Power grid management and control method based on artificial intelligence and related equipment

Abstract

The embodiment of the present application relates to the technical field of smart grid, and discloses a power grid management and control method based on artificial intelligence and related equipment, which comprises the following steps: collecting real-time power grid data of a current period of power grid equipment; inputting the real-time power grid data into a power grid state prediction model to predict a current power grid operation state; inputting the current power grid operation state and the real-time power grid data into a power grid strategy dynamic optimization module to generate a new power distribution strategy; setting power grid control parameters according to the new power distribution strategy and the real-time power grid data, and executing the new power distribution strategy; when a preset optimization period is reached, performing power grid resource dynamic optimization according to the current power grid operation state and real-time resource data by using a power grid resource dynamic optimization algorithm to obtain an optimized power grid resource optimization scheme. The embodiment of the present application realizes real-time monitoring of the power grid state and optimal distribution of power resources.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the technical field of smart grid, in particular to a power grid management and control method based on artificial intelligence and related equipment. BACKGROUND

[0002] At present, with the growth of global energy demand and the rapid development of new energy technology, smart grid has become the key to the modernization of power systems. Smart grid uses information communication technology, advanced measurement technology, automation technology and artificial intelligence to realize efficient, reliable and environmentally friendly operation of the power grid. However, although smart grid technology has made significant progress, existing systems still face the following technical problems in practical application:

[0003] 1. Insufficient data processing capacity: Existing power grid management systems often rely on traditional data processing methods when dealing with large-scale, high-frequency energy data. These methods are difficult to meet the real-time optimization requirements in terms of processing speed and accuracy.

[0004] 2. Limited prediction accuracy: Power load forecasting is critical to optimizing power distribution, but existing prediction models are usually based on historical data and simple statistical methods, which are difficult to adapt to complex and changing power grid environments, resulting in inaccurate predictions.

[0005] 3. Lack of adaptive ability: Existing power grid management software often lacks sufficient adaptive ability to automatically adjust management strategies according to changes in power grid operating conditions, limiting the system's response capability in the face of emergencies.

[0006] 4. Poor user interaction experience: The user interface design is not intuitive and the operation is complex, making it difficult for power grid managers to quickly understand and control system status, affecting management efficiency.

[0007] 5. Difficulty integrating new energy: With the integration of solar, wind and other new energy sources, existing power grid management systems face challenges in handling these intermittent and unpredictable energy sources, lacking effective integration and management strategies. SUMMARY

[0008] In view of the above problems, the embodiment of the present application provides a power grid management and control method based on artificial intelligence and related equipment to solve the problems of insufficient data processing capacity and low prediction accuracy in the prior art.

[0009] According to an aspect of the embodiment of the present application, a power grid management and control method based on artificial intelligence is provided, the method comprising:

[0010] Collecting real-time power grid data of the current period of the power grid equipment; the real-time power grid data includes power output, load demand, voltage fluctuation data and weather condition data;

[0011] Inputting the real-time grid data into a grid state prediction model to predict the current grid operating state; the current grid operating state includes load peak period, anomaly detection information, and grid fault location information; wherein the grid state prediction model is obtained by pre-training a deep learning network based on grid state sample data, and the grid state sample data includes historical grid operating data and corresponding sample labels;

[0012] Inputting the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy;

[0013] According to the new power distribution strategy and the real-time power grid data, setting power grid control parameters and executing the new power distribution strategy;

[0014] When the preset optimization cycle is reached, the grid resources are dynamically optimized using a grid resource dynamic optimization algorithm based on the current grid operating status and real-time resource data to obtain an optimized grid resource optimization plan; wherein, the grid resource dynamic optimization algorithm includes a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data includes load demand information, renewable energy power generation, remaining capacity of the energy storage system, grid topology structure and external factor data.

[0015] In an optional manner, before inputting the real-time power grid data into the power grid state prediction model to predict the current power grid operation state, the method further includes:

[0016] Collecting historical grid operation data; the historical grid operation data includes historical power production, historical load demand, historical voltage fluctuation data, and historical weather condition data;

[0017] Adding corresponding sample tags to the historical operation data of the power grid to obtain power grid status sample data; the sample tags include the corresponding historical operation status of the power grid, and the historical operation status tags of the power grid include a load peak period tag, an anomaly detection information tag, and a power grid fault location information tag;

[0018] The grid state sample data is input into a deep learning network for iterative training, and the parameters of the deep learning network are adjusted to obtain a trained grid state prediction model.

