Energy station mutual aid scheduling method, system and equipment and storage medium
By acquiring load forecasts and weight allocations, and combining them with a mixed integer programming model, the problem of low efficiency in traditional energy stations was solved, and efficient mutual dispatching between energy stations and improved power supply reliability were achieved.
Patent Information
- Application Number
- CN202510982008.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-16
- Publication Date
- 2025-10-21
AI Technical Summary
Traditional regional energy stations adopt a single energy supply mode, which is inefficient, inflexible, highly polluting, and lacks cross-site mutual assistance capabilities.
By obtaining regional load values and timestamps to generate load forecast values, assigning weights to energy stations based on equipment efficiency and geographical location, constructing a cost minimization objective function and constraints, and using a mixed integer linear programming method to solve the optimal scheduling solution, mutual scheduling among energy stations is achieved.
It significantly optimizes the load distribution accuracy among multiple energy stations, improves overall energy utilization efficiency, reduces system operating costs, and enhances power supply reliability.
Smart Images
Figure CN120822700A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of data processing technology, and specifically relates to an energy station mutual assistance scheduling method, system, equipment and storage medium. Background Art
[0002] Traditional regional energy stations generally adopt the "single energy supply + independent operation" model, which is inefficient, lacks flexibility, causes serious pollution, and has a common "information island" phenomenon between sites. There is also a lack of cross-site emergency mutual assistance capabilities in the event of a failure. Summary of the Invention
[0003] In view of the above-mentioned deficiencies in the prior art, the present invention provides an energy station mutual assistance scheduling method, system, device and storage medium to solve the above-mentioned technical problems.
[0004] In a first aspect, the present invention provides a method for mutual assistance scheduling of energy stations, comprising: Obtain the actual load value of the area and generate a load forecast value based on the actual load value and timestamp; Assign weights to each energy station in the region based on its equipment efficiency and geographical location; Generating a benchmark output of each energy station based on the load forecast value and the weight of each energy station, and generating mutual assistance requirements between energy stations based on the benchmark output of each energy station; Constructing an objective function and a constraint system for minimizing cost, wherein the constraint system includes generating transmission constraints based on the mutual aid demand; The mixed integer linear programming method is used to solve the optimal scheduling solution based on the objective function of minimizing cost and the constraint system.
[0005] In an optional embodiment, obtaining an actual load value of a region and generating a load forecast value based on the actual load value and a timestamp includes: Collect the actual load values of the area and generate a timestamp for the actual load values; Arrange the actual load values into a load sequence according to the timestamps, and arrange the timestamps into a time series; The load series and the time series are input into a pre-trained LSTM model to obtain a load forecast value.
[0006] In an optional embodiment, weights are assigned to the energy stations in the region based on their equipment efficiency and geographical locations, including: Obtain the distance from each energy station to the load center; Obtain equipment efficiency of each energy station; The weight of the corresponding energy station is calculated based on the distance and the equipment efficiency.
[0007] In an optional embodiment, generating a benchmark output of each energy station based on the load forecast value and the weight of each energy station, and generating mutual assistance requirements between energy stations based on the benchmark output of each energy station includes: Decomposing the load forecast value into load demands in multiple time periods; According to the weight ratio of each energy station and the load demand in each period, the benchmark output in each period is allocated to each energy station; Calculate the benchmark output difference of the energy station in adjacent time periods, and determine the mutual assistance demand of the energy station in the corresponding time period based on the benchmark output difference.
[0008] In an optional embodiment, constructing an objective function and a constraint system for minimizing cost includes: Constructing an objective function for minimizing costs, wherein the objective function includes energy consumption costs, carbon tax costs, and equipment loss costs; The constraint condition system includes transmission constraint conditions, equipment output limitation conditions, pipeline network flow rate upper limit, pipeline network pressure drop upper limit and energy storage tank inertia constraint conditions.
