheduling can be realized to ensure the optimal utilization of wind, light, storage and charging equipment under different weather conditions. At the same time, based on dynamic programming algorithm and path selection mechanism, the optimal power supply path can be calculated, and flexible charging and discharging management can be carried out according to the equivalent resistance of power grid and load emergency degree, effectively avoiding power fluctuation. In addition, by using similarity analysis of real-time load curve and historical data, potential mutation risk can be accurately identified for timely warning, improving the safety and stability of the system. Finally, based on distributed negotiation protocol, each node reaches scheduling consensus through priority broadcast mechanism to ensure the coordinated operation of each node in microgrid, greatly improving the scheduling efficiency and fault tolerance of the system. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 The method proposed by the present application is shown in the schematic diagram.

[0049] Figure 2 The load demand prediction model construction schematic diagram proposed by the present application is shown in the schematic diagram.

[0050] Figure 3 The path selection schematic diagram proposed by the present application is shown in the schematic diagram.

[0051] Figure 4 The charging and discharging rate adjustment schematic diagram proposed by the present application is shown in the schematic diagram.

[0052] Figure 5 The potential mutation risk identification schematic diagram proposed by the present application is shown in the schematic diagram.

[0053] Figure 6 The scheduling consensus schematic diagram proposed by the present application is shown in the schematic diagram.

[0054] Figure 7 The architecture diagram of the electronic device in the present scheme is shown in the schematic diagram.

[0055] Figure 8 The structure schematic diagram of the computer readable storage medium in the present scheme is shown in the schematic diagram. DETAILED DESCRIPTION

[0056] The following description is used to disclose the present application so that those skilled in the art can implement the present application. The preferred embodiments in the following description are only as examples, and those skilled in the art can think of other obvious modifications.

[0057] A wind, light, storage and charging microgrid distribution optimization system, comprising:

[0058] Data acquisition module: the data acquisition module is mainly used for real-time acquisition of wind and light power generation, energy storage status, charging load demand data and power grid interaction constraint parameters of each node in microgrid, and provides basic data support;

[0059] Load demand prediction module: the load demand prediction module is mainly used for collected data, decomposes load demand, constructs a prediction model in time and space dimensions, and dynamically adjusts the equipment scheduling weight according to the weather type;

[0060] Path selection module: the path selection module is mainly used for calculating the equivalent resistance parameters based on the power supply path, adjusting the charging and discharging efficiency in real time, and realizing power fluctuation suppression through virtual impedance adjustment;

[0061] Risk identification module: the risk identification module is mainly used for matching and identifying potential mutation risks by monitoring the similarity of load curves and historical data in real time, and performing hierarchical early warning of mutation types;

[0062] Scheduling consensus module: the scheduling consensus module is mainly used for reaching scheduling consensus by priority broadcast mechanism through distributed negotiation protocol, to ensure the coordination and efficiency of micro-grid scheduling;

[0063] Processor: the processor is mainly used for the calculation process of each formula and the construction and calculation process of each model.

[0064] Referring to Figure 1 The wind, light and storage micro-grid distribution optimization method shown in the figure comprises:

[0065] Step 1: Real-time collection of wind and light power generation data, energy storage state data, charging load demand data and grid interaction constraint parameters of each node in the micro-grid;

[0066] Step 2: Based on the collected data, the load demand is decomposed into a priority sequence in time dimension and a power supply radius topology structure in space dimension, a load demand prediction model is constructed, and the scheduling weight coefficient of the wind, light and storage equipment is automatically adjusted according to the weather type;

[0067] Step 3: Based on the output result of the load demand prediction model, the matching relationship between line impedance and load emergency is established, the power supply path set is generated, and the power path selection mechanism based on dynamic programming algorithm is created;

[0068] Step 4: Calculate the real-time charging and discharging efficiency based on the equivalent resistance parameters of the power supply path, dynamically adjust the charging and discharging rate threshold according to the prediction error, and realize power fluctuation suppression through adjusting the virtual impedance;

[0069] Step 5: Based on the real-time monitoring of the grid load data, the real-time monitoring load curve is obtained, the similarity of the load curve and the historical data is calculated, and the potential mutation risk is matched and identified;

[0070] Step 6: Based on the obtained power supply path and load demand, according to the distributed negotiation protocol, each node reaches scheduling consensus through priority broadcast mechanism.