[0019] In an optional manner, the deep learning network includes a time series prediction module, a spatial correlation prediction module, and an anomaly detection module; wherein the time series prediction module includes one of a self-attention mechanism and a CNN-LSTM hybrid model; the spatial correlation prediction module includes a GNN algorithm; and the anomaly detection module includes a variational autoencoder;

[0020] The step of inputting the grid state sample data into a deep learning network for iterative training and adjusting the parameters of the deep learning network to obtain a trained grid state prediction model includes:

[0021] Inputting the grid state sample data into a self-attention mechanism or a CNN-LSTM hybrid model for training to obtain a time series prediction module for predicting load peak period prediction results;

[0022] Inputting the grid state sample data into a GNN algorithm for training to obtain a spatial correlation prediction module for locating grid faults;

[0023] The grid state sample data is input into a variational autoencoder for training to obtain an anomaly detection module for detecting abnormal events.

[0024] In an optional manner, collecting real-time grid data of grid equipment in the current period includes:

[0025] Collecting power generation information of each power generation device in the power grid to obtain power generation data; the power generation equipment includes thermal power plants, hydropower stations, wind power stations and solar photovoltaic systems;

[0026] Obtain real-time load data from load monitoring equipment in substations and distribution networks to obtain load demand;

[0027] Voltage fluctuations are monitored and recorded by voltage sensors installed at key nodes of the power grid, and voltage fluctuation data is collected;

[0028] Obtain weather data that affects energy production and consumption through communication with meteorological service centers.

[0029] In an optional manner, inputting the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy includes:

[0030] Evaluate the effectiveness of a current power distribution strategy and identify areas for improvement based on the current power grid operating status and the real-time power grid data;

[0031] Generating a new power distribution strategy according to a preset adjustment strategy based on the improvement points and the current power grid operation status;

[0032] Conducting simulation tests on the new power distribution strategy;

[0033] When the test passes, the new power distribution strategy is applied to grid management.

[0034] In an alternative mode, when the preset optimization period is reached, the power grid resource dynamic optimization algorithm is used to perform power grid resource dynamic optimization according to the current power grid operation state and real-time resource data, and an optimized power grid resource optimization scheme is obtained, including:

[0035] According to the traditional power generation fuel cost, energy storage loss cost, new energy abandoned power penalty and voltage deviation, a multi-objective function is determined; wherein, the power balance constraint, energy storage dynamic constraint and power grid equipment limit constraint are set;

[0036] When the preset optimization period is reached, the multi-objective function is optimized by using the reinforcement learning adaptive strategy according to the current power grid operation state and real-time resource data, and an optimized power grid resource optimization scheme is obtained.

[0037] In an alternative mode, the method further includes: displaying the current power grid operation state and the optimized power grid resource optimization scheme in a user interface.

[0038] According to another aspect of the embodiment of the application, a power grid management and control system based on artificial intelligence is provided, including:

[0039] The acquisition module is configured to acquire real-time power grid data of the power grid equipment in the current period; the real-time power grid data includes power output, load demand, voltage fluctuation data and weather condition data;

[0040] The prediction module is configured to input the real-time power grid data into a power grid state prediction model to predict a current power grid operation state; the current power grid operation state includes whether it is a load peak period and whether the voltage is abnormal; wherein, the power grid state prediction model is obtained by pre-training a deep learning network according to power grid state sample data, and the power grid state sample data includes power grid historical operation data and corresponding sample labels;

[0041] The power strategy module is configured to input the current power grid operation state and the real-time power grid data into a power grid strategy dynamic optimization module to generate a new power distribution strategy;

[0042] The execution module is configured to set power grid control parameters according to the new power distribution strategy and the real-time power grid data, and execute the new power distribution strategy;

[0043] The resource optimization module is used to dynamically optimize the power grid resources using a power grid resource dynamic optimization algorithm based on the current power grid operating status and real-time resource data when a preset optimization cycle is reached, thereby obtaining an optimized power grid resource optimization plan; wherein the power grid resource dynamic optimization algorithm includes a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data includes load demand information, renewable energy power generation, remaining capacity of the energy storage system, power grid topology structure and external factor data.

[0044] According to another aspect of an embodiment of the present invention, there is provided a computer device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0045] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the operation of the artificial intelligence-based power grid management and control method.

[0046] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores at least one executable instruction. When the executable instruction is executed on a computer device, the computer device executes the operation of the artificial intelligence-based power grid management and control method.

