Multi-energy complementary micro-grid coordination control method

Abstract

The invention discloses a multi-energy complementary micro-grid coordination control method, and relates to the technical field of micro-grid coordination control, and the method comprises the steps: obtaining the voltage, current, operation power, active power and circuit parameters of a gas generator, a diesel generator and a photovoltaic power generation system, and constructing a micro-grid link topological graph; load fluctuation is automatically shared according to a preset frequency-power and voltage-reactive Droop curve in the micro-grid of the gas generator and the diesel generator; when the bus frequency deviates from the nominal value, each power generation device increases or decreases the output according to a preset proportion; according to the method, the shortest path is calculated based on the power transmission loss, the current-carrying capacity and the voltage drop on the weighted topological graph, and the first power transmission path is dynamically verified and adjusted, so that rapid switching and reconstruction during a fault are realized; the monitoring and path recalculation mechanism can effectively improve the safety and reliability of the micro-grid, and reduce the risk of power supply interruption caused by abnormal lines or equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrid coordinated control, and specifically to a microgrid coordinated control method with multi - energy complementarity. Background Technique

[0002] With the continuous increase in the proportion of renewable energy, photovoltaic power generation has been widely used due to its clean and renewable characteristics. However, its output is easily affected by meteorological factors such as cloud cover, temperature, and humidity, resulting in large fluctuations in power generation. Traditional microgrid dispatching strategies mainly rely on gas generators and diesel generators for load support, making it difficult to fully utilize photovoltaic output. Moreover, when the photovoltaic output suddenly changes or the load changes violently, the frequent start - stop and large - scale adjustment of the units increase fuel consumption and equipment wear, reducing the economy and reliability of the system; The existing transmission path planning within the power grid generally based on static topological information does not fully consider dynamic factors such as real - time load distribution, line resistance, and voltage drop, and the dynamic verification mechanism for transmission loss is not perfect enough; In view of the above - mentioned technical defects, a solution is proposed now. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides a microgrid coordinated control method with multi - energy complementarity.

[0004] To achieve the above object, the present invention is realized through the following technical solutions: A microgrid coordinated control method with multi - energy complementarity, including: S1. Obtain the voltage, current, operating power, active power, and circuit parameters of the gas generator, diesel generator, and photovoltaic power generation system, and construct a microgrid link topology diagram; S2. Inside the microgrid of the gas generator and diesel generator, automatically share the load fluctuations according to the preset frequency - power and voltage - reactive power Droop curves; when the bus frequency deviates from the nominal value, each power generation device increases or decreases its output with a preset ratio; S3. Obtain the historical power generation power sequence and historical meteorological data sequence, construct a photovoltaic power generation prediction model using LSTM, and the photovoltaic power generation prediction model outputs a photovoltaic power generation curve; generate a demand curve for the load according to the historical power consumption data. During dispatching, first connect the gas generator and diesel generator, and the remaining load is borne by the photovoltaic power generation system; S4. Calculate the first transmission path for the microgrid link topology diagram based on the energy - saving strategy, convert the first transmission path into a switching operation instruction, and send it to the power distribution device.

[0005] The process of constructing the microgrid link topology diagram includes: S11. Create a unique node for each of the gas generator, diesel generator, and photovoltaic power generation system. Consider the bus or busbar trunking unit where the power generation equipment output converges as an independent node, and the important primary and secondary load branches as separate nodes; S12. If there is a cable or bus connection between any two nodes, add an undirected edge in the graph, and attach impedance, flow rate, line length, and voltage level attributes to each edge; S13. When a certain node or undirected edge is detected to be abnormal, immediately set the corresponding node or undirected edge label in the graph to invalid, and dynamically add or remove the corresponding edge through the closing / opening signal of the switch node.

