Power grid intelligent scheduling method, system, equipment and medium

Abstract

The invention relates to the technical field of power grid intelligent scheduling, and discloses a power grid intelligent scheduling method, system and device and a medium, and the method comprises the steps: constructing a first power grid device coupling dynamic representation model, comprehensively and dynamically reflecting the correlation and operation state between power grid devices, and providing a solid foundation for the subsequent optimization regulation and control. And the establishment of the second multi-target collaborative optimization regulation and control model combines global load optimization with precise control of the local power grid, so that the power grid dispatching can realize reasonable load distribution from a macroscopic level, and also can ensure stable operation of the local power grid from a microscopic level. Compared with a traditional power grid dispatching mode, the method does not depend on single experience judgment or a simple control strategy any more. The capacity of the power grid for coping with complex operation environments and emergency situations is greatly improved, for example, under the conditions of extreme weather, equipment faults and the like, the scheduling scheme can be rapidly adjusted, and safe and reliable operation of the power grid is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of intelligent power grid dispatching technology, and in particular to an intelligent power grid dispatching method, system, device and medium. Background Technology

[0002] As power systems continue to evolve, their complexity and intelligence levels are increasing. Traditional power grid dispatching methods are proving inadequate and unable to fully meet the demands of efficient and stable operation of modern power grids. Traditional dispatching methods largely rely on the personal experience of dispatchers and pre-defined static models. These methods are ill-suited to cope with rapid changes in the power grid operating environment and the complex and diverse states of equipment. Specifically, when the power grid encounters sudden natural disasters such as strong winds, torrential rains, or earthquakes, or when equipment experiences sudden failures, traditional dispatching methods often fail to make accurate and effective dispatching decisions in the immediate situation.

[0003] This slow response and poor decision-making will not only lead to a significant decline in the overall operating efficiency of the power grid, but may also further trigger power outages in local areas. In severe cases, it may even threaten the safe and stable operation of the entire power grid, causing widespread social impact and economic losses.

[0004] Therefore, there is an urgent need to explore and introduce more advanced and intelligent power grid dispatching technologies to address the various complex challenges in modern power grid operation. Summary of the Invention

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, this invention provides a method, system, device, and medium for intelligent power grid dispatching, which can solve the shortcomings of traditional power grid dispatching methods in dealing with complex and ever-changing power grid operating environments and equipment states, improve the accuracy, timeliness, and effectiveness of power grid dispatching, and ensure the efficient, stable, and safe operation of the power grid.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a smart grid dispatching method, comprising:

[0009] Collect power grid operating environment parameters and equipment status signals, and perform a first preprocessing on the power grid operating environment parameters and equipment status signals;

[0010] A first dynamic characterization model of power grid equipment is constructed based on the preprocessed power grid operating environment parameters and equipment status signals.

[0011] Based on the first coupled dynamic characterization model of power grid equipment, and combined with the intelligent dispatching objectives of the power grid and the safety constraints of the equipment, a second multi-objective collaborative optimization control model is constructed.

[0012] The second multi-objective collaborative optimization and control model includes an upper-level global load optimization objective function and a lower-level local power grid precise control objective function;

[0013] Solve the second multi-objective collaborative optimization control model, and perform intelligent power grid dispatching based on the solution results.

[0014] As a preferred embodiment of the intelligent power grid dispatching method of the present invention, the step of performing intelligent power grid dispatching based on the solution results includes:

[0015] Based on the solution results, generate the optimal start-up, shutdown, and regulation command sequence for power generation, transmission, and distribution equipment in the future time period;

[0016] The optimal start / stop and adjustment command sequence is sent to the field execution unit;

[0017] After receiving the optimal start-stop and regulation command sequence, the field execution unit controls the power generation, transmission, and distribution equipment to perform corresponding start-stop and regulation operations according to the command sequence.

[0018] As a preferred embodiment of the intelligent power grid dispatching method of the present invention, the construction of the first power grid equipment coupled dynamic representation model includes:

[0019] A set of key factors affecting the load of power grid nodes is preset, and a time series prediction sub-model is established based on historical operating data and physical mechanisms;

[0020] The time series prediction sub-model is used to predict the future short-term load evolution trend of power grid nodes.

[0021] A voltage stability assessment sub-model is constructed. The inputs of the voltage stability assessment sub-model are load level, generator output, and line impedance, and the output is the predicted value of voltage stability margin.

[0022] This preferred solution enables a more accurate grasp of the operating status and load changes of power grid equipment. By pre-setting a set of key factors affecting the load of power grid nodes and establishing a time-series prediction sub-model, it is possible to predict the short-term load evolution trend of power grid nodes in advance. This helps to plan the operation strategies of power generation, transmission, and distribution equipment in advance, avoiding power grid failures or instability caused by sudden load changes. Simultaneously, the constructed voltage stability assessment sub-model uses key parameters such as load level, generator output, and line impedance to output predicted voltage stability margin values, enabling real-time monitoring of power grid voltage stability. When the voltage stability margin approaches the safety threshold, timely adjustment measures can be taken, such as adjusting generator output or switching lines, to ensure the safe and stable operation of the power grid. This multi-dimensional modeling and prediction approach transforms intelligent power grid dispatch from traditional experience-based dispatch to intelligent dispatch based on accurate data and scientific models, improving the efficiency and reliability of power grid dispatch, reducing power grid operating costs, decreasing the probability of power outages, and providing users with a more stable and high-quality power supply.