[0047] The embodiment of the present invention collects real-time grid data of the current period of grid equipment; inputs the real-time grid data into a grid state prediction model to predict the current grid operation state; inputs the current grid operation state and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy; sets grid control parameters according to the new power distribution strategy and the real-time grid data, and executes the new power distribution strategy; when a preset optimization cycle is reached, a grid resource dynamic optimization algorithm is used to dynamically optimize the grid resources according to the current grid operation state and real-time resource data to obtain an optimized grid resource optimization solution, which can improve the data processing capability, prediction accuracy and adaptability of the grid management system, while optimizing the user interaction interface, enhancing the integration and management of new energy, and realizing real-time monitoring of the grid operation state, load forecasting, fault diagnosis and optimal allocation of power resources, thereby reducing operating costs, improving energy utilization, and supporting the development of sustainable energy.

[0048] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to more clearly understand the technical means of the embodiments of the present invention, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the drawings. In the drawings:

[0050] Figure 1 A schematic diagram of a process flow of an artificial intelligence-based power grid management and control method provided by an embodiment of the present invention is shown;

[0051] Figure 2 A schematic diagram of a flow chart of an artificial intelligence-based power grid management and control method provided in one embodiment of the present invention is shown;

[0052] Figure 3 A schematic diagram of the structure of an artificial intelligence-based power grid management and control system provided by an embodiment of the present invention is shown;

[0053] Figure 4 A schematic structural diagram of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0054] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0055] Figure 1 The flowchart of the power grid control method based on artificial intelligence provided by an embodiment of the present invention is shown, and the method is executed by a computer device. The computer device can be an electronic device that deploys an artificial intelligence-based power grid control system, or a computer, distributed device, edge processing device, etc. that communicates with various power grid devices. The embodiment of the present invention does not impose specific restrictions. Figure 1 As shown, the method includes the following steps:

[0056] Step 110: Collect real-time grid data of the grid equipment in the current period.

[0057] The real-time power grid data includes power production, load demand, voltage fluctuation data and weather condition data. In the embodiment of the present invention, the real-time power grid data is obtained by the following method:

[0058] Power generation information is collected from each power generation device in the power grid to obtain power generation data. The power generation devices include thermal power plants, hydropower stations, wind power stations, and solar photovoltaic systems. In an embodiment of the present invention, a computer device is integrated with each power generation device to collect power generation information from each device. Real-time load data is obtained from load monitoring devices in substations and distribution networks. This data reflects power demand over different time periods, thereby obtaining load demand.

[0059] Voltage fluctuation data is collected by monitoring and recording voltage fluctuation and stability information through voltage sensors installed at key nodes of the power grid.

[0060] By communicating with the meteorological service center, weather data that affects energy production and consumption can be obtained. Specifically, the API interface of the meteorological service center can be connected to obtain weather data that affects energy production and consumption, such as temperature, wind speed, precipitation, etc.

[0061] Step 120: Input the real-time grid data into a grid state prediction model to predict the current grid operation state.

[0062] The current grid operating status includes information on peak load periods, abnormal voltage detection, and other information, as well as grid fault location. The grid status prediction model is obtained by pre-training a deep learning network based on grid status sample data, which includes historical grid operation data and corresponding sample labels.

[0063] In an embodiment of the present invention, before real-time grid data is input into the grid state prediction model, the grid state prediction model is trained in advance. The specific training process includes:

[0064] Step 001: Collect historical grid operation data; the historical grid operation data includes historical power production, historical load demand, historical voltage fluctuation data, and historical weather condition data. After obtaining the historical grid operation data, the data is pre-processed and cleaned and standardized to eliminate noise and outliers.

[0065] Step 002: Add corresponding sample tags to the historical grid operation data to obtain grid status sample data, wherein the sample tags include the corresponding historical grid operation status, and the historical grid operation status tags include load peak period tags, anomaly detection information tags, and grid fault location information tags.

[0066] Step 003: Input the grid state sample data into a deep learning network for iterative training, and adjust the parameters of the deep learning network to obtain a trained grid state prediction model.