[0006] The calculation of the Droop curve includes: determining the allowable maximum frequency deviation and voltage deviation amplitude based on the rated frequency and rated active power, rated voltage and rated reactive power of the unit; then calculating the active power correction coefficient and reactive power correction coefficient respectively according to the predetermined frequency - power and voltage - reactive Droop ratios, and writing them into the local controller parameters; verifying whether the active and reactive responses of the unit to frequency and voltage conform to the preset linear relationship by applying small - amplitude frequency deviation and voltage deviation, and fine - tuning the coefficients according to the test results to obtain the characteristic curve; finally, obtaining the predicted power quantity according to the timing of the verified characteristic curve, and subtracting the operating power from the predicted power quantity to obtain the active power correction quantity; Convert the active power correction quantity into a fuel valve opening / fuel injection quantity change command for the gas engine or diesel engine. The controller monitors the correction effect in each control cycle, and continuously iterates the Droop operation until the bus frequency and voltage return to the preset range.

[0007] The construction of the photovoltaic power generation prediction model to output the photovoltaic power generation curve includes: S21. Obtain the historical power generation power sequence of the photovoltaic inverter, obtain the historical meteorological data sequence, align the historical power generation power sequence and the historical meteorological data sequence at a unified time interval to form a preliminary data set; S22. Sequentially intercept windows of length W + H from the aligned data set. Use the first W - step meteorological and power generation characteristics as the input X, and the subsequent H - step power generation power as the label Y to form many - to - one or many - to - many training samples; S23. Construct a multi - layer LSTM network. The input layer inputs the multi - dimensional meteorological and power generation characteristics with a step length of W; set 1 to 2 layers of LSTM units in the hidden layer, with each layer containing M hidden states; the fully - connected output layer maps the output of the last layer of LSTM to the predicted value of the H - step photovoltaic power; select the mean square error MSE as the loss function and the Adam optimizer, and set the initial learning rate to η; S24. Invoke the photovoltaic power generation prediction model based on LSTM. The model takes the current and recent historical meteorological features as inputs, where the meteorological features include cloud amount, cloud cluster distribution, temperature, humidity, and time tags, and outputs the photovoltaic power generation curve.

[0008] Generate the average demand value of the current time segment based on historical electricity consumption data. First, connect the gas generator and the diesel generator to the grid and operate them at their respective minimum stable operating powers. When the sum of the minimum stable outputs of the gas generator and the diesel generator is greater than or equal to the average demand value, the photovoltaic power generation system provides reactive power compensation or charges the energy storage system. When the sum of the minimum stable outputs of the gas generator and the diesel generator is less than the average demand value, the system calculates the difference between the sum of the aforementioned minimum stable outputs and the average demand value as the remaining load.

[0009] Calculate the available photovoltaic power generation power of the current time period according to the photovoltaic power generation curve, and compare the available photovoltaic power generation power with the remaining load: If the available photovoltaic power generation power is greater than or equal to the remaining load, then allocate all of the remaining load to the output of the photovoltaic power generation system, and at the same time maintain the minimum stable operating powers of the gas generator and the diesel generator. The excess power of the photovoltaic power generation system is used for reactive power regulation or charging the energy storage system; If the available photovoltaic power generation power is less than the remaining load, the gas generator and the diesel generator supplement the power as needed based on their minimum stable outputs to reach the remaining load.

[0010] The calculation of the first power transmission path based on the energy-saving strategy includes: S41. Obtain the microgrid link topology map and the attributes of each edge. For each source node (including the gas generator node, the diesel generator node, and the photovoltaic power generation system node) and the equivalent load node, establish a weighted directed graph, where the weight wij of each edge eij is calculated according to the formula; Among them, Rij is the resistance value of the edge eij, Unom is the rated voltage, αij is the historical loss correction coefficient, and Pflow is the power to be transmitted; S42. Invoke the Dijkstra shortest path algorithm for each source node in turn to obtain the minimum cumulative loss path to the equivalent load node, and after the calculation is completed, compare the minimum cumulative loss values corresponding to all source nodes, and select the path with the minimum loss and its corresponding source node as the alternative first power transmission path; S43. Conduct ampacity check and voltage sag check for each edge in the alternative first power transmission path: Calculate the actual current Iij through the formula Iij = Pflow / Unom, and determine whether it exceeds the rated ampacity Iijmax of the edge; at the same time, calculate the cumulative voltage sag of the path ∑Rij × Iij and determine whether it exceeds the set voltage sag threshold; if either of the above checks is not satisfied, remove the corresponding edge from the weighted graph and re - execute step S42; S44. When the alternative first power transmission path passes all the checks, the system confirms it as the final first power transmission path; S45. Extract the breaker identifiers corresponding to the path edges from the final first power transmission path, and generate corresponding closing operation instructions in the path start - end order; the system simultaneously generates opening operation instructions for all edges adjacent to the path nodes but not on the path.