[0023] As a preferred embodiment of the intelligent power grid dispatching method of the present invention, the construction of the first power grid equipment coupled dynamic representation model further includes:

[0024] The time series prediction sub-model and the voltage stability assessment sub-model are integrated;

[0025] The first power grid equipment coupled dynamic characterization model is used to describe the nonlinear response relationship between climate environment, operating conditions, power generation mode and load distribution to the load and voltage stability of power grid nodes.

[0026] As a preferred embodiment of the intelligent power grid dispatching method described in this invention, the second multi-objective collaborative optimization control model includes:

[0027] The objective function for optimizing the upper-level global load aims to minimize the overall load of the power grid.

[0028] The overall load of the power grid includes the generation-side load, the transmission-side load, and the distribution-side load;

[0029] The objective function for precise control of the lower-level local power grid aims to minimize the deviation between the load of the power grid nodes and the set value, as well as to minimize the probability of voltage instability.

[0030] As a preferred embodiment of the intelligent power grid dispatching method of the present invention, the intelligent power grid dispatching objectives and equipment security constraints include:

[0031] The objectives of the intelligent power grid dispatch include minimizing the overall power grid load, minimizing the deviation between the power grid node load and the set value, and minimizing the probability of voltage instability.

[0032] The equipment safety constraints include at least the equipment's rated power limit, equipment operating time limit, equipment start-stop frequency limit, equipment environmental adaptability constraint, and equipment maintenance cycle constraint.

[0033] As a preferred embodiment of the intelligent power grid dispatching method of the present invention, the solution of the second multi-objective collaborative optimization control model includes a preset first improved solution strategy, which includes improvements based on model predictive control and particle swarm optimization.

[0034] In a second aspect, the present invention provides a smart grid dispatching system, comprising:

[0035] The data acquisition and processing module is used to acquire power grid operating environment parameters and equipment status signals, and to perform a first preprocessing on the power grid operating environment parameters and equipment status signals;

[0036] The first model building module is used to construct a first power grid equipment coupled dynamic characterization model based on the first preprocessed power grid operating environment parameters and equipment status signals.

[0037] The second model building module is used to construct a second multi-objective collaborative optimization control model based on the first power grid equipment coupled dynamic representation model and combined with the power grid intelligent dispatching objectives and equipment safety constraints.

[0038] The second multi-objective collaborative optimization and control model includes an upper-level global load optimization objective function and a lower-level local power grid precise control objective function;

[0039] The solution module is used to solve the second multi-objective collaborative optimization control model, and to perform intelligent power grid scheduling based on the solution results.

[0040] Thirdly, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0041] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0042] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention proposes a smart grid dispatching method. By constructing a first dynamic characterization model of coupled grid equipment, it comprehensively and dynamically reflects the interrelationships and operating states between grid equipment, providing a solid foundation for subsequent optimization and control. Furthermore, the establishment of a second multi-objective collaborative optimization and control model combines global load optimization with precise local grid control, enabling grid dispatching to achieve reasonable load allocation at the macro level while ensuring stable operation of local grids at the micro level. Compared with traditional grid dispatching methods, this invention no longer relies on single empirical judgments or simple control strategies, but instead makes dispatching decisions based on precise models and multi-objective optimization algorithms. This greatly improves the grid's ability to cope with complex operating environments and emergencies, such as extreme weather or equipment failures, allowing for rapid adjustment of dispatching schemes to ensure the safe and reliable operation of the grid.

[0043] Meanwhile, this invention also reduces power grid operating costs. By optimizing the upper-level global load objective function, power generation resources are rationally allocated, unnecessary power generation losses are reduced, and efficient energy utilization is achieved. The lower-level local power grid precise control objective function ensures the stability of parameters such as voltage and frequency of the local power grid, reducing equipment losses and maintenance costs. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of a smart power grid dispatching method provided in one embodiment of the present invention.

[0046] Figure 2 This is an internal structure diagram of an electronic device for a smart power grid dispatching method according to an embodiment of the present invention. Detailed Implementation

[0047] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0048] Example 1, referring to Figure 1This is the first embodiment of the present invention, which provides a smart grid dispatching method, including:

[0049] Existing technologies have several drawbacks. Traditional power grid dispatching methods rely heavily on manual experience and simple rule-based settings, lacking the ability to accurately perceive and rapidly respond to real-time power grid conditions and dynamic changes. For example, during peak electricity demand periods, the inability to promptly and accurately obtain changes in electricity demand across different regions often hinders the rational allocation of power generation resources, leading to power shortages in some areas and overcapacity in others, resulting in energy waste. Furthermore, when a device in the power grid malfunctions, traditional dispatching methods struggle to quickly locate the fault and adjust power transmission paths, potentially triggering a chain reaction and expanding the scope of the fault's impact.

[0050] This invention provides a method that can effectively solve the problems mentioned above. The following will describe in detail how to implement the intelligent power grid dispatching method with reference to several embodiments.