[0067] The embodiment of the present invention designs the architecture of the deep learning network according to the characteristics of the power grid data and the requirements of the prediction task, and selects the appropriate network type, number of layers, number of neurons, activation function and loss function. Specifically, the architecture of the deep learning network includes a time series prediction module, a spatial correlation prediction module and an anomaly detection module. Among them, the time series prediction module includes one of the self-attention mechanism and the CNN-LSTM hybrid model; the spatial correlation prediction module includes the GNN algorithm; and the anomaly detection module includes a variational autoencoder. Time series prediction tasks, such as load forecasting, are performed through the self-attention mechanism or the CNN-LSTM hybrid model. Therefore, the power grid status sample data is input into the deep learning network for iterative training. The specific process is as follows:

[0068] Step 030: The grid status sample data is fed into a self-attention mechanism or a CNN-LSTM hybrid model for training to generate a time series prediction module for predicting peak load periods. The Transformer uses an attention mechanism to capture global dependencies, making it suitable for long-sequence prediction. In the CNN-LSTM hybrid model, the CNN is used to extract spatial features, while the LSTM is used to process temporal features.

[0069] Step 031: The grid status sample data is fed into a GNN algorithm for training to develop a spatial correlation prediction module for grid fault location. GNNs (Graph Neural Networks) process the grid as a graph structure, where nodes represent grid devices and edges represent connections. GNNs are used to handle tasks with strong spatial correlation, such as grid fault location.

[0070] Step 032: Input the grid state sample data into a variational autoencoder for training to obtain an anomaly detection module for detecting abnormal events.

[0071] The embodiment of the present invention selects a loss function based on the task type. For regression tasks, MSE (mean squared error) is used. This loss function is sensitive to outliers and suitable for stable data. Cross-entropy loss is used for classification tasks. During training, the model is initialized: network parameters such as weights and biases are initialized. The initial values ​​of these parameters have an important impact on the training effect of the model. Training execution: Model training is performed using a part of the dataset as the training set. The predicted output is calculated through forward propagation, and the network parameters are updated according to the gradient calculated by the loss function through the backpropagation algorithm. Hyperparameter tuning: Hyperparameters such as the learning rate, batch size, and number of training rounds are adjusted to improve the convergence speed and prediction performance of the model. Model validation: Model performance is evaluated using a validation set, cross-validation is performed to avoid overfitting, and the model structure or hyperparameters are adjusted based on the validation results. Model testing: The final performance of the model is evaluated on an independent test set to ensure that the model has good generalization ability. Model iteration: The model is iteratively optimized based on the test results until the preset performance level is reached.

[0072] After the trained grid state prediction model is obtained, the real-time grid data is preprocessed and input into the grid state prediction model to obtain the current grid operation state; the current grid operation state includes the load peak period, anomaly detection information and grid fault location information.

[0073] The embodiment of the present invention also extracts knowledge from the trained grid state prediction model, such as typical modes of grid operation, key influencing factors, etc., to provide decision support for intelligent management of the grid.

[0074] Step 130: Input the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy.

[0075] Among them, the power grid strategy dynamic optimization module constructs the objective function according to the key factors of power distribution, and optimizes it to obtain the power distribution strategy.

[0076] Step 140: According to the new power distribution strategy and the real-time power grid data, grid control parameters are set and the new power distribution strategy is executed.

[0077] Among them, based on the current grid operation status and the real-time grid data, the effectiveness of the current power distribution strategy is evaluated and improvement points are identified; based on the improvement points and the current grid operation status, a new power distribution strategy is generated according to a preset adjustment strategy; a simulation test is performed on the new power distribution strategy; when the test passes, the new power distribution strategy is applied to grid management.

[0078] Step 150: When the preset optimization period is reached, a power grid resource dynamic optimization algorithm is used to perform dynamic optimization of the power grid resource according to the current power grid operation status and real-time resource data to obtain an optimized power grid resource optimization plan.

[0079] Among them, the dynamic optimization algorithm of power grid resources includes a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data includes load demand information, new energy power generation, remaining capacity of energy storage system, power grid topology structure and external factor data.

[0080] When the preset optimization cycle is reached, the multi-objective function is optimized using a reinforcement learning adaptive strategy according to the current grid operation status and real-time resource data to obtain an optimized grid resource optimization plan.

[0081] Specifically, in an embodiment of the present invention, a multi-objective function is determined based on traditional power generation fuel costs, energy storage loss costs, and voltage deviations; wherein power balance constraints, energy storage dynamic constraints, and grid equipment limitation constraints are set.

[0082] In one embodiment of the present invention, the objective function can be expressed as: in, is the cost of traditional power generation fuel, (t) is the energy storage loss cost, is the voltage deviation. , and is the weight coefficient, which is dynamically adjusted during the reinforcement learning process.

[0083] The power balance constraint equation is defined based on the relationship between stored power, acquired power, and updated power, as well as load power and lost power. Dynamic energy storage constraints are also set, such as the thermal power ramp rate, energy storage SOC range, and grid equipment constraints. Grid equipment constraints ensure voltage stability within a ±5% threshold.