[0071] Referring to Figure 2 As shown, based on the collected data, the load demand is decomposed into a priority sequence in the time dimension and a power supply radius topology in the spatial dimension, a load demand prediction model is constructed, and the dispatch weight coefficient of the wind-solar-storage-charging equipment is automatically adjusted according to the weather type, which specifically includes:

[0072] Obtain the type characteristics of the charging load, divide the priority according to the tolerance time of the load power supply interruption, and obtain the time dimension priority sequence;

[0073] Based on the microgrid node topology graph, the Dijkstra algorithm is used to calculate the shortest electrical distance from each load point to the distributed power supply, and the energy storage compensation is started for the edge load to obtain the spatial dimension power supply radius;

[0074] Based on the real-time acquired meteorological monitoring data, the weather type is divided, the basic weight coefficient is preset according to the equipment type, and the dynamic adjustment is made based on the weather type;

[0075] Prevent weight mutation through inertia link, trigger emergency mode under extreme weather, cancel smooth transition and directly switch to preset safety weight;

[0076] Based on the collected data, two-dimensional data of load demand and dynamic weight coefficient, the trained load demand prediction model is obtained through the LSTM neural network model.

[0077] Specifically, according to the tolerance time of the load power supply interruption, it is divided into three levels:

[0078] Emergency type: tolerance time less than 15 minutes, including emergency facility power supply, electric vehicle instantaneous energy compensation demand;

[0079] Conventional type: tolerance time between 15 minutes and two hours, covering resident basic electricity, industrial and commercial continuous production load;

[0080] Interruptible type: tolerance time greater than two hours, such as energy storage system charging and adjustable air conditioning load;

[0081] The topology graph of the microgrid can be represented in the form of a graph, where each node represents a load point or a power supply point, and the edge represents the electrical connection. The shortest path from the load point to the power supply point is calculated by the Dijkstra algorithm. According to the shortest path, the electrical distance of each load point is calculated. If the distance of the load point is far, the energy storage system can be enabled for compensation;

[0082] According to the meteorological monitoring data, the weather type is divided, the common weather types include sunny, cloudy, rainy, storm, the basic weight coefficient is preset according to the equipment type, for example, the fast charging station and the ordinary charging station may have different sensitivity to weather conditions, based on the real-time weather data, the weight coefficient is adjusted;

[0083] To avoid the dramatic change of weights when the weather changes suddenly, a step inertia link is used to smooth the weight change, the formula is:

[0084]

[0085] Where ω i (t) is the current value of the i-th weight at time t, ω i (t+1) is the updated weight value at time t+1, α is the smoothing factor (0≤α<1), and the control history weight retention ratio is The weight adjustment amount calculated according to the new data;

[0086] When the weather condition becomes extreme, an emergency mode is automatically triggered to cancel the smooth transition and directly set the weight to the preset safety value;

[0087] LSTM (Long Short Term Memory) is used for load demand prediction to accurately predict future load and optimize power dispatch.

[0088] Referring to Figure 3 Based on the output results of the load demand prediction model, a matching relationship between line impedance and load emergency degree is established, and a power path selection mechanism based on dynamic programming algorithm is created, which specifically includes:

[0089] Based on the output results of the load demand prediction model, the parameters of each branch of the microgrid are collected, the line impedance matrix is constructed, and the equivalent impedance covering all possible power supply paths is calculated;

[0090] The load emergency degree index is quantified by the emergency degree comprehensive score, and the emergency degree is normalized;

[0091] The microgrid is abstracted as a weighted directed graph, the grid nodes are the vertices of the directed graph, and the electrical connection lines are the edges of the directed graph. The initial path is generated by Prim algorithm, and the candidate power supply path set is output;

[0092] Based on the current node position and the real-time state of charge of the energy storage, the state variable is defined, and the power supply recursive equation is designed;

[0093] By initializing the boundary conditions, the optimal path is solved by reverse iteration, and the global optimal power supply path is generated.