[0011] Encapsulate the closing and opening operation instructions into a control message containing the target breaker ID, operation type, execution timing, and security verification code in a predetermined protocol format, and send it to each distribution terminal through the communication channel; when it is detected that any breaker fails to execute the instruction successfully or an abnormality occurs, mark the corresponding edge as invalid and start the recalculation process from step S41.

[0012] The present invention provides a coordinated control method for a multi - energy complementary microgrid. Compared with the prior art, it has the following beneficial effects: The present invention calculates the shortest path based on transmission loss, ampacity, and voltage sag on the weighted topology graph, and dynamically checks and adjusts the first power transmission path to achieve fast switching and reconstruction during faults; this monitoring and path recalculation mechanism can effectively improve the security and reliability of the microgrid and reduce the risk of power supply interruption caused by line or equipment abnormalities; The present invention realizes the prediction of available photovoltaic output by collecting historical power generation power sequences and historical meteorological data sequences and constructing an LSTM prediction model; combines the historical electricity consumption curve to generate a stable load demand, and preferentially uses photovoltaic output to cover the remaining load, thereby significantly reducing the operation duration and fuel consumption of gas engines and diesel engines and improving the overall energy utilization efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the principle framework of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0015] Embodiment 1

[0016] Please refer to Figure 1 , this application provides a multi - energy complementary micro - grid coordinated control method, including: S1. Obtain the voltage, current, operating power, active power, and circuit parameters of the gas generator, diesel generator, and photovoltaic power generation system, and construct a micro - grid link topology diagram; S2. Inside the micro - grid of the gas generator and diesel generator, automatically share the load fluctuations according to the preset frequency - power and voltage - reactive power Droop curves; when the bus frequency deviates from the nominal value, each power generation device increases or decreases its output with a preset ratio; S3. Obtain the historical power generation power sequence and historical meteorological data sequence, use LSTM to construct a photovoltaic power generation prediction model, and the photovoltaic power generation prediction model outputs a photovoltaic power generation curve; generate a demand curve for the load according to historical power consumption data. During scheduling, first connect the gas generator and diesel generator, and the remaining load is borne by the photovoltaic power generation system; S4. Calculate the first power transmission path for the micro - grid link topology diagram based on the energy - saving strategy, convert the first power transmission path into a switch operation instruction, and send it to the power distribution device.

[0017] The process of constructing the micro - grid link topology diagram includes: S11. Create a unique node for each of the gas generator, diesel generator, and photovoltaic power generation system, regard the bus or bus - bar box where the power generation equipment output converges as an independent node, and regard the important primary and secondary load branches as separate nodes; S12. If there is a cable or bus connection between any two nodes, add an undirected edge in the graph, and attach impedance, flow, line length, and voltage level attributes to each edge; S13. When detecting an abnormality in a certain node or undirected edge, immediately mark the corresponding node or undirected edge as invalid in the graph, and dynamically add or remove the corresponding edge through the closing / opening signal of the switch node.

[0018] Specifically, for each inverter in the gas generator, the diesel generator 1, the diesel generator 2, and the photovoltaic power generation system, a corresponding power generation node (node ID) is created according to the unique equipment number, and the following metadata is associated with each power generation node: physical location (such as cabinet number, machine room coordinates), rated voltage level, rated active / reactive power, access point bus number, equipment operation status pointer (used to read voltage, current, frequency, active / reactive power in real time); For the busbar or busbar box where the output of the photovoltaic modules or each generator converges, an independent busbar node is created, and the node ID corresponds to the corresponding busbar number or busbar box number.