[0009] In an optional implementation, the transmission constraint condition includes:
[0010] in, represents the transmission flow from energy station i to energy station j in time period t; is a binary variable representing the activation state of the transmission path; is the set allowable deviation; represents the theoretical transmission demand driven by the forecast load from station i to station j in time period t, i.e., the mutual assistance demand; It represents the maximum physical limit of energy that energy station i can transmit to other stations in unit time.
[0011] In an optional embodiment, a mixed integer linear programming method is used to solve the optimal scheduling solution based on the objective function of minimizing cost and the constraint system, including: The objective function and constraint system are modeled and linearized to obtain a mixed integer linear programming model; The mixed integer linear programming model is solved using the branch and bound method to obtain the optimal scheduling solution.
[0012] In a second aspect, the present invention provides an energy station mutual assistance scheduling system, comprising: A load forecasting module is used to obtain the actual load value of the area and generate a load forecast value based on the actual load value and a timestamp; A weight allocation module is used to assign weights to each energy station in the region based on its equipment efficiency and geographical location; a demand generation module, configured to generate a benchmark output of each energy station based on the load forecast value and the weight of each energy station, and to generate mutual assistance demands between energy stations based on the benchmark output of each energy station; a function construction module for constructing an objective function and a constraint system for minimizing cost, wherein the constraint system includes generating transmission constraints based on the mutual aid demand; The function solving module is used to solve the optimal scheduling plan based on the objective function of minimizing cost and the constraint system using the mixed integer linear programming method.
[0013] According to a third aspect, a device is provided, comprising: A memory, used for storing an energy station mutual aid scheduling program; A processor is used to implement the steps of the energy station mutual aid scheduling method provided in the first aspect when executing the energy station mutual aid scheduling program.
[0014] In a fourth aspect, a computer-readable storage medium is provided, on which an energy station mutual aid scheduling program is stored. When the energy station mutual aid scheduling program is executed by a processor, the steps of the energy station mutual aid scheduling method provided in the first aspect are implemented.
[0015] The beneficial effects of the present invention are that the energy station mutual assistance scheduling method, system, equipment and storage medium provided by the present invention significantly optimize the load distribution accuracy among multiple energy stations and effectively improve the overall energy utilization efficiency by integrating the dual-factor dynamic empowerment mechanism of equipment efficiency and geographical distance; based on the mixed integer programming model constructed based on mutual assistance transmission constraints, the optimal economic scheduling of cross-station resources is achieved, which greatly reduces the system operating costs and spare capacity requirements; a dynamic mutual assistance response mechanism is established between energy stations, which significantly improves the power supply reliability of the system under equipment failure or load mutation conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0017] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.
[0018] Figure 2 FIG. 4 is a schematic block diagram of a system according to an embodiment of the present invention.
[0019] Figure 3 A schematic structural diagram of a device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0020] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.
[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.
[0022] The energy station mutual aid scheduling method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the energy station mutual aid scheduling system runs in the computer device.
[0023] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject can be an energy station mutual assistance scheduling system. According to different needs, the order of the steps in the flowchart can be changed, and some can be omitted.
[0024] like Figure 1 As shown, the method includes: S1. Obtain the actual load value of the region and generate a load forecast value based on the actual load value and timestamp; S2. Assign weights to each energy station within the region based on its equipment efficiency and location; S3. Generates a benchmark output of each energy station based on the load forecast value and the weight of each energy station, and generates mutual aid demand between energy stations based on the benchmark output of each energy station; S4. Constructing an objective function and a constraint system to minimize the cost, wherein the constraint system includes generating transmission constraints based on the mutual aid demand; S5. Use the mixed integer linear programming method to solve the optimal scheduling solution based on the objective function of minimizing cost and the constraint system.
[0025] In an embodiment of the present invention, based on step S1, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.
[0026] S101. Collect actual load values of a region and generate a timestamp for the actual load values.