[0094] Specifically, the electrical parameters of each branch of the microgrid are obtained, especially the impedance of the line. Let the impedance of the i-th line be Z i The elements of the line impedance matrix Z are the impedances between each pair of adjacent nodes;

[0095] The path impedance is calculated by series and parallel rules;

[0096] The urgency of each load point is calculated based on the load type, tolerance time and other related factors, and the urgency values of all load points are normalized to be between 0 and 1;

[0097] The topology of the micro-grid is abstracted as a graph, where nodes represent various load points and power points in the grid, and edges represent electrical connection lines, and the weight of the edge is determined by the line impedance. The Prim algorithm is applied to start from the high-urgency load node, and the edge with the minimum weighted distance is preferentially selected, and the spanning tree is iteratively expanded, and the constraint conditions include node voltage deviation ΔV≤±10%, branch load rate ≤85%, and the candidate power supply path set and its characteristic parameters are output;

[0098] The optimal power supply path is solved by the reverse iteration method to ensure the maximum power supply efficiency of the micro-grid system, and the initial boundary conditions are set, i.e. the initial energy storage state and load demand at the initial time, and the optimal power supply path is calculated by reverse iteration starting from the target node. Based on the state equation and dynamic programming method, the optimal path and power supply strategy of each node are updated by iteration, and the final optimal path solving formula is:

[0099]

[0100] Where P opt (t) is the optimal power supply value at time t, N is the total number of nodes in the power supply network, min p is the minimum value of the power supply path p, Z i is the weight coefficient of node i, P i is the power supply value through node i.

[0101] Referring to Figure 4 , the real-time charging and discharging efficiency is calculated based on the equivalent resistance parameters of the power supply path, the charging and discharging rate threshold is dynamically adjusted according to the prediction error, and the power fluctuation is suppressed by adjusting the virtual impedance, which specifically includes:

[0102] Based on the obtained global optimal power supply path, the resistance of the line, the transformer loss resistance and the contact resistance are extracted, and the total equivalent resistance is calculated;

[0103] The real-time charging and discharging efficiency is calculated by defining the comprehensive efficiency of the energy storage system, and the efficiency value is updated by synchronous phasor measurement;

[0104] Based on the prediction error value between the real-time load demand and the predicted load demand, an error adaptive adjustment rule is set, the charging and discharging rate change rate is controlled by a ramp function, and the upper limit of the charging rate and the lower limit of the discharging rate are constrained;

[0105] The equivalent resistance of the power supply path selects the virtual resistance, inductance and capacitance values, adjusts the virtual impedance through the feedback state data, and responds to power fluctuations.

[0106] Specifically, the line resistance is the main impedance in the power transmission process, the transformer loss resistance is the loss generated by the transformer in the power transmission process, and the contact resistance is the resistance at the connection part of the power equipment and the power line. It is usually small, but it also needs to be considered for high-precision calculation. Assuming that the micro-grid has multiple resistance values to be considered, the total equivalent resistance can be calculated by series, parallel and other methods. According to the actual grid topology and physical model, select the appropriate calculation method;

[0107] The efficiency of the energy storage system affects the overall operation performance of the micro-grid. By measuring the charge and discharge power of the energy storage system in real time, and combining with the synchronous phasor measurement technology, the energy storage efficiency can be updated in real time;