[0019] Initialize the attributes for each busbar node: busbar voltage level (such as 400 V, 10.5 kV), real-time voltage measurement point pointer, real-time current accumulation pointer (used to count the parallel output of multiple connected devices). Reflect the important first-level loads in the system (such as key communications, command centers, life support equipment) as independent load nodes in the topology diagram and assign node IDs.

[0020] Calculating the Droop curve includes: determining the allowable maximum frequency deviation and voltage deviation amplitude according to the rated frequency and rated active power, rated voltage and rated reactive power of the unit; then calculating the active power correction coefficient and reactive power correction coefficient respectively according to the predetermined frequency - power and voltage - reactive power Droop ratios, and writing them into the local controller parameters; verifying whether the active and reactive power responses of the unit to frequency and voltage conform to the preset linear relationship by applying small-amplitude frequency deviation and voltage deviation, and fine-tuning the coefficients according to the test results to obtain the characteristic curve; finally, obtaining the predicted power amount according to the timing of the verified characteristic curve, and subtracting the operating power from the predicted power amount to obtain the active power correction amount; Local Droop regulation of the unit: According to the nameplate parameters of each unit, read the rated frequency, rated active / reactive power and rated voltage, select the maximum frequency deviation and voltage deviation amplitude, calculate the initial frequency - active power and voltage - reactive power Droop coefficients, and send them to the gas turbine excitation system, diesel engine Governor or photovoltaic inverter reactive power control unit.

[0021] In the on-site test, apply a small-amplitude frequency deviation or voltage deviation to the unit, measure the active and reactive power responses of the unit, verify their linear relationship, and fine-tune the Droop coefficients according to the test results until the error meets the set accuracy.

[0022] When powered on and running, within each control cycle of 10 ms to 100 ms, the unit measures the bus frequency and voltage in real time, calculates the expected active / reactive power output through look-up table or linear interpolation, converts the correction amount into the opening of the gas valve or the diesel fuel injection amount / the reference value of the PV inverter, quickly injects or absorbs reactive power, and ensures that the bus frequency and voltage recover stably within the deviation range.

[0023] Convert the active power correction amount into the change command of the fuel valve opening / fuel injection amount of the gas engine or diesel engine. The controller monitors the correction effect in each control cycle and continuously iterates the Droop operation until the bus frequency and voltage recover to the preset range.

[0024] Construct a photovoltaic power generation prediction model to output the photovoltaic power generation curve, including: S21. Obtain the historical power generation power sequence of the PV inverter, obtain the historical meteorological data sequence, align the historical power generation power sequence and the historical meteorological data sequence at a unified time interval to form a preliminary data set; S22. Sequentially intercept windows with a length of W + H from the aligned data set. Use the first W-step meteorological and power generation characteristics as the input X, and use the subsequent H-step power generation power as the label Y to form one-to-many or many-to-many training samples; S23. Construct a multi-layer LSTM network. The input layer inputs the multi-dimensional meteorological and power generation characteristics of W steps; set 1 to 2 layers of LSTM units in the hidden layer, with each layer containing M hidden states; the fully connected output layer maps the output of the last layer of LSTM to the predicted value of the H-step photovoltaic power; select the mean squared error MSE as the loss function and the Adam optimizer, and set the initial learning rate to η; S24. Call the photovoltaic power generation prediction model based on LSTM. The model takes the current and recent historical meteorological characteristics as the input, and the meteorological characteristics include cloud amount, cloud cluster distribution, temperature, humidity and time label, and outputs the photovoltaic power generation curve.

[0025] Multi-layer LSTM network structure: The first layer of LSTM hidden layer: contains M1 hidden units (such as 64 or 128), return_sequences = True; The second layer of LSTM hidden layer (optional): contains M2 hidden units (such as 32 or 64), return_sequences = False; Fully connected output layer: For the many-to-many model, connect TimeDistributedDense to map each time step to a scalar prediction; for the one-to-many model, only connect the Dense layer at the last moment to output the photovoltaic power generation curve with a length of H.