[0027] Distributed data acquisition terminals are used to monitor the target area's power load in real time, with a sampling frequency of 15 minutes to ensure the data's temporal resolution meets short-term forecasting requirements. Acquisition parameters include active power, reactive power, and auxiliary information such as voltage and current at the corresponding moment. Active power data is stored as the core load value. Timestamp generation utilizes a conversion mechanism between Coordinated Universal Time (UTC) and the local time zone. An embedded clock module synchronizes the time base of each acquisition terminal to ensure consistent time recording. The timestamp format is defined as "YYYY-MM-DDHH:MM:SS," accurate to the second level, facilitating subsequent time series alignment and analysis. For occasional data loss caused by offline acquisition terminals, linear interpolation is used to fill in missing data. The threshold for missing data is set to no more than three consecutive sampling points. Any data loss exceeding this threshold is flagged as an anomaly and triggers re-collection.
[0028] S102. Arrange the actual load values into a load sequence according to the timestamps, and arrange the timestamps into a time sequence.
[0029] Arrange the collected load data in ascending order by timestamp to construct the original load sequence, where each element represents the load value at the corresponding sampling moment, and the total number of elements is the total number of samples. Simultaneously construct the corresponding time series, where each element is the timestamp corresponding to the load value.
[0030] To eliminate the impact of different date periods on load characteristics, the original series was segmented using a sliding window method. The window size was set to 96 (i.e., 24 hours x 4 15-minute intervals), and multiple groups of continuous load subsequences were generated using a sliding method with a step size of 1. Simultaneously, feature extraction was performed on the time series, parsing the timestamps into time features such as hours, weekdays / holidays, and seasons. A time feature matrix was constructed, where the number of rows in the matrix corresponds to the total number of samples, and the number of columns corresponds to the time feature dimensions (such as hour code, day of the week code, month code, etc.).
[0031] S103. Input the load series and the time series into a pre-trained LSTM model to obtain a load forecast value.
[0032] The processed load subsequences are fused with the time feature matrix to form the model input vector, which contains a load subsequence of length 96 and the corresponding time feature submatrix. The input data is preprocessed using the min-max normalization method to map the load values to the range of 0 to 1. The specific processing method is to subtract the minimum value of the training set load data from each load value, and then divide it by the difference between the maximum and minimum values of the training set load data.
[0033] The pre-trained LSTM model adopts a three-layer network structure: the input layer contains 128 neurons, corresponding to the fused load and time feature dimensions; the hidden layer is set to 64 neurons and uses the tanh activation function; the output layer is 1 neuron, which is used to output the load value at the predicted time.
[0034] During model training, the Adam optimizer was used, with an initial learning rate of 0.001. A learning rate decay strategy (decreasing by a factor of 0.1 every 10 training epochs) was used to optimize convergence. The root mean square error (RMSE) loss function was calculated by taking the square root of the sum of the squares of the differences between the actual load values and the model's predictions. The number of samples used in this calculation was the total number of samples in the training set. The training, validation, and test sets were divided in a ratio of 7:2:1. Early stopping was used to prevent overfitting, and training was terminated when the validation set loss did not decrease for five consecutive training epochs.
[0035] The constructed load sequence and time series are fed into the trained LSTM model. A forward propagation algorithm is used to calculate the normalized forecast value. This is then denormalized (using the minimum and maximum load values from the training set) to restore the predicted value to the actual physical load. The time granularity of the forecast output remains consistent with the input sequence, at 15 minutes per event. The forecast results are accompanied by corresponding timestamps for time series alignment with actual load data and accuracy assessment.
[0036] In an embodiment of the present invention, based on step S2, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.
[0037] S201. Obtain the distance from each energy station to the load center.
[0038] A spatial model of the regional energy network was constructed using a geographic information system (GIS), accurately locating the geographic locations of each energy station and load center using longitude and latitude coordinates. Distance calculations were performed using geodetic methods that take into account the Earth's ellipsoidal shape to improve the accuracy of spherical distance calculations. The average radius of the Earth was 6,371 km.