[0084] In the embodiment of the present invention, the process of learning reinforcement is: ;in, Indicates the current state, such as load demand and renewable energy output. a indicates an action, such as energy storage charge and discharge instructions. Represents an immediate reward, such as a cost reduction value. is the learning rate, Represents the discount factor.

[0085] The optimization window is updated every 5 minutes, and the optimal solution is recalculated based on the latest data. The state space (s) includes both discrete and continuous variables. Discrete variables include load level (high / medium / low), new energy penetration rate, and energy storage SOC range. Continuous variables include voltage deviation and real-time electricity price.

[0086] The set action space (a) includes discrete actions and continuous actions. Discrete actions include starting and stopping hydropower and forcing solar / wind curtailment commands; continuous actions include adjusting the thermal power output percentage and energy storage charging and discharging power.

[0087] Through the Q-learning algorithm, the optimization weights are dynamically adjusted based on historical operational feedback, including degradation of energy storage charging and discharging efficiency.

[0088] Through the above process, a hybrid algorithm combining model predictive control (MPC) and reinforcement learning (RL) is adopted to achieve dynamic optimal allocation of power grid resources.

[0089] One embodiment of the present invention further includes displaying the current grid operating status and the optimized grid resource optimization plan on a user interface. This intuitive user interface allows grid managers to easily monitor system status, view real-time data and forecast results, and execute control commands. The interface supports multi-platform access, including desktops, mobile devices, and tablets.

[0090] The embodiment of the present invention collects real-time grid data of the current period of grid equipment; inputs the real-time grid data into a grid state prediction model to predict the current grid operation state; inputs the current grid operation state and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy; sets grid control parameters according to the new power distribution strategy and the real-time grid data, and executes the new power distribution strategy; when a preset optimization cycle is reached, a grid resource dynamic optimization algorithm is used to dynamically optimize the grid resources according to the current grid operation state and real-time resource data to obtain an optimized grid resource optimization solution, which can improve the data processing capability, prediction accuracy and adaptability of the grid management system, while optimizing the user interaction interface, enhancing the integration and management of new energy, and realizing real-time monitoring of the grid operation state, load forecasting, fault diagnosis and optimal allocation of power resources, thereby reducing operating costs, improving energy utilization, and supporting the development of sustainable energy.

[0091] Figure 2 FIG1 shows a schematic diagram of the structure of the power grid management and control system based on artificial intelligence provided by an embodiment of the present invention. Figure 2 As shown, the system 200 includes:

[0092] The acquisition module 210 is used to collect real-time grid data of the grid equipment during the current period; the real-time grid data includes power production, load demand, voltage fluctuation data and weather condition data;

[0093] Prediction module 220, configured to input the real-time grid data into a grid state prediction model to predict the current grid operating state; the current grid operating state includes whether it is a peak load period and whether the voltage is abnormal; wherein the grid state prediction model is obtained by pre-training a deep learning network based on grid state sample data, wherein the grid state sample data includes historical grid operating data and corresponding sample labels;

[0094] The power strategy module 230 is configured to input the current power grid operation status and the real-time power grid data into the power grid strategy dynamic optimization module to generate a new power distribution strategy;

[0095] An execution module 240 is configured to set power grid control parameters and execute the new power distribution strategy based on the new power distribution strategy and the real-time power grid data;

[0096] The resource optimization module 250 is used to dynamically optimize the grid resources using a grid resource dynamic optimization algorithm based on the current grid operation status and real-time resource data when a preset optimization cycle is reached, so as to obtain an optimized grid resource optimization plan; wherein the grid resource dynamic optimization algorithm includes a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data includes load demand information, renewable energy power generation, remaining capacity of the energy storage system, grid topology structure and external factor data.

[0097] In an optional manner, the device further comprises: a collection module for collecting historical grid operation data; the historical grid operation data includes historical power production, historical load demand, historical voltage fluctuation data, and historical weather condition data;

[0098] a label marking module, configured to add corresponding sample labels to the historical operation data of the power grid to obtain grid status sample data; the sample labels include the corresponding historical operation status of the power grid, and the historical operation status labels of the power grid include a load peak period label and a voltage anomaly label;

[0099] The iterative training module is used to input the grid state sample data into the deep learning network for iterative training, and adjust the parameters of the deep learning network to obtain a trained grid state prediction model.