[0026] Training process: Divide the samples generated by the sliding window into a training set (70%), a validation set (20%), and a test set (10%), maintaining the chronological order; set the batch size to 32 or 64, and train for several epochs (such as 50 - 200) in a loop; after each epoch, evaluate MSE and MAE on the validation set. If the validation error does not decrease for p consecutive epochs (such as 10 epochs), trigger early stopping and save the current optimal model weights; conduct a final evaluation on the test set, calculate metrics such as MSE, MAE, and MAPE, and generate a comparison graph of the photovoltaic power generation curve and the actual curve to verify the generalization ability of the model under various weather conditions such as sunny days, cloudy days, and showers.

[0027] Beneficial effects: The present invention realizes the prediction of the available photovoltaic output by collecting historical power generation power sequences and historical meteorological data sequences and constructing an LSTM prediction model; combines historical electricity consumption curves to generate a stable load demand, preferentially uses photovoltaic output to cover the remaining load, thereby significantly reducing the operating duration and fuel consumption of gas engines and diesel engines, and improving the overall energy utilization efficiency of the system.

[0028] Embodiment 2

[0029] Generate the average demand value of the current time segment based on historical electricity consumption data. First, connect the gas generator and the diesel generator to the grid and operate them at their respective minimum stable operating powers. When the sum of the minimum stable outputs of the gas generator and the diesel generator is greater than or equal to the average demand value, the photovoltaic power generation system provides reactive power compensation or charges the energy storage system. When the sum of the minimum stable outputs of the gas generator and the diesel generator is less than the stable demand value, the system calculates the difference between the sum of the aforementioned minimum stable outputs and the stable demand value as the remaining load.

[0030] Generating the average demand value of the current time segment based on historical electricity consumption data includes: real-time collecting the historical active power time series of each level of load (including first-level, second-level, and third-level loads) in the microgrid through a distribution monitoring system, with the sampling granularity being the same as that of photovoltaic prediction (such as once every 5 minutes), and recording the corresponding timestamps; Then, perform missing value processing on the collected load power data: for data empty points caused by communication delays or faults, use forward filling or the average value of adjacent time periods for filling; Segment the above historical load data according to the time granularity (for example, process each upcoming 5-minute period of the current day separately), calculate the arithmetic mean of the load data corresponding to all historical dates within each period, and obtain the average demand value of the current time segment.

[0031] Calculate the available photovoltaic power generation for the current time period according to the photovoltaic power generation curve, and compare the available photovoltaic power generation with the remaining load: If the available photovoltaic power generation is greater than or equal to the remaining load, allocate all of the remaining load to the output of the photovoltaic power generation system, and at the same time keep the gas generator and the diesel generator operating at the minimum stable power. The excess power of the photovoltaic power generation system is used for reactive power regulation or charging the energy storage system; If the available photovoltaic power generation is less than the remaining load, the gas generator and the diesel generator supplement the remaining load as needed based on their minimum stable output.

[0032] The reactive power compensation or energy storage charging of the photovoltaic system includes: When the base load of the unit can fully meet the average load, after the photovoltaic system is connected to the grid, it does not need to undertake active power output, and all available photovoltaic power can be used for reactive power compensation to maintain the stability of the bus voltage; If there is an energy storage device and it is in a rechargeable state, the available photovoltaic power can also be preferentially used to charge the energy storage device to reserve standby energy in advance; In this state, if the actual output of the photovoltaic is lower than the predicted value, only reactive power regulation can be performed or energy storage charging can be suspended, and the unit continues to operate at the lowest base load without adjusting the active power output.