[0051] Figure 1 A flowchart of a smart grid dispatching method is shown, including:

[0052] S101, collect power grid operating environment parameters and equipment status signals, and perform the first preprocessing on the power grid operating environment parameters and equipment status signals, wherein:

[0053] It should be noted that, in order to achieve intelligent power grid dispatching, accurate and comprehensive collection of power grid operating environment parameters and equipment status signals is crucial. It is necessary to analyze the real-time operating status and potential risks of the power grid from these parameters and signals.

[0054] In some specific implementations, power grid operating environment parameters and equipment status signals can be collected from multiple sources. Power grid operating environment parameters may include meteorological data such as temperature, humidity, and wind speed, which can affect the performance of power grid equipment and power transmission. For example, high temperatures may increase wire resistance, increasing transmission losses; strong winds may cause power poles to tilt or even collapse, affecting power delivery. Geographic information, such as topography and altitude, should also be collected, as different geographical environments can influence the layout and construction of the power grid and also have potential impacts on its operation.

[0055] In some specific implementations, for equipment status signals, it is necessary to collect operating parameters of the power generation equipment, such as the generator's output power, speed, and temperature. These parameters reflect the generator's operating status and health condition. For transmission equipment, it is necessary to collect parameters such as transmission line current, voltage, and power factor, as well as equipment status information of substations, such as transformer oil temperature and winding temperature. For distribution equipment, it is necessary to collect information such as the switch status of the distribution cabinet and load current.

[0056] It should be noted that this invention does not limit the specific content of the power grid operating environment parameters and equipment status signals, as long as these parameters and signals can reflect the operating status of the power grid and the equipment status, and can be used to establish subsequent models.

[0057] It should also be noted that after obtaining the power grid operating environment parameters and equipment status signals, considering that these signals may contain noise, missing values, etc., which may affect the accuracy and reliability of subsequent models, they need to be preprocessed first.

[0058] In one specific implementation, for noise processing, filtering algorithms such as mean filtering and median filtering can be used to remove random noise from the signal and make it smoother. For missing value processing, interpolation methods such as linear interpolation and spline interpolation can be used to supplement the missing data, based on the characteristics and distribution of the data.

[0059] In one specific implementation, the data can also be normalized to unify data of different ranges and magnitudes to the same scale, avoiding the impact of excessive differences in data scale on the training and learning effect of the model. The data after the first preprocessing can provide a more accurate and reliable foundation for the subsequent construction of the first dynamic representation model of power grid equipment coupling, enabling the model to better reflect the actual operating state of the power grid and the interrelationships between equipment, and further improve the accuracy and effectiveness of intelligent power grid dispatching.

[0060] It should be noted that the accurate and reliable data obtained after the first preprocessing significantly improves the construction quality of the first dynamic characterization model of the power grid equipment coupling. When constructing the time series forecasting sub-model, precise data enables the model to more accurately capture the changing patterns of power grid node loads, thereby more accurately predicting the short-term load evolution trends of power grid nodes. This allows for more scientific and rational planning of operation strategies for power generation, transmission, and distribution equipment, effectively avoiding power grid faults or instability caused by inaccurate load forecasting.

[0061] S102, construct a first coupled dynamic characterization model of power grid equipment based on the first preprocessed power grid operating environment parameters and equipment status signals, wherein:

[0062] It should be noted that after obtaining the first pre-processed power grid operating environment parameters and equipment status signals, it is necessary to delve deeper into the information to construct the first coupled dynamic characterization model of the power grid equipment. The construction of this model is a complex and crucial process, involving analysis and integration at multiple levels.

[0063] In some specific implementations, the coupled dynamic characterization model of the first power grid equipment can be constructed using various modeling methods. For example, machine learning algorithms, such as neural networks and support vector machines, can be employed. These algorithms have strong nonlinear fitting capabilities and can effectively handle the complex relationships in power grid operation. Taking neural networks as an example, they can be trained using a large amount of historical data to learn the nonlinear response relationships between factors such as climate environment, operating conditions, power generation methods, and load distribution, and the load and voltage stability of power grid nodes.

[0064] In some specific implementations, a physical model can be combined, utilizing the physical principles and fundamental laws of the power grid, such as Kirchhoff's laws, to describe the electrical connections and energy transmission relationships between power grid equipment. By combining the physical model with machine learning algorithms, the advantages of both can be fully utilized, making the first dynamic characterization model of the coupled power grid equipment more accurate and reliable.

[0065] In some specific implementations, the model needs to be continuously validated and optimized during the construction process. Methods such as cross-validation can be used to divide historical data into training and validation sets, and the model's performance is evaluated by its performance on the validation set. If the model's predictions deviate significantly from reality, the model's parameters or structure need to be adjusted until the model achieves satisfactory performance.

[0066] In this embodiment of the invention, constructing the first power grid equipment coupling dynamic characterization model includes:

[0067] A set of key factors affecting the load of power grid nodes is preset, and a time series prediction sub-model is established based on historical operating data and physical mechanisms;

[0068] The time series forecasting sub-model is used to predict the evolution trend of grid node load in the short term.

[0069] A voltage stability assessment sub-model is constructed. The inputs of the voltage stability assessment sub-model are load level, generator output, and line impedance, and the output is the predicted value of voltage stability margin.