[0100] In an optional manner, the deep learning network includes a time series prediction module, a spatial correlation prediction module, and an anomaly detection module; wherein the time series prediction module includes one of a self-attention mechanism and a CNN-LSTM hybrid model; the spatial correlation prediction module includes a GNN algorithm; and the anomaly detection module includes a variational autoencoder;

[0101] The step of inputting the grid state sample data into a deep learning network for iterative training and adjusting the parameters of the deep learning network to obtain a trained grid state prediction model includes:

[0102] Inputting the grid state sample data into a self-attention mechanism or a CNN-LSTM hybrid model for training to obtain a time series prediction module for predicting load peak period prediction results;

[0103] Inputting the grid state sample data into a GNN algorithm for training to obtain a spatial correlation prediction module for locating grid faults;

[0104] The grid state sample data is input into a variational autoencoder for training to obtain an anomaly detection module for detecting abnormal events.

[0105] In an optional manner, collecting real-time grid data of grid equipment in the current period includes:

[0106] Collecting power generation information of each power generation device in the power grid to obtain power generation data; the power generation equipment includes thermal power plants, hydropower stations, wind power stations and solar photovoltaic systems;

[0107] Obtain real-time load data from load monitoring equipment in substations and distribution networks to obtain load demand;

[0108] Voltage fluctuations are monitored and recorded by voltage sensors installed at key nodes of the power grid, and voltage fluctuation data is collected;

[0109] Obtain weather data that affects energy production and consumption through communication with meteorological service centers.

[0110] In an optional manner, inputting the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy includes:

[0111] Evaluate the effectiveness of a current power distribution strategy and identify areas for improvement based on the current power grid operating status and the real-time power grid data;

[0112] Generating a new power distribution strategy according to a preset adjustment strategy based on the improvement points and the current power grid operation status;

[0113] Conducting simulation tests on the new power distribution strategy;

[0114] When the test passes, the new power distribution strategy is applied to grid management.

[0115] In an optional manner, when the preset optimization period is reached, a power grid resource dynamic optimization algorithm is used to perform dynamic optimization of the power grid resources according to the current power grid operation status and real-time resource data to obtain an optimized power grid resource optimization plan, including:

[0116] Determine a multi-objective function based on traditional power generation fuel costs, energy storage loss costs, penalties for renewable energy curtailment, and voltage deviations. This includes setting power balance constraints, energy storage dynamic constraints, and grid equipment restriction constraints.

[0117] When the preset optimization cycle is reached, the multi-objective function is optimized using a reinforcement learning adaptive strategy according to the current grid operation status and real-time resource data to obtain an optimized grid resource optimization plan.

[0118] In an optional manner, the method further includes: displaying the current grid operation status and the optimized grid resource optimization plan in a user interface.

[0119] like Figure 3 As shown, in the artificial intelligence-based smart grid optimization and management system provided by the embodiment of the present invention, the real-time grid data is collected by integrating with various grid devices, and the data is processed by relying on the DPM (data processor) of the data processing module, thereby effectively improving the data processing speed and data processing accuracy.

[0120] The embodiment of the present invention collects real-time grid data of the current period of grid equipment; inputs the real-time grid data into a grid state prediction model to predict the current grid operation state; inputs the current grid operation state and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy; sets grid control parameters according to the new power distribution strategy and the real-time grid data, and executes the new power distribution strategy; when a preset optimization cycle is reached, a grid resource dynamic optimization algorithm is used to dynamically optimize the grid resources according to the current grid operation state and real-time resource data to obtain an optimized grid resource optimization solution, which can improve the data processing capability, prediction accuracy and adaptability of the grid management system, while optimizing the user interaction interface, enhancing the integration and management of new energy, and realizing real-time monitoring of the grid operation state, load forecasting, fault diagnosis and optimal allocation of power resources, thereby reducing operating costs, improving energy utilization, and supporting the development of sustainable energy.

[0121] Figure 4The schematic diagram of the structure of the computer device provided by the embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computer device.

[0122] like Figure 4 As shown, the computer device may include: a processor 402 , a communications interface 404 , a memory 406 , and a communication bus 408 .

[0123] Processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. Communication interface 404 is used to communicate with other devices, such as clients or other server network elements. Processor 402 is used to execute program 410, which may specifically perform the steps described in the aforementioned embodiment of the artificial intelligence-based power grid management method.

[0124] Specifically, the program 410 may include program code including computer-executable instructions.

[0125] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in a computer device may be of the same type, such as one or more CPUs, or may be of different types, such as one or more CPUs and one or more ASICs.