[0033] Calculating the first power transmission path based on the energy-saving strategy includes: S41. Obtain the microgrid link topology diagram and the attributes of each edge. For each source node (including the gas generator node, the diesel generator node, and the photovoltaic power generation system node) and the equivalent load node, establish a weighted directed graph, where the weight wij of each edge eij is calculated according to the formula; Among them, Rij is the resistance value of the edge eij, Unom is the rated voltage, αij is the historical loss correction coefficient, and Pflow is the power to be transmitted; S42. Call the Dijkstra shortest path algorithm for each source node in turn to obtain the minimum cumulative loss path to the equivalent load node. After the calculation is completed, compare the minimum cumulative loss values corresponding to all source nodes, and select the path with the smallest loss and its corresponding source node as the alternative first power transmission path; S43. Perform current-carrying capacity verification and voltage drop verification on each edge in the alternative first power transmission path: Calculate the actual current Iij through the formula Iij = Pflow / Unom, and judge whether it exceeds the rated current-carrying capacity Iijmax of the edge; At the same time, calculate the cumulative voltage drop ∑Rij×Iij of the path and judge whether it exceeds the set voltage drop threshold; If either of the above verifications is not satisfied, remove the corresponding edge from the weighted graph and re-execute step S42; S44. When the alternative first power transmission path passes all verifications, the system confirms it as the final first power transmission path; S45. Extract the breaker identifiers corresponding to the path edges from the final first power transmission path, and generate corresponding closing operation instructions in the path start - end order; meanwhile, the system generates opening operation instructions for all edges that are adjacent to the path nodes but not on the path.

[0034] The specific implementation method of calling the shortest path algorithm to obtain the path with the minimum cumulative loss to the equivalent load node includes: For each source node (including gas generator nodes, diesel generator nodes, and photovoltaic power generation system nodes), obtain the corresponding weighted directed graph from step S41. This graph contains all power generation nodes, intermediate bus nodes, and equivalent load nodes in the microgrid, and each edge has been assigned a weight calculated based on the line resistance R, rated voltage U_nom, historical loss correction factor α, and power to be transmitted P_flow; then, for the current source node s, the system initializes the distance values for all nodes in the local temporary data structure, sets the initial distance of the source node to zero, and the other nodes to infinity, and establishes a predecessor pointer prev for each node to record the optimal path information. At the same time, insert all nodes and their distance values into the priority queue Q. Then, when the queue Q is not empty, loop to execute: take out the node u with the current minimum distance from Q. If the node has not been visited, mark it as visited; if u is the equivalent load node, it means that the shortest cumulative loss path from the source node s to the equivalent load node has been found, and the loop can be terminated in advance; otherwise, the system traverses all edges starting from u, and for each edge (u,v) that is not marked as invalid and has a non - infinite weight, calculate the candidate distance alt = dist[u]+w(u,v). If alt is less than the currently stored dist[v], then update dist[v] = alt and set prev[v] = u. At the same time, update the priority of node v in the queue Q to alt. After the loop ends, if the distance of the equivalent load node is still infinity, mark this source node as unreachable and no longer participate in the candidate path comparison; otherwise, reconstruct the optimal path Path_s by backtracking the predecessor pointer prev from the equivalent load node to the source node s and record the cumulative loss value Cost_s of this path. After completing the above shortest path search for all source nodes, the system compares the minimum cumulative loss values Cost_s corresponding to each source node, and selects the source node s_min and its path Path_{s_min} with the minimum value as the first power transmission path.

[0035] Encapsulate the closing and opening operation instructions into a control message containing the target circuit breaker ID, operation type, execution timing, and security verification code according to a predetermined protocol format, and send it to each distribution terminal through the communication channel; when it is detected that any circuit breaker fails to execute the instruction successfully or an abnormality occurs, mark the corresponding edge as invalid and start the recalculation process from step S41.

[0036] Specifically, extract the circuit breaker numbers corresponding to each edge from the final path, generate closing instructions in the order of the path from the source node to the load node, generate opening instructions for other edges outside the path but adjacent to the path nodes, and encapsulate all closing / opening operations into a control message according to the communication protocol format (including circuit breaker ID, operation type, execution timing, and security verification code), and send it to each distribution terminal through the SCADA / IEC61850 channel; after each terminal executes, it will feedback the circuit breaker status and voltage and current data in real time. If it is monitored that any circuit breaker fails to complete the operation according to the instruction or an abnormality occurs, mark the corresponding path edge as invalid and recalculate from the first step again.