[0108] The synchronous phasor measurement technology is used to measure the current and voltage phasor in the power grid in real time. Through the synchronous phasor, the real-time charge and discharge state and electrical parameters of the energy storage system can be obtained. The charge and discharge power of the energy storage can be calculated by the following formula:

[0109] P(t)=V(t)·I(t)·cos(φ)

[0110] Where P(t) is the charge and discharge power of the energy storage system at time t, V(t) is the voltage effective value at time t, I(t) is the current effective value at time t, and cos(φ) is the power factor. The cosine value of the phase difference φ between voltage and current;

[0111] The energy storage efficiency can be adjusted according to real-time data. For example, if the efficiency fluctuates during charging and discharging, it can be corrected according to historical data;

[0112] Load prediction error will affect the charge and discharge rate of the energy storage system. Set an adaptive adjustment rule, and the charge and discharge rate change rate is adjusted by a ramp function, the formula is:

[0113]

[0114] Where ΔP storage (t) is the charge and discharge rate change rate, k is the control factor of the ramp function, which adjusts the change of the charge and discharge rate, and ΔP(t) is the load prediction error;

[0115] In order to ensure the stability of the micro-grid, the charging rate and discharging rate need to be set upper and lower limits. These rate limits can be dynamically adjusted by adjusting the load demand error in real time;

[0116] Based on real-time grid state data (such as voltage, frequency, etc.), the virtual impedance is adjusted through feedback control, and the adjustment of the virtual impedance helps to smooth the power fluctuation. By dynamically adjusting these parameters, the response capability of the microgrid can be optimized, thereby reducing the power supply instability caused by power fluctuations.

[0117] Referring to Figure 5 As shown, based on real-time monitoring of grid load data, the real-time monitoring load curve is obtained, the similarity of the load curve and the historical data is calculated, and the potential mutation risk is matched and identified, which specifically includes:

[0118] Based on real-time monitoring of grid load data, time-frequency domain key feature extraction is performed, and a feature vector set is constructed;

[0119] The mutation load mode in the historical data is divided and a risk label is added;

[0120] The similarity between the real-time grid load data and the historical data is calculated through dynamic time warping similarity, and the mutation probability distribution is obtained;

[0121] Based on the type of mutation, a graded early warning is performed.

[0122] Specifically, the grid load data is analyzed through short-time Fourier transform, the data signal is divided into multiple short periods, and the Fourier transform of each short period is calculated;

[0123] Key information is extracted from the time-frequency analysis results, and a feature vector set is constructed. The following features can be extracted:

[0124] Spectrum features: such as power spectral density, frequency center, bandwidth;

[0125] Time domain features: such as mean, variance, kurtosis, skewness of load;

[0126] Time-frequency joint features: combination of frequency domain and time domain features, for example, instantaneous change of frequency domain features;

[0127] According to the historical load data, the mutation mode is identified, the load data is clustered through clustering algorithm, different load modes are identified, and risk labels are assigned to each mode according to the characteristics of the mutation load mode, including:

[0128] Minor risk: when the load mutation amplitude is small and the duration is short, it is defined as a minor risk;

[0129] Medium risk: when the load mutation amplitude is large, it is defined as a medium risk;

[0130] High risk: when the load mutation amplitude is very large, it is defined as a high risk;

[0131] The similarity between real-time network load data and historical data is calculated using the dynamic time warping algorithm to estimate the probability distribution of mutations. The similarity measure is obtained by calculating the DTW distance between real-time load data and historical data. The higher the similarity, the lower the probability of mutation.

[0132] Based on the type and probability of mutation, a tiered early warning system is implemented, including:

[0133] Low risk warning: When the mutation probability is below a certain threshold (for example, the mutation probability is less than 0.2), it is considered that the possibility of mutation is small and belongs to low risk.

[0134] Medium risk warning: When 0.2 ≤ mutation probability < 0.5, the probability of mutation is considered to be moderate, belonging to medium risk.

[0135] High alert: When the mutation probability is ≥0.5, the possibility of mutation is considered high, which is considered a high risk.