[0039] To further optimize the accuracy of distance data, corrections are made based on terrain characteristics. The average slope of the path is obtained based on the Digital Elevation Model (DEM). When the slope exceeds 15°, a terrain complexity factor of 1.1-1.3 is introduced. For paths crossing unusual terrain, such as waterways or tunnels, an additional correction factor of 1.05-1.2 is added. The final corrected distance is the product of the original spherical distance and the terrain factor, reflecting the physical characteristics of the actual transmission path.
[0040] S202. Obtain the equipment efficiency of each energy station.
[0041] Differentiated efficiency evaluation indicators are formulated for different types of energy stations: power stations use net power generation efficiency (the ratio of output electric power to input fuel energy), and heating stations use comprehensive heating efficiency (the ratio of effective heat at the user end to the input energy of the heat source).
[0042] Equipment efficiency data is collected in real time via an intelligent sensor network, with a sampling interval of 5 minutes. Monitoring parameters include key indicators such as power, temperature, and fuel consumption. Calibration tests are conducted quarterly, comparing measured values under standard operating conditions with theoretical values. A correction factor (the ratio of the calibration value to the measured value) is calculated. A weighted average method is used to combine the real-time monitoring data with the calibration results (weights of 0.7 and 0.3, respectively) to eliminate systematic errors caused by sensor drift.
[0043] S203. Calculate the weight of the corresponding energy station based on the distance and the equipment efficiency.
[0044] A multi-factor evaluation model was constructed using the Analytic Hierarchy Process (AHP), with distance and equipment efficiency as the core influencing factors. A judgment matrix was constructed using a 1-9 scale to quantify the relative importance of the two factors (1 indicates equal importance, 9 indicates extreme importance).
[0045] The maximum eigenvalue of the judgment matrix and its corresponding eigenvector were calculated and normalized to obtain the weight distribution of the two factors (distance factor weight w1 and equipment efficiency weight w2). A consistency check was performed to ensure the rationality of the evaluation logic (consistency ratio CR < 0.1 was considered valid).
[0046] The final weight calculation uses a standardized weighted summation method: distance metrics are treated using "reciprocal normalization" (the reciprocal of the ratio of a station's distance to the average distance), and equipment efficiency is treated using "forward normalization" (the ratio of a station's efficiency to the average efficiency). These two metrics are then multiplied by their corresponding weights and summed to obtain the overall weight of each energy station. This calculation logic ensures that closer and more efficient energy stations receive higher weights, meeting the actual requirements of energy optimization.
[0047] In an embodiment of the present invention, based on step S3, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.
[0048] S301. Decompose the load forecast value into load demands in multiple time periods; and allocate a benchmark output in each time period to each energy station based on the weight ratio of each energy station and the load demand in each time period.
[0049] Divide 24 hours into 96 time periods at 15-minute intervals and construct a time series T={t1,t2,...,t 96Each time period corresponds to a unique timestamp, forming a continuous and non-overlapping time window, and the time resolution meets the refined requirements of power grid scheduling.
[0050] Sliding window smoothing technology is used to process the load forecast value L pred , the window size is set to 3 periods (i.e. 45 minutes). For each target period t i , its load demand L i Calculated as:
[0051] Among them, α is the center weight coefficient (taken as 0.6), and β is the neighborhood smoothing coefficient (taken as 0.4), which ensures that the load decomposition results have both prediction accuracy and time series continuity.
[0052] Based on the energy station weight vector W={w1,w2,...,w n}, use the proportional allocation method to calculate the ES of each energy station j In period t i The benchmark output P i,j :
[0053] Among them, w j Energy Station ES j The comprehensive weight of The sum of the weights of all energy stations. This allocation method follows the principle of "efficiency first, distance first", ensuring that high-weight energy stations bear more load.
[0054] A nested dictionary structure is used to store allocation results. The outer key is the time period index (1-96), the inner key is the energy station identifier, and the value is the corresponding benchmark output. To improve data access efficiency, a binary search algorithm based on the time period index is implemented, supporting random access with O(logn) time complexity.