[0037] Beneficial effects: The present invention performs the shortest path calculation based on transmission loss, current-carrying capacity, and voltage drop on the weighted topology graph, and dynamically verifies and adjusts the first transmission path to achieve fast switching and reconstruction during faults; the monitoring and path recalculation mechanism can effectively improve the security and reliability of the microgrid and reduce the risk of power supply interruption caused by line or equipment abnormalities.

[0038] Some of the data in the above formula are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0039] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A coordinated control method for a multi - energy complementary microgrid, characterized in that, Including: S1. Obtain the voltage, current, operating power, active power, and circuit parameters of the gas generator, diesel generator, and photovoltaic power generation system, and construct a microgrid link topology diagram; S2. Inside the microgrid of the gas generator and diesel generator, automatically share the load fluctuations according to the preset frequency–power and voltage–reactive power Droop curves; when the bus frequency deviates from the nominal value, each power generation device increases or decreases its output by a preset ratio; S3. Obtain the historical power generation power sequence and historical meteorological data sequence, and use LSTM to construct a photovoltaic power generation prediction model. The photovoltaic power generation prediction model outputs a photovoltaic power generation curve; generate a demand curve for the load according to the historical power consumption data. During scheduling, first connect the gas generator and diesel generator, and the remaining load is borne by the photovoltaic power generation system; S4. Calculate the first power transmission path for the microgrid link topology diagram based on the energy-saving strategy, convert the first power transmission path into a switch operation instruction, and send it to the power distribution device.

2. The multi - energy complementary microgrid coordinated control method according to claim 1, wherein, The process of constructing the microgrid link topology diagram includes: S11. Create a unique node for each of the gas generator, diesel generator, and photovoltaic power generation system. Regard the bus or busbar box where the power generation equipment output converges as an independent node, and regard the important first-level and second-level load branches as separate nodes; S12. If there is a cable or bus connection between any two nodes, add an undirected edge in the diagram, and attach impedance, flow rate, line length, and voltage level attributes to each edge; S13. When detecting an abnormality in a certain node or undirected edge, immediately set the corresponding node or undirected edge label in the diagram to invalid, and dynamically add or remove the corresponding edge through the closing / opening signal of the switch node.

3. A coordinated control method for a multi - energy complementary microgrid according to claim 1, characterized in that, The calculation of the Droop curve includes: determining the allowable maximum frequency deviation and voltage deviation amplitude according to the rated frequency and rated active power, rated voltage and rated reactive power of the unit; then calculating the active power correction coefficient and reactive power correction coefficient respectively according to the preset frequency–power and voltage–reactive power Droop ratios, and writing them into the local controller parameters; verifying whether the active and reactive power responses of the unit to frequency and voltage conform to the preset linear relationship by applying a small frequency deviation and voltage deviation, and fine-tuning the coefficients according to the test results to obtain the characteristic curve; finally, obtaining the predicted power quantity according to the timing of the verified characteristic curve, and subtracting the operating power from the predicted power quantity to obtain the active power correction quantity; Convert the active power correction quantity into a fuel valve opening / fuel injection quantity change instruction for the gas engine or diesel engine. The controller monitors the correction effect in each control cycle, and continuously iterates the Droop operation until the bus frequency and voltage return to the preset range.

4. A coordinated control method for a multi - energy complementary microgrid according to claim 1, characterized in that, The construction of the photovoltaic power generation prediction model outputting the photovoltaic power generation curve includes: S21. Obtain the historical power generation power sequence of the photovoltaic inverter, obtain the historical meteorological data sequence, align the historical power generation power sequence and historical meteorological data sequence at a unified time interval to form a preliminary data set; S22. Sequentially intercept windows with a length of W + H for the aligned data set. Use the first W-step meteorological and power generation characteristics as the input X, and use the subsequent H-step power generation power as the label Y to form one-to-many or many-to-many training samples; S23. Construct a multi-layer LSTM network. The input layer inputs multi-dimensional meteorological and power generation features with a step size of W. The hidden layer is set with 1 to 2 layers of LSTM units, and each layer contains M hidden states. The fully connected output layer maps the output of the last layer of LSTM to the predicted photovoltaic power value for H steps. The mean squared error (MSE) is selected as the loss function, and the Adam optimizer is used with the initial learning rate set to η. S24. Invoke the photovoltaic power generation prediction model based on LSTM. The model takes the current and recent historical meteorological features as inputs, and the meteorological features include cloud amount, cloud cluster distribution, temperature, humidity, and time tags, and outputs the photovoltaic power generation curve.