[0070] In this embodiment of the invention, constructing the first power grid equipment coupling dynamic characterization model further includes:

[0071] The time series prediction sub-model and the voltage stability assessment sub-model are integrated;

[0072] The first coupled dynamic characterization model of power grid equipment is used to describe the nonlinear response relationship between climate environment, operating conditions, power generation mode and load distribution to the load and voltage stability of power grid nodes.

[0073] Specifically, a set of key factors affecting the load of power grid nodes is pre-defined, and the set of key influencing factors is defined as follows:

[0074]

[0075] in, This represents the set of key factors affecting the load at power grid nodes; T represents ambient temperature in °C, reflecting the impact of air temperature on loads such as air conditioning and heating; H represents relative humidity in %, affecting human comfort and thus indirectly influencing electricity consumption behavior; W represents wind speed in m / s, affecting wind power output and some loads (such as ventilation equipment); L h This represents historical load data, measured in MW, used to capture the time-series characteristics of the load; G o This represents the total current generator output in MW, reflecting the operating status of the power supply side; D t Indicates the date type, which is a categorical variable, such as weekday (0), weekend (1), holiday (2); S p This indicates the projected output of renewable energy sources (such as photovoltaics and wind power), expressed in MW.

[0076] Furthermore, a time series forecasting sub-model (load forecasting) is established using an LSTM model with an attention mechanism for load forecasting:

[0077]

[0078] in, f represents the predicted load values ​​at each node of the power grid at time t, which is an N-dimensional vector with units of MW, where N is the total number of nodes in the power grid; LSTM-Attn X represents a nonlinear prediction function based on a Long Short-Term Memory (LSTM) network and incorporating an attention mechanism; t-n:t This represents the historical input data sequence from time tn to t, including multi-dimensional time series such as temperature, humidity, historical load, and power generation output; n represents the length of the historical time window, in time steps (e.g., one step every 15 minutes, n=96 represents the past 24 hours); This represents the set of key influencing factors mentioned above, which serve as the input features for the model.

[0079] It should be noted that the output of the time series forecasting sub-model is the future T. p Load forecast sequence for each time period

[0080] Furthermore, a voltage stability assessment sub-model is constructed, defining the voltage stability margin as follows:

[0081]

[0082] Where, η vλ represents the voltage stability margin, a scalar value ranging from [0,1], with values ​​closer to 1 indicating greater system stability; λ0 represents the load growth factor corresponding to the current operating point, indicating the multiple of the current load level relative to the base load; λ max The critical load growth factor represents the point at which the system reaches voltage collapse (saddle-node bifurcation point); this value is approximated by the continuous power flow method (CPF) or deep neural network (DNN).

[0083] In some specific implementations, neural networks can be used for modeling in practice:

[0084]

[0085] in, The predicted voltage stability margin is represented by L; the current load vector at each node is represented by G; the output vector of each generator is represented by Y; bus This represents the node admittance matrix, with dimensions N×N, describing the power grid topology and line parameters.

[0086] Furthermore, the first power grid equipment coupled dynamic representation model is constructed, and the overall dynamic representation model is defined as follows:

[0087]

[0088] in, This represents the coupled dynamic characterization model of the first power grid equipment, describing the nonlinear relationship between the environment, operating state, and power grid response; This represents the comprehensive state vector of the system at time t, containing T, H, W, and L. h G o D t S p Y bus wait; This represents the time from t+1 to t+T. p The load forecast sequence, totaling T p step; This represents the voltage stability margin prediction sequence for the corresponding time period; T p Indicates the prediction time domain length, in units of time steps (e.g., T). p =24 indicates a prediction of the next 6 hours, with one step every 15 minutes.

[0089] It should be noted that the first coupled dynamic characterization model of power grid equipment, constructed based on the preprocessed power grid operating environment parameters and equipment status signals, can accurately reflect the nonlinear response relationship between factors such as climate environment, operating conditions, power generation mode, and load distribution on the load and voltage stability of power grid nodes, providing a scientific basis for power grid dispatch. Based on this first coupled dynamic characterization model, reasonable dispatch strategies can be further formulated. For example, based on the short-term load evolution trend of power grid nodes predicted by the time series prediction sub-model, the output of power generation equipment can be adjusted in advance. If a significant increase in load is predicted for a certain period, the output power of generators can be increased in advance to ensure stable power supply. Simultaneously, combined with the voltage stability margin predicted by the voltage stability assessment sub-model, when the margin is low, timely measures can be taken to adjust the power grid operation mode, such as adjusting transformer taps and activating reactive power compensation equipment, to improve voltage stability.

[0090] S103, based on the first coupled dynamic characterization model of power grid equipment, and combining the goals of intelligent power grid dispatching with equipment safety constraints, constructs a second multi-objective collaborative optimization control model, wherein:

[0091] It should be noted that after establishing the first coupled dynamic characterization model of power grid equipment, a second multi-objective collaborative optimization control model needs to be constructed by combining the goals of intelligent power grid dispatching with equipment safety constraints. This model aims to achieve collaborative optimization of multiple goals of power grid dispatching while satisfying various constraints.