[0055] S302. Calculate the benchmark output difference of the energy station in adjacent time periods, and determine the mutual assistance demand of the energy station in the corresponding time period based on the benchmark output difference.
[0056] For each energy station ES j , calculate the change in benchmark output between adjacent time periods:
[0057] Among them, P i,j is the time period t i The benchmark output, P i-1,j It is the benchmark output of the previous period. , it means that the output needs to be increased during this period; otherwise, the output needs to be reduced.
[0058] Based on the benchmark output change, combined with the energy station regulation capacity coefficient (Value range 0.8-1.2, reflecting the rapid response capability of the energy station), calculate the mutual aid demand D i,j :
[0059] in, The threshold is set to 5% of the baseline output to filter out minor fluctuations. The model ensures that mutual assistance demands are generated only for significant output changes.
[0060] Constructing a mutual aid needs matrix , where rows represent time periods and columns represent energy stations. By using spatiotemporal clustering algorithms, we can identify peak demand periods (e.g., 8 a.m., 7 p.m.) and key mutual aid stations ( The wavelet transform is used to decompose the time-frequency characteristics of the demand sequence, extract the fluctuation components such as daily cycle and weekly cycle, and provide decision support for cross-time mutual assistance scheduling.
[0061] Mutual assistance demands are stored using a nested dictionary structure consistent with load distribution results, enabling quick query of regulation demands for any time period and any site. Demand aggregation functions are also implemented, allowing data to be aggregated by site, time period, or demand type (increment / decrement), meeting the analytical needs of different decision-making levels.
[0062] In an embodiment of the present invention, based on step S4, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.
[0063] S401. Construct an objective function for minimizing costs, wherein the objective function includes energy consumption costs, carbon tax costs, and equipment loss costs.
[0064] Objective function:
[0065] Where T is the total number of time periods in the scheduling cycle (15 minutes / time period).
[0066] Energy costs:
[0067] is the power purchased from the grid during period t (kW), is the period length (15 minutes = 0.25 hours), The electricity price during time period t (yuan / kWh).
[0068] Carbon tax costs:
[0069] Indicates the grid emission intensity (kgCO2 / kWh), Indicates the carbon tax rate (yuan / kgCO2).
[0070] Equipment loss: =
[0071] Indicates that device i is in the time period start up and hour , otherwise 0), Indicates a device collection. It represents the loss cost of each start and stop of equipment i (yuan / time), It is a binary variable, indicating the start and stop status of device i in time period t. It represents the operating loss coefficient of equipment i (yuan / kWh), It represents the output power (kW) of device i in time period t.
[0072] S402. The constraint condition system includes transmission constraint conditions, equipment output limitation conditions, pipeline network flow rate upper limit, pipeline network pressure drop upper limit and energy storage tank inertia constraint conditions.
[0073] Transmission constraints, including:
[0074] in, represents the transmission flow from energy station i to energy station j in time period t; is a binary variable representing the activation state of the transmission path; is the set allowable deviation; represents the theoretical transmission demand driven by the forecast load from station i to station j in time period t, i.e., the mutual assistance demand; It represents the maximum physical limit of energy that energy station i can transmit to other stations in unit time.
[0075] Equipment output limit:
[0076] represents the output power (kW) of device i in time period t, Indicates the start and stop status of the device (1 = running, 0 = stopping), Indicates the minimum output of the device (usually 0), Indicates the maximum output of the device (e.g. 300 kW).
[0077] Pipeline network flow rate upper limit:
[0078] Indicates mass flow rate (kg / s), Indicates the density of the fluid (kg / m³, water is 1000), Indicates the inner diameter of the pipe (m).
[0079] Pipeline network pressure drop upper limit:
[0080] represents the friction coefficient (dimensionless), Indicates the length of the pipeline (m).
[0081] Inertia constraint of energy storage tank:
[0082] Indicates charge / discharge rate*time.
[0083] In an embodiment of the present invention, based on step S5, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.
[0084] S501. Perform problem modeling and linearization on the objective function and constraint condition system to obtain a mixed integer linear programming model.