5. A coordinated control method for a multi - energy complementary microgrid according to claim 1, characterized in that, Generate the equilibrium value for each unit time segment based on historical electricity consumption data. First, connect the gas generator and the diesel generator to the grid and operate them at their respective minimum stable operating powers. When the sum of the minimum stable outputs of the gas generator and the diesel generator is greater than or equal to the equilibrium value, the photovoltaic power generation system provides reactive power compensation or charges the energy storage system. When the sum of the minimum stable outputs of the gas generator and the diesel generator is less than the equilibrium value, calculate the difference between the sum of the minimum stable outputs and the equilibrium value as the remaining load.

6. A coordinated control method for a multi - energy complementary microgrid according to claim 1, characterized in that, Calculate the available photovoltaic power generation power for the current time period according to the photovoltaic power generation curve, and compare the available photovoltaic power with the remaining load: If the available photovoltaic power is greater than or equal to the remaining load, then allocate the remaining load entirely to the output of the photovoltaic power generation system, and at the same time keep the gas generator and the diesel generator at their minimum stable operating powers. The excess power of the photovoltaic power generation system is used for reactive power regulation or charging the energy storage system; If the available photovoltaic power is less than the remaining load, the gas generator and the diesel generator supplement the remaining load as needed based on their minimum stable outputs.

7. A coordinated control method for a multi - energy complementary microgrid according to claim 1, characterized in that, The calculation of the first power transmission path based on the energy-saving strategy includes: S41. Obtain the microgrid link topology diagram and the attributes of each edge. For each source node (including the gas generator node, diesel generator node, and photovoltaic power generation system node) and the equivalent load node, establish a weighted directed graph, where the weight wij of each edge eij is calculated according to the formula; Among them, Rij is the resistance value of the edge eij, Unom is the rated voltage, αij is the historical loss correction coefficient, and Pflow is the power to be transmitted; S42. Invoke the Dijkstra shortest path algorithm for each source node in turn to obtain the path with the minimum cumulative loss to the equivalent load node. After the calculation is completed, compare the minimum cumulative loss values corresponding to all source nodes, and select the path with the minimum loss and its corresponding source node as the alternative first power transmission path. S43. Conduct ampacity verification and voltage drop verification for each edge in the alternative first power transmission path: Calculate the actual current Iij through the formula Iij = Pflow / Unom, and determine whether it exceeds the rated ampacity Iijmax of this edge; At the same time, calculate the cumulative voltage drop ∑Rij×Iij of the path and determine whether it exceeds the set voltage drop threshold; If either of the above verifications is not satisfied, remove the corresponding edge from the weighted graph and re-execute step S42. S44. When the alternative first power transmission path passes all verifications, the system confirms it as the final first power transmission path. S45. Extract the breaker identifiers corresponding to the path edges from the final first power transmission path, and generate the corresponding closing operation instructions in the path start - end order; The system also generates opening operation instructions for all edges adjacent to the path nodes but not on this path.

8. A coordinated control method for a multi - energy complementary microgrid according to claim 1, characterized in that Encapsulate the closing and opening operation instructions into a control message containing the target circuit breaker ID, operation type, execution timing, and security verification code according to a predetermined protocol format, and send it to each distribution terminal through the communication channel; when it is detected that any circuit breaker fails to execute the instruction successfully or an abnormality occurs, mark the corresponding edge as invalid and start the recalculation process from step S41.

Images