[0126] The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0127] The program 410 may be specifically called by the processor 402 to cause the computer device to perform the following operations:

[0128] Collecting real-time grid data of the grid equipment during the current period; the real-time grid data includes power production, load demand, voltage fluctuation data and weather condition data;

[0129] Inputting the real-time grid data into a grid state prediction model to predict the current grid operation state; the current grid operation state includes whether it is a peak load period and whether the voltage is abnormal; wherein the grid state prediction model is obtained by pre-training a deep learning network based on grid state sample data, and the grid state sample data includes historical grid operation data and corresponding sample labels;

[0130] inputting the current power grid operation state and the real-time power grid data into a power grid strategy dynamic optimization module to generate a new power distribution strategy;

[0131] setting a power grid control parameter according to the new power distribution strategy and the real-time power grid data to execute the new power distribution strategy;

[0132] when a preset optimization period is reached, performing power grid resource dynamic optimization according to the current power grid operation state and real-time resource data by using a power grid resource dynamic optimization algorithm to obtain an optimized power grid resource optimization scheme; wherein the power grid resource dynamic optimization algorithm comprises a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data comprises load demand information, new energy power generation, remaining capacity of an energy storage system, power grid topology structure, and external factor data.

[0133] In an optional manner, before the real-time power grid data is input into the power grid state prediction model to obtain the current power grid operation state, the method further comprises:

[0134] collecting power grid historical operation data; the power grid historical operation data comprises historical power output, historical load demand, historical voltage fluctuation data, and historical weather condition data; adding corresponding sample labels to the power grid historical operation data to obtain power grid state sample data; the sample labels comprise corresponding power grid historical operation states, and the power grid historical operation state labels comprise load peak period labels and voltage abnormality labels;

[0135] inputting the power grid state sample data into a deep learning network for iterative training and adjusting parameters of the deep learning network to obtain a trained power grid state prediction model.

[0136] In an optional manner, the deep learning network comprises a time series prediction module, a spatial correlation prediction module, and an anomaly detection module; wherein the time series prediction module comprises one of a self-attention mechanism and a CNN-LSTM hybrid model; the spatial correlation prediction module comprises a GNN algorithm; and the anomaly detection module comprises a variational autoencoder.

[0137] inputting the power grid state sample data into a deep learning network for iterative training and adjusting parameters of the deep learning network to obtain a trained power grid state prediction model, comprises:

[0138] inputting the power grid state sample data into a self-attention mechanism or a CNN-LSTM hybrid model for training to obtain a time series prediction module for predicting a load peak period prediction result;

[0139] Inputting the grid state sample data into a GNN algorithm for training to obtain a spatial correlation prediction module for locating grid faults;

[0140] The grid state sample data is input into a variational autoencoder for training to obtain an anomaly detection module for detecting abnormal events.

[0141] In an optional manner, collecting real-time grid data of grid equipment in the current period includes:

[0142] Collecting power generation information of each power generation device in the power grid to obtain power generation data; the power generation equipment includes thermal power plants, hydropower stations, wind power stations and solar photovoltaic systems;

[0143] Obtain real-time load data from load monitoring equipment in substations and distribution networks to obtain load demand;

[0144] Voltage fluctuations are monitored and recorded by voltage sensors installed at key nodes of the power grid, and voltage fluctuation data is collected;

[0145] Obtain weather data that affects energy production and consumption through communication with meteorological service centers.

[0146] In an optional manner, inputting the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy includes:

[0147] Evaluate the effectiveness of a current power distribution strategy and identify areas for improvement based on the current power grid operating status and the real-time power grid data;

[0148] Generating a new power distribution strategy according to a preset adjustment strategy based on the improvement points and the current power grid operation status;

[0149] Conducting simulation tests on the new power distribution strategy;

[0150] When the test passes, the new power distribution strategy is applied to grid management.

[0151] In an optional manner, when the preset optimization period is reached, a power grid resource dynamic optimization algorithm is used to perform dynamic optimization of the power grid resources according to the current power grid operation status and real-time resource data to obtain an optimized power grid resource optimization plan, including:

[0152] Determine a multi-objective function based on traditional power generation fuel costs, energy storage loss costs, penalties for renewable energy curtailment, and voltage deviations. This includes setting power balance constraints, energy storage dynamic constraints, and grid equipment restriction constraints.

[0153] When a preset optimization period is reached, a multi-objective function is optimized by using a reinforcement learning adaptive strategy according to the current power grid operation state and real-time resource data, and an optimized power grid resource optimization scheme is obtained.