[0085] To address nonlinear terms in the model (such as the quadratic function relationship of the equipment efficiency curve and the squared term of the transmission loss), a combination of piecewise linearization and convex envelope approximation is employed. For continuous nonlinear functions, the original function curve is approximated using broken line segments, with auxiliary variables introduced to represent the weight coefficients of each segment. For nonlinear constraints containing product terms (such as the product of power and time), the large-M method is used to convert them into a system of linear inequalities, where the M value is determined based on the theoretical extreme value of the variable's range. The linearization error is kept within 5%. Approximation accuracy can be further improved by increasing the number of segments, but this requires a balance between model complexity and solution efficiency.
[0086] Define continuous variables: represents the power purchased from the grid during period t (kW), It represents the output power (kW) of device i in time period t, Indicates mass flow rate (kg / s), represents the energy of the energy storage tank in time period t (kWh), Indicates that the energy storage battery is charged. Indicates that the energy storage battery is discharged. represents the load demand, Indicates that device i is in the time period start up and hour , otherwise 0), It is a binary variable, indicating the start and stop status of device i in time period t.
[0087] Linearization of the objective function:
[0088] Where Δt = 0.25 hours (15 minutes).
[0089] Nonlinear constrained linearization: Pipeline network pressure drop constraint (quadratic terms need to be linearized):
[0090] Processing method: Calculate the maximum allowable flow rate of pipeline j .
[0091] , = , (∀j,t).
[0092] Complete MILP model: Objective function:
[0093] Constraints: 1. Equipment output limit: (∀i,t), 2. Pipeline network flow constraints: (∀j,t), 3. Energy change rate of energy storage pool: , (Linearized to: - (∀t) ).
[0094] 4. Equipment start and stop logic:
[0095] 5. Energy balance: , Other constraints: Power purchased from the grid ≥0.
[0096] S502. Solve the mixed integer linear programming model using the branch and bound method to obtain an optimal scheduling solution.
[0097] 1. Solving the initial relaxation problem First, ignore the integer constraints in the model and relax the mixed-integer linear programming problem into a linear programming problem. Use the interior point method to find the optimal solution to the relaxed problem. If all integer variables in the optimal solution are integers, then it is directly used as the optimal solution to the original problem. Otherwise, select a non-integer variable as a branch variable, and construct two subproblems based on its fractional part (adding constraints that the variable is less than or equal to the integer part, and greater than or equal to the integer part plus 1, respectively).
[0098] 2. Branching strategy and demarcation rules A depth-first search strategy is used to select branching subproblems, prioritizing nodes with better objective function values (minimization problems with smaller lower bounds). During the bounding process, the upper bound is determined by the feasible integer solutions found, and the lower bound is the objective function value of the relaxed solutions to each subproblem. Subproblems with lower bounds greater than the current upper bound are directly pruned to reduce computational effort. For subproblems with feasible but non-integer solutions, the branching process is repeated until an integer solution is found.
[0099] 3. Accelerated solving techniques Preprocessing techniques are introduced to simplify the model, including fixing variable values (for variables with a single value range, constraints are directly substituted), removing redundant constraints (identified through rank analysis of the constraint coefficient matrix), and merging similar subproblems (based on constraint equivalence). Furthermore, heuristic algorithms are used to generate initial feasible solutions (such as local searches based on historical scheduling solutions) and to quickly tighten upper bounds to improve pruning efficiency. Termination conditions are set during the solution process. When the difference between the upper and lower bounds is less than 1% of the objective function value or the computation time reaches a preset threshold (set at 1-2 hours depending on the problem size), the current optimal solution is output as a near-optimal scheduling solution.
[0100] In one example, the branch and bound solution process is: Step 1: Relax the integer constraints Binary variables Relax to a continuous variable ∈ [0,1], solve the relaxed linear programming (LP) problem, and obtain the lower bound (LB).