[0092] It should also be noted that the goals of smart grid dispatch typically include multiple aspects, such as ensuring the reliability of power supply, improving the economic efficiency of grid operation, and promoting the consumption of renewable energy. Equipment safety constraints, on the other hand, are to ensure that grid equipment operates within safe limits and to avoid equipment overload, overheating, and other situations, such as rated power limits and safe current and voltage ranges.

[0093] In a specific implementation, various optimization algorithms can be employed when constructing the second multi-objective collaborative optimization control model. For example, genetic algorithms have strong global search capabilities and can find optimal scheduling schemes in complex solution spaces. They iteratively update the population by simulating biological evolution, gradually approaching the optimal solution. Particle swarm optimization (PSO) is also a commonly used optimization algorithm. It simulates the collective behavior of flocks of birds or schools of fish, allowing particles to continuously search the solution space until the optimal solution is found.

[0094] In this embodiment of the invention, the second multi-objective collaborative optimization and control model includes an upper-level global load optimization objective function and a lower-level local power grid precise control objective function;

[0095] In this embodiment of the invention, the objectives of smart grid dispatching and equipment security constraints include:

[0096] The objectives of intelligent power grid dispatching include minimizing the overall power grid load, minimizing the deviation between the power grid node load and the set value, and minimizing the probability of voltage instability.

[0097] Equipment safety constraints include at least the equipment's rated power limit, equipment operating time limit, equipment start-stop frequency limit, equipment environmental adaptability constraint, and equipment maintenance cycle constraint.

[0098] In an embodiment of the present invention, the second multi-objective collaborative optimization control model includes:

[0099] The objective function for global load optimization at the upper level aims to minimize the overall load on the power grid.

[0100] The overall load of the power grid includes generation load, transmission load, and distribution load.

[0101] The objective function for precise control of the lower-level local power grid aims to minimize the deviation between the load at the grid nodes and the set value, as well as to minimize the probability of voltage instability.

[0102] Specifically, the objective function for optimizing the global load at the upper level can be expressed as follows:

[0103]

[0104] Where J1(u) represents the upper-level objective function value, which represents the weighted sum of the overall load of the power grid; u represents the control variable vector, including generator output, reactive power compensation, transformer tap changers, etc.; α1 and α2 represent weighting coefficients, satisfying α1 + α2 = 1, used to balance generator output and network losses; P g (t) represents the total power generation at time t, in MW; P loss (t) represents the total power loss of the power grid (transmission + distribution) at time t, in MW; T p This indicates the length of the optimized time domain, expressed in time steps.

[0105] It should be noted that the output of the upper-level global load optimization objective function is to minimize the total power generation and grid loss, thereby improving energy utilization efficiency.

[0106] Furthermore, the objective function for precise control of the lower-level local power grid can be expressed as follows:

[0107]

[0108] Where J2(u) represents the lower-level objective function value, reflecting local control performance; u represents the control variable as above; β1 and β2 represent weighting coefficients, satisfying β1 + β2 = 1, used to balance load deviation and voltage stability; L i (t) represents the actual load of node i at time t, in MW; η represents the load setpoint (such as planned or reference value) for node i, in MW; v,i (t) represents the voltage stability margin of node i at time t, ranging from [0,1]; N represents the total number of load nodes in the power grid; T p This indicates the optimized time domain length.

[0109] It should be noted that the objective function of the precise control of the lower-level local power grid aims to make the load of each node close to the set value, while maintaining a voltage stability margin close to 1.

[0110] Furthermore, it is necessary to fuse the upper-level global load optimization objective function with the lower-level local power grid precise control objective function to obtain a second multi-objective collaborative optimization control model, which can be specifically represented as follows:

[0111]

[0112] Where J(u) represents the comprehensive objective function, used to unify the optimization of upper and lower level objectives; w1 and w2 represent the multi-objective weight coefficients, satisfying w1+w2=1, which can be determined by AHP, entropy weight method or Pareto analysis; J1(u) represents the upper level global load optimization objective; J2(u) represents the lower level local precision control objective.

[0113] Furthermore, the equipment safety constraints are designed as follows:

[0114] ① Rated power limit:

[0115]

[0116] Among them, P i (t) represents the actual output or load of equipment i at time t, in MW; P i min P represents the minimum permissible output power of device i, in MW; i max This represents the maximum rated output of device i, in MW; This refers to the collection of all power-limited devices (such as generators, energy storage, transformers, etc.).

[0117] ②Minimum start-stop time constraint:

[0118]

[0119] Among them, u i (t) represents the start / stop state of device i at time t, u i (t) = 1 indicates operation, u i (t) = 0 indicates shutdown; T i on,minT represents the minimum continuous operating time of device i, in time steps; i off,min This represents the minimum continuous downtime of device i, expressed in time steps.

[0120] ③Start-stop frequency limit:

[0121]

[0122] Among them, |u i (t)-u i (t-1)| indicates whether device i undergoes a state transition (0→1 or 1→0) at time t; This indicates the maximum number of start-stop operations allowed for device i during the entire optimization cycle; the total number of switches does not exceed [a certain number]. (Each start-stop cycle involves two state changes).