[0136] Different response strategies are adopted according to the warning level. For example, in high-risk situations, energy storage systems can be activated or other measures can be taken to stabilize the grid load.

[0137] See Figure 6 As shown, based on the acquired power supply path and load demand, and according to the distributed negotiation protocol, each node reaches a scheduling consensus through a priority broadcast mechanism, specifically including:

[0138] Based on the acquired power supply path and load demand, scheduling data for each node is generated;

[0139] Node priority is obtained by setting dynamic weights based on energy availability and historical packet loss rate.

[0140] Based on the acquired node priorities, conflicts are eliminated through an iterative negotiation process, and the nodes are broadcast in descending order.

[0141] Furthermore, the method according to the embodiments of this application can also be achieved by means of... Figure 7 The architecture of the electronic device shown is used to implement this. For example... Figure 7 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store the microgrid distribution optimization method and system for wind, solar, energy storage, and charging provided in this application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 7 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 7One or more components in the electronic device.

[0142] Figure 8 is a computer readable storage medium structure diagram provided by an embodiment of the present application. As shown in Figure 8 The computer readable storage medium 600 stores computer readable instructions. When the computer readable instructions are run by a processor, a micro-grid distribution optimization method and system for wind-solar-storage charging according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM), cache memory, and the like. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, and the like.

[0143] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0144] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0145] The above is only the preferred embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for optimizing the distribution of a microgrid integrating wind, solar, energy storage, and charging, characterized in that, include: Real-time data collection of wind and solar power generation, energy storage status, charging load demand, and grid interaction constraint parameters at each node within the microgrid; Obtain the type characteristics of the charging load, prioritize it according to the tolerance time of the load power supply interruption, and establish a time-dimensional priority sequence; Based on the microgrid node topology, the Dijkstra algorithm is used to calculate the shortest electrical distance from each load point to the distributed power source, and energy storage compensation is initiated for edge loads to obtain the spatial power supply radius. Based on real-time acquired meteorological monitoring data, weather types are classified, basic weight coefficients are preset according to equipment type, and dynamic adjustments are made based on weather type; The system prevents sudden weight changes by using a step-inertial mechanism, triggers an emergency mode in extreme weather conditions, and cancels the smooth transition to directly switch to the preset safe weight. Based on the collected data, two-dimensional load demand data, and dynamic weight coefficients, an LSTM neural network model is trained to obtain a trained load demand prediction model. Based on the output of the load demand forecasting model, a matching relationship between line impedance and load urgency is established, a set of power supply paths is generated, and a power path selection mechanism based on dynamic programming algorithm is created. Real-time charging and discharging efficiency is calculated based on the equivalent resistance parameters of the power supply path. The charging and discharging rate threshold is dynamically adjusted according to the prediction error, and power fluctuations are smoothed by adjusting the virtual impedance. Based on real-time monitored power grid load data, real-time monitored load curves are obtained, the similarity between the load curves and historical data is calculated, and potential sudden change risks are identified through matching. Based on the obtained power supply path and load demand, each node reaches a scheduling consensus through a priority broadcast mechanism according to the distributed negotiation protocol.

2. The microgrid distribution optimization method for wind, solar, energy storage, and charging according to claim 1, characterized in that, The output results of the load demand forecasting model are used to establish a matching relationship between line impedance and load urgency, generate a set of power supply paths, and create a power path selection mechanism based on dynamic programming algorithm, specifically including: Based on the output of the load demand forecasting model, parameters of each branch of the microgrid are collected, a line impedance matrix is ​​constructed, and the equivalent impedance covering all possible power supply paths is calculated. The urgency level of the load is quantified by a comprehensive urgency score, and then normalized. The microgrid is abstracted as a weighted directed graph, with grid nodes as vertices and electrical connection lines as edges. The Prim algorithm is used to generate initial paths and output a set of candidate power supply paths. State variables are defined based on the current node location and the real-time state of charge of the energy storage, and power supply recursive equations are designed. By initializing boundary conditions, the optimal path is solved through inverse iteration to generate the globally optimal power supply path.