[0101] Step 2: Branch Operation Choose the variable that deviates the most from an integer in the relaxed solution (e.g. = 0.6), creating two subproblems: Subproblem 1: Adding constraints =0; Subproblem 2: Adding constraints =1.
[0102] Step 3: Bounding and Pruning Solve the LP relaxation for each subproblem: if the solution ≥ the current upper bound (UB), prune the branch; if the solution is an integer feasible solution and the objective value < UB, update UB; if the solution is non-integer but the objective value < UB, keep this node and continue branching.
[0103] Step 4: Iterative solution Repeat the process of branching → solving LP → bounding → pruning until: all nodes are pruned or the solution is completed. The difference between UB and LB is less than the tolerance error.
[0104] Calculate the cycle processing (15 minutes per period), scheduling cycle: 24 hours → a total of T = 24 × 4 = 96 periods.
[0105] Model scale control: Piecewise linearization (such as the charging and discharging power of the energy storage pool). Rolling optimization (RollingHorizon): Only solve for the next 3 - 4 hours (12 - 16 periods) to reduce the computational complexity.
[0106] In some embodiments, the energy station mutual aid scheduling system may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the energy station mutual aid scheduling system can be stored in the memory of a computer device and executed by at least one processor to execute (see details in Figure 1 description) the functions of energy station mutual aid scheduling.
[0107] In this embodiment, the energy station mutual aid scheduling system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 shown. The module referred to in the present invention means a series of computer program segments that can be executed by at least one processor and can complete fixed functions, and are stored in the memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.
[0108] Load forecasting module, used to obtain the actual load value of the region and generate a load forecast value based on the actual load value and timestamp; Weight allocation module, used to allocate weights to each energy station according to the equipment efficiency and geographical location of each energy station in the region; Demand generation module, used to generate the reference output of each energy station based on the load forecast value and the weights of each energy station, and generate the mutual aid demand between energy stations based on the reference output of each energy station; Function construction module, used to construct an objective function for minimizing cost and a system of constraint conditions, and the system of constraint conditions includes transmission constraint conditions generated based on the mutual aid demand; Function solving module, used to adopt the mixed integer linear programming method to solve the optimal scheduling plan based on the objective function for minimizing cost and the system of constraint conditions.
[0109] Figure 3 The energy station mutual assistance scheduling method provided for the embodiment of the present application can be applied to equipment. Those skilled in the art will understand that the equipment structure involved in the embodiment of the present invention does not constitute a limitation on the equipment, and the equipment may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In the embodiment of the present invention, the equipment includes but is not limited to laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The equipment can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.
[0110] The device 300 may include a processor 310, a memory 320, and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention. The server structure may be a bus structure or a star structure, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.
[0111] The memory 320 can be used to store execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the device 300 can perform some or all of the steps in the above-described method embodiments.
[0112] The processor 310 is the control center of the storage device, which uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and / or processes data by running or executing software programs and / or modules stored in the memory 320, and calling data stored in the memory. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In an embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.
[0113] The communication unit 330 is configured to establish a communication channel so that the storage device can communicate with other devices, receive user data sent by other devices, or send user data to other devices.
[0114] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program that, when executed, may include some or all of the steps of each embodiment provided herein. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
[0115] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software and a necessary general-purpose hardware platform. Based on this understanding, the technical solutions in the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, among other media capable of storing program code, and includes instructions for causing a computer device (which can be a personal computer, a server, or a second device, a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention.
[0116] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.
[0117] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, and can be electrical, mechanical or other forms.
[0118] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of the present embodiment according to actual needs.
[0119] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0120] Although the present invention has been described in detail with reference to the accompanying drawings and in conjunction with preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, persons of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and such modifications or substitutions shall be within the scope of the present invention. Any changes or substitutions that can be easily conceived by persons skilled in the art within the technical scope disclosed in the present invention shall be within the scope of protection of the present invention.