[0123] ④ Environmental adaptability constraints:

[0124]

[0125] in, The wind turbine i represents the operating state of the wind turbine i; W(t) represents the wind speed at time t, in m / s; V in This indicates the cut-in wind speed of the wind turbine; it will not start if the wind speed is below this value; V out This indicates the cut-out wind speed of the wind turbine unit. If the speed exceeds this value, the unit must be shut down for protection.

[0126] ⑤ Maintenance cycle constraints:

[0127]

[0128] Among them, u i (t) represents the start / stop state of device i at time t; [t a ,t b [] indicates the planned maintenance period for device i, in time steps; during this period, the device is forcibly shut down and cannot participate in scheduling.

[0129] It is important to note that equipment maintenance cycle constraints are a crucial aspect of ensuring the long-term stable operation of power grid equipment. Reasonably scheduling equipment maintenance cycles not only reduces the probability of equipment failure but also extends equipment lifespan and mitigates risks to power grid operation. By forcibly shutting down equipment during planned maintenance periods, potential safety hazards from continued operation during maintenance are avoided. This also provides maintenance personnel with a safe working environment, facilitating comprehensive inspection, repair, and maintenance of the equipment.

[0130] In actual power grid dispatching, the constraints of equipment maintenance cycles must be fully considered. Dispatchers must plan ahead for adjusting the output of generating equipment and allocating loads based on the equipment maintenance schedule. For example, before a generator enters its maintenance cycle, the output of other generators should be increased in advance to ensure the continuity and stability of power supply. At the same time, the impact of the maintenance cycle on the overall operation of the power grid must be considered, potential risks must be assessed, and corresponding contingency plans must be developed.

[0131] Furthermore, with the continuous expansion of the power grid and the increase in the number of devices, the management of equipment maintenance cycles has become more complex. Advanced information technology and data analysis methods can be used to monitor and analyze the operating status of equipment in real time, predict potential equipment failures and the timing of maintenance, thereby enabling more scientific and rational scheduling of maintenance plans. This allows for meeting equipment maintenance needs while minimizing the impact on the normal operation of the power grid, achieving efficient, safe, and stable power grid dispatch.

[0132] S104, Solve the second multi-objective collaborative optimization control model, and perform intelligent power grid dispatching based on the solution results, wherein:

[0133] It should be noted that once the second multi-objective collaborative optimization control model is obtained, it can be solved. There are many methods for solving this model, such as mathematical programming methods, like linear programming and nonlinear programming, which can find the optimal solution of the objective function under the constraints. There are also intelligent optimization algorithms, such as ant colony optimization and simulated annealing, which can search for better scheduling schemes in complex solution spaces.

[0134] During the solution process, it is crucial to fully consider all constraints in the model, especially the maintenance cycle constraints of the equipment. This constraint directly affects the availability of equipment within a specific time period, and consequently, the overall power grid dispatch strategy. For example, if a critical transformer is under maintenance, it cannot be relied upon for power transmission and distribution during this period, necessitating a readjustment of the operating parameters of other transformers and load allocation.

[0135] In an embodiment of the present invention, solving the second multi-objective collaborative optimization control model includes a preset first improved solution strategy, which includes improvements based on model predictive control and particle swarm optimization.

[0136] In this embodiment of the invention, intelligent power grid scheduling based on the solution results includes:

[0137] Based on the solution results, generate the optimal start-up, shutdown, and regulation command sequence for power generation, transmission, and distribution equipment in the future time period;

[0138] The optimal start / stop and adjustment command sequence is sent to the field execution unit;

[0139] After receiving the optimal start-stop and regulation command sequence, the field execution unit controls the power generation, transmission, and distribution equipment to perform corresponding start-stop and regulation operations according to the command sequence.

[0140] Specifically, the Model Predictive Control (MPC) framework is designed to perform the following rolling optimization at each time t:

[0141] Get the current state

[0142] use predict

[0143] Establish an optimization problem minJ(u) that satisfies all security constraints;

[0144] Solving the optimal control sequence u using an improved PSO * (t:t+T p -1);

[0145] Execute u * (t), discard subsequent plans and re-optimize at t+1;

[0146] Furthermore, an improved Particle Swarm Optimization (PSO) algorithm is designed, with an adaptive inertia weight update formula:

[0147]

[0148] Where ω(t) represents the inertia weight at the t-th iteration; ω max This represents the initial inertia weight, typically taken as 0.9; ω min The final inertia weight is represented, typically 0.4; t represents the current iteration number; T max This indicates the maximum number of iterations.

[0149] It should be noted that in this invention, high weights in the early stages are beneficial for global search, while low weights in the later stages are beneficial for fine-grained local search.

[0150] Furthermore, particle velocity and position updates:

[0151]

[0152] in, This represents the velocity vector of particle i at the k-th iteration; p represents the current position of particle i (i.e., a set of control variables); best,i G represents the historical best position of particle i; bestc1 and c2 represent the historical best position of the entire group; c1 and c2 represent the learning factors, usually 2.0; r1 and r2 represent random numbers in [0,1]; k represents the number of iterations.