3. The microgrid distribution optimization method for wind, solar, energy storage, and charging according to claim 1, characterized in that, The calculation of real-time charging and discharging efficiency based on the equivalent resistance parameters of the power supply path, the dynamic adjustment of the charging and discharging rate threshold according to the prediction error, and the power fluctuation smoothing by adjusting the virtual impedance specifically include: Based on the obtained global optimal power supply path, the line resistance, transformer loss resistance and contact resistance are extracted, and the total equivalent resistance is calculated. Real-time charge and discharge efficiency is obtained by defining the overall efficiency of the energy storage system and updating the efficiency value through synchronous phasor measurement. Based on the prediction error between real-time load demand and predicted load demand, an error adaptive adjustment rule is set, and the rate of change of charging and discharging rate is controlled by a ramp function to constrain the upper limit of charging rate and the lower limit of discharging rate. The virtual resistance, inductance, and capacitance values ​​are selected based on the equivalent resistance of the power supply path, and the virtual impedance is adjusted by using feedback state data to respond to power fluctuations.

4. The microgrid distribution optimization method for wind, solar, energy storage, and charging according to claim 1, characterized in that, The process of acquiring real-time monitored load curves based on real-time monitored power grid load data, calculating the similarity between the load curves and historical data, and matching and identifying potential sudden change risks specifically includes: Based on real-time monitored power grid load data, key features in the time and frequency domain are extracted, and a feature vector set is constructed. The mutation load patterns in historical data are segmented and risk labels are added; The similarity between real-time network load data and historical data is calculated by dynamic time warping similarity to obtain the probability distribution of mutations. Graded early warning based on mutation type.

5. The microgrid distribution optimization method for wind, solar, energy storage, and charging according to claim 1, characterized in that, Based on the acquired power supply path and load demand, and according to the distributed negotiation protocol, the nodes reach a scheduling consensus through a priority broadcast mechanism, which specifically includes: Based on the acquired power supply path and load demand, scheduling data for each node is generated; Node priority is obtained by setting dynamic weights based on energy availability and historical packet loss rate. Based on the acquired node priorities, conflicts are eliminated through an iterative negotiation process, and the nodes are broadcast in descending order.

6. A microgrid distribution optimization system incorporating wind, solar, energy storage, and charging, used to implement the microgrid distribution optimization method for wind, solar, energy storage, and charging as described in any one of claims 1-5, characterized in that, include: Data acquisition module: The data acquisition module is mainly used to collect data on wind and solar power generation, energy storage status, charging load demand, and grid interaction constraint parameters of each node in the microgrid in real time, and to provide basic data support; Load demand forecasting module: The load demand forecasting module is mainly used to collect data, decompose load demand, construct a forecasting model in time and space dimensions, and dynamically adjust equipment scheduling weights according to weather type. Path selection module: The path selection module is mainly used to calculate the equivalent resistance parameters based on the power supply path, adjust the charging and discharging efficiency in real time, and achieve power fluctuation smoothing through virtual impedance adjustment; Risk identification module: By monitoring the similarity between the load curve and historical data in real time, potential mutation risks are identified and classified for early warning of mutation types; Scheduling consensus module: The scheduling consensus module is mainly used to reach a scheduling consensus through a distributed negotiation protocol and a priority broadcast mechanism among nodes, so as to ensure the coordination and efficiency of microgrid scheduling. Processor: The processor is mainly used for the calculation process of each formula and the construction calculation process of each model.

7. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a microgrid distribution optimization method for wind, solar, energy storage, and charging as described in any one of claims 1-5.

8. A computer-readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, they implement the microgrid distribution optimization method according to any one of claims 1-5, which includes wind, solar, energy storage and charging.

Images