Claims
1. A mutual assistance scheduling method for energy stations, characterized in that: include: Obtain the actual load value of the area and generate a load forecast value based on the actual load value and timestamp; Assign weights to each energy station in the region based on its equipment efficiency and geographical location; Generating a benchmark output of each energy station based on the load forecast value and the weight of each energy station, and generating mutual assistance requirements between energy stations based on the benchmark output of each energy station; Constructing an objective function and a constraint system for minimizing cost, wherein the constraint system includes generating transmission constraints based on the mutual aid demand; The mixed integer linear programming method is used to solve the optimal scheduling solution based on the objective function of minimizing cost and the constraint system.
2. The method according to claim 1, characterized in that Get the actual load value of the area and generate the load forecast value based on the actual load value and timestamp, including: Collect the actual load values of the area and generate a timestamp for the actual load values; Arrange the actual load values into a load sequence according to the timestamps, and arrange the timestamps into a time series; The load series and the time series are input into a pre-trained LSTM model to obtain a load forecast value.
3. The method according to claim 1, characterized in that Weights are assigned to each energy station within the region based on its equipment efficiency and geographical location, including: Obtain the distance from each energy station to the load center; Obtain equipment efficiency of each energy station; The weight of the corresponding energy station is calculated based on the distance and the equipment efficiency.
4. The method according to claim 1, wherein Generating a benchmark output of each energy station based on the load forecast value and the weight of each energy station, and generating mutual assistance requirements between energy stations based on the benchmark output of each energy station, including: Decomposing the load forecast value into load demands in multiple time periods; According to the weight ratio of each energy station and the load demand in each period, the benchmark output in each period is allocated to each energy station; Calculate the benchmark output difference of the energy station in adjacent time periods, and determine the mutual assistance demand of the energy station in the corresponding time period based on the benchmark output difference.
5. The method according to claim 1, wherein Construct an objective function and constraint system to minimize the cost, including: Constructing an objective function for minimizing costs, wherein the objective function includes energy consumption costs, carbon tax costs, and equipment loss costs; The constraint condition system includes transmission constraint conditions, equipment output limitation conditions, pipeline network flow rate upper limit, pipeline network pressure drop upper limit and energy storage tank inertia constraint conditions.
6. The method according to claim 5, characterized in that The transmission constraints include: in, represents the transmission flow from energy station i to energy station j in time period t; is a binary variable representing the activation state of the transmission path; is the set allowable deviation; represents the theoretical transmission demand driven by the forecast load from station i to station j in time period t, i.e., the mutual assistance demand; It represents the maximum physical limit of energy that energy station i can transmit to other stations in unit time.
7. The method according to claim 1, characterized in that The mixed integer linear programming method is used to solve the optimal scheduling solution based on the objective function of minimizing cost and the constraint system, including: The objective function and constraint system are modeled and linearized to obtain a mixed integer linear programming model; The mixed integer linear programming model is solved using the branch and bound method to obtain the optimal scheduling solution.
8. An energy station mutual assistance dispatching system, characterized in that: include: A load forecasting module is used to obtain the actual load value of the area and generate a load forecast value based on the actual load value and a timestamp; A weight allocation module is used to assign weights to each energy station in the region based on its equipment efficiency and geographical location; a demand generation module, configured to generate a benchmark output of each energy station based on the load forecast value and the weight of each energy station, and to generate mutual assistance demands between energy stations based on the benchmark output of each energy station; a function construction module for constructing an objective function and a constraint system for minimizing cost, wherein the constraint system includes generating transmission constraints based on the mutual aid demand; The function solving module is used to solve the optimal scheduling plan based on the objective function of minimizing cost and the constraint system using the mixed integer linear programming method.
9. An energy station mutual aid dispatching device, characterized in that: include: A memory, used for storing an energy station mutual aid scheduling program; A processor is used to implement the steps of the energy station mutual assistance scheduling method as described in any one of claims 1 to 7 when executing the energy station mutual assistance scheduling program.
10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores an energy station mutual aid scheduling program, which, when executed by a processor, implements the steps of the energy station mutual aid scheduling method according to any one of claims 1 to 7.