[0153] Furthermore, we design the overall objective function with a penalty. After introducing the penalty function, the problem is transformed into an unconstrained problem:

[0154]

[0155] Among them, J total (u) represents the overall objective function after adding the penalty; J(u) represents the original objective function; g j (u)≤0 indicates the j-th inequality constraint (such as a power limit); γ represents the penalty coefficient, which takes a large positive value (such as 10). 4 ); m represents the total number of constraints.

[0156] It should be noted that solving the second multi-objective collaborative optimization control model and using the results for intelligent grid dispatch can fully utilize the efficiency of grid equipment and achieve optimal allocation of power resources. In practical applications, real-time monitoring and evaluation of the dispatch results are also necessary. By establishing a comprehensive monitoring system, real-time operational data of the grid, including parameters such as power generation output, load changes, voltage, and frequency, can be acquired and compared with the dispatch results. If deviations are found between the actual operating conditions and the dispatch plan, the dispatch strategy should be adjusted promptly to ensure the stable operation of the grid.

[0157] In summary, this invention proposes an intelligent power grid dispatching method. By constructing a first dynamic characterization model of coupled power grid equipment, it comprehensively and dynamically reflects the interrelationships and operating states among power grid equipment, providing a solid foundation for subsequent optimization and control. The establishment of a second multi-objective collaborative optimization and control model combines global load optimization with precise local power grid control, enabling power grid dispatching to achieve rational load allocation at the macro level while ensuring stable operation of local power grids at the micro level. Compared with traditional power grid dispatching methods, this invention no longer relies on single empirical judgments or simple control strategies, but instead makes dispatching decisions based on precise models and multi-objective optimization algorithms. This significantly improves the power grid's ability to cope with complex operating environments and emergencies, such as extreme weather or equipment failures, allowing for rapid adjustment of dispatching schemes to ensure the safe and reliable operation of the power grid.

[0158] Meanwhile, this invention also reduces power grid operating costs. By optimizing the upper-level global load objective function, power generation resources are rationally allocated, unnecessary power generation losses are reduced, and efficient energy utilization is achieved. The lower-level local power grid precise control objective function ensures the stability of parameters such as voltage and frequency of the local power grid, reducing equipment losses and maintenance costs.

[0159] Example 2, in a preferred embodiment, the steps for solving the second multi-objective collaborative optimization control model and performing intelligent power grid dispatching based on the solution results can be as follows:

[0160] At each scheduling time t, the system executes the following process:

[0161] Predicting Future States: Using the "Coupled Dynamic Characterization Model of First Power Grid Equipment" to Predict Future State T p Load and voltage stability over a time period (e.g., the next 6 hours, every 15 minutes);

[0162] Constructing the optimization problem: Based on the prediction results, establish a multi-objective optimization model that includes upper and lower level objectives and equipment safety constraints;

[0163] Solving for the optimal instruction sequence: using an improved PSO algorithm to solve for the future T p The optimal control commands for each step (such as unit start-up and shutdown, output adjustment);

[0164] Execute the first step instruction: Only execute the first step u in the optimal sequence. * (t), the rest are discarded;

[0165] Rolling updates: At the next time step t+1, data is collected again, predictions are re-made, and optimizations are re-optimized, forming a closed-loop feedback. This is the "rolling time-domain optimization" mechanism of MPC, which can effectively cope with the uncertainties and dynamic changes in power grid operation.

[0166] Furthermore, generate and issue instruction sequences, and generate the optimal start-stop and adjustment instruction sequences. Let the optimal solution be:

[0167] U * ={u * (t),u * (t+1),…,u * (t+T p -1)}

[0168] Among them, U * Indicates the future T p The optimal control command sequence for each time period; u * (t) represents the control vector to be executed at time t, which includes: generator output setpoint; unit start / stop command (0 / 1); reactive power compensation device switching; transformer tap adjustment, etc.

[0169] Furthermore, instructions are issued via dispatch communication networks (such as IEC61850, DNP3) to: the power plant's DCS system; the substation's RTU or IED; and the distribution automation terminal (FTU / DTU). Field equipment receives and executes the instructions, adjusting generators, circuit breakers, SVCs, etc. The execution results are fed back to the dispatch center for the next round of rolling optimization.

[0170] Example 3, referring to Figure 2 This embodiment also provides a smart grid dispatching system, including:

[0171] The data acquisition and processing module is used to acquire power grid operating environment parameters and equipment status signals, and to perform the first preprocessing on the power grid operating environment parameters and equipment status signals;

[0172] The first model building module is used to construct a first power grid equipment coupled dynamic characterization model based on the first preprocessed power grid operating environment parameters and equipment status signals.

[0173] The second model building module is used to construct a second multi-objective collaborative optimization control model based on the first power grid equipment coupled dynamic representation model and combined with the power grid intelligent dispatching objectives and equipment safety constraints.

[0174] The second multi-objective collaborative optimization control model includes an upper-level global load optimization objective function and a lower-level local power grid precise control objective function.

[0175] The solution module is used to solve the second multi-objective collaborative optimization control model, and to perform intelligent power grid scheduling based on the solution results.

[0176] The above-mentioned unit modules can be embedded in the processor of the electronic device in hardware form or independent of it, or they can be stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of the above modules.

[0177] This embodiment also provides an electronic device, which can be a terminal, and its internal structure diagram can be as follows: Figure 2 As shown, the electronic device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a smart grid dispatching method. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the device's casing, or an external keyboard, touchpad, or mouse.