[0154] In an optional manner, the method further comprises: displaying the current power grid operation state and the optimized power grid resource optimization scheme in a user interface.

[0155] The embodiment of the present application can improve the data processing capability, prediction accuracy and self-adaptive capability of the power grid management system, optimize the user interaction interface, enhance the integration and management of new energy, realize real-time monitoring of the power grid operation state, load prediction, fault diagnosis and optimal allocation of power resources, thereby reducing the operation cost, improving the energy utilization rate, and supporting the development of sustainable energy.

[0156] The embodiment of the present application provides a computer readable storage medium, the storage medium stores at least one executable instruction, the executable instruction is run on a computer device, and the computer device executes the power grid management and control method based on artificial intelligence in any method embodiment.

[0157] The executable instruction can be specifically used to make the computer device execute the following operations:

[0158] Real-time power grid data of a current period of power grid equipment is collected, and the real-time power grid data includes power output, load demand, voltage fluctuation data and weather condition data;

[0159] The real-time power grid data is input into a power grid state prediction model to predict a current power grid operation state, and the current power grid operation state includes whether it is a load peak period and whether the voltage is abnormal; wherein the power grid state prediction model is obtained by pre-training a deep learning network according to power grid state sample data, and the power grid state sample data includes power grid historical operation data and corresponding sample labels;

[0160] The current power grid operation state and the real-time power grid data are input into a power grid strategy dynamic optimization module to generate a new power distribution strategy;

[0161] According to the new power distribution strategy and the real-time power grid data, setting power grid control parameters and executing the new power distribution strategy;

[0162] When the preset optimization cycle is reached, the grid resources are dynamically optimized using a grid resource dynamic optimization algorithm based on the current grid operating status and real-time resource data to obtain an optimized grid resource optimization plan; wherein, the grid resource dynamic optimization algorithm includes a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data includes load demand information, renewable energy power generation, remaining capacity of the energy storage system, grid topology structure and external factor data.

[0163] In an optional manner, before inputting the real-time power grid data into the power grid state prediction model to predict the current power grid operation state, the method further includes:

[0164] Collecting historical grid operation data; the historical grid operation data includes historical power production, historical load demand, historical voltage fluctuation data, and historical weather condition data;

[0165] Adding corresponding sample tags to the historical operation data of the power grid to obtain power grid status sample data; the sample tags include the corresponding historical operation status of the power grid, and the historical operation status tags of the power grid include a load peak period tag and a voltage anomaly tag;

[0166] The grid state sample data is input into a deep learning network for iterative training, and the parameters of the deep learning network are adjusted to obtain a trained grid state prediction model.

[0167] In an optional manner, the deep learning network includes a time series prediction module, a spatial correlation prediction module, and an anomaly detection module; wherein the time series prediction module includes one of a self-attention mechanism and a CNN-LSTM hybrid model; the spatial correlation prediction module includes a GNN algorithm; and the anomaly detection module includes a variational autoencoder;

[0168] The step of inputting the grid state sample data into a deep learning network for iterative training and adjusting the parameters of the deep learning network to obtain a trained grid state prediction model includes:

[0169] Inputting the grid state sample data into a self-attention mechanism or a CNN-LSTM hybrid model for training to obtain a time series prediction module for predicting load peak period prediction results;

[0170] Inputting the grid state sample data into a GNN algorithm for training to obtain a spatial correlation prediction module for locating grid faults;

[0171] The grid state sample data is input into a variational autoencoder for training to obtain an anomaly detection module for detecting abnormal events.

[0172] In an optional manner, collecting real-time grid data of grid equipment in the current period includes:

[0173] Collecting power generation information of each power generation device in the power grid to obtain power generation data; the power generation equipment includes thermal power plants, hydropower stations, wind power stations and solar photovoltaic systems;

[0174] Obtain real-time load data from load monitoring equipment in substations and distribution networks to obtain load demand;

[0175] Voltage fluctuations are monitored and recorded by voltage sensors installed at key nodes of the power grid, and voltage fluctuation data is collected;

[0176] Obtain weather data that affects energy production and consumption through communication with meteorological service centers.

[0177] In an optional manner, inputting the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy includes:

[0178] Evaluate the effectiveness of a current power distribution strategy and identify areas for improvement based on the current power grid operating status and the real-time power grid data;

[0179] Generating a new power distribution strategy according to a preset adjustment strategy based on the improvement points and the current power grid operation status;

[0180] Conducting simulation tests on the new power distribution strategy;

[0181] When the test passes, the new