[0178] This embodiment also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it performs the following steps:

[0179] Collect power grid operating environment parameters and equipment status signals, and perform the first preprocessing on the power grid operating environment parameters and equipment status signals;

[0180] A first dynamic characterization model of power grid equipment is constructed based on the preprocessed power grid operating environment parameters and equipment status signals.

[0181] Based on the first coupled dynamic characterization model of power grid equipment, and combined with the goals of intelligent power grid dispatching and equipment safety constraints, a second multi-objective collaborative optimization control model is constructed.

[0182] The second multi-objective collaborative optimization control model includes an upper-level global load optimization objective function and a lower-level local power grid precise control objective function.

[0183] Solve the second multi-objective collaborative optimization control model, and perform intelligent power grid dispatching based on the solution results.

[0184] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0185] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0186] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A power grid intelligent dispatching method, characterized in that, The method comprises the following steps: Collecting power grid operation environment parameters and equipment state signals, and performing first preprocessing on the power grid operation environment parameters and equipment state signals; According to the first pre-processed power grid operation environment parameters and equipment state signals, a first power grid equipment coupling dynamic modeling model is constructed; Based on the first power grid equipment coupling dynamic modeling model, combined with the power grid intelligent scheduling target and the equipment safety constraint, a second multi-objective collaborative optimization control model is constructed; The second multi-objective collaborative optimization control model includes an upper global load optimization objective function and a lower local power grid precise control objective function; Solving the second multi-objective collaborative optimization control model, and performing power grid intelligent scheduling according to the solving result.

2. The power grid intelligent dispatching method of claim 1, wherein, The power grid intelligent scheduling according to the solving result comprises the following steps: According to the solving result, the optimal start-stop and adjustment instruction sequence of the power generation, power transmission and power distribution equipment in the future period is generated; The optimal start-stop and adjustment instruction sequence is sent to the field execution unit; After the field execution unit receives the optimal start-stop and adjustment instruction sequence, the power generation, power transmission and power distribution equipment are controlled to perform corresponding start-stop and adjustment operations according to the instruction sequence.

3. The method of claim 2, wherein, The construction of the first power grid equipment coupling dynamic modeling model comprises the following steps: A set of key factors affecting the power grid node load is preset, and a time series prediction sub-model is established based on historical operation data and physical mechanism; The time series prediction sub-model is used to predict the evolution trend of the power grid node load in the future short time; A voltage stability evaluation sub-model is constructed, and the input of the voltage stability evaluation sub-model is the load level, the generator output and the line impedance, and the output is the voltage stability margin prediction value.

4. The power grid intelligent dispatching method of claim 3, wherein, The construction of the first power grid equipment coupling dynamic modeling model further comprises the following steps: Fusion of the time series prediction sub-model and the voltage stability evaluation sub-model; The first power grid equipment coupling dynamic modeling model is used to describe the nonlinear response relationship of climate environment, operation condition, power generation mode and load distribution to power grid node load and voltage stability.

5. The method of claim 4, wherein, The second multi-objective collaborative optimization control model comprises: The upper global load optimization objective function aims to minimize the overall load of the power grid; The overall load of the power grid includes the load on the power generation side, the load on the power transmission side and the load on the power distribution side; The lower local power grid precise control objective function aims to minimize the deviation of the power grid node load from the set value and minimize the voltage instability probability.

6. The method of claim 5, wherein, The power grid intelligent scheduling target and the equipment safety constraint comprise: The power grid intelligent scheduling target includes minimizing the overall load of the power grid, minimizing the deviation of the power grid node load from the set value, and minimizing the voltage instability probability; The equipment safety constraint at least includes the rated power limit of the equipment, the operation time limit of the equipment, the start-stop frequency limit of the equipment, the environmental adaptability constraint of the equipment and the maintenance cycle constraint of the equipment.

7. The method of claim 6, wherein, The solving of the second multi-objective collaborative optimization control model comprises presetting a first improved solving strategy, and the first improved solving strategy comprises improvement based on model predictive control and particle swarm optimization.

8. A power grid intelligent dispatching system, applying the method of any one of claims 1-7, characterized in that, The method comprises the following steps: A data acquisition and processing module is used to collect power grid operation environment parameters and equipment state signals, and perform first preprocessing on the power grid operation environment parameters and equipment state signals; The first model establishing module is configured to construct a first power grid equipment coupling dynamic characterization model according to the first preprocessed power grid operation environment parameters and the equipment state signals; The second model establishing module is configured to construct a second multi-objective collaborative optimization control model based on the first power grid equipment coupling dynamic characterization model, in combination with a power grid intelligent dispatching target and equipment safety constraints; The second multi-objective collaborative optimization control model comprises an upper-layer global load optimization target function and a lower-layer local power grid precise control target function; The solving module is configured to solve the second multi-objective collaborative optimization control model and perform power grid intelligent dispatching according to a result of the solving. 9.An electronic device comprising a memory and a processor, the memory storing a computer program, wherein, The computer program is executed by the processor to implement the steps of the power grid intelligent dispatching method in any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the power grid intelligent dispatching method in any one of claims 1-7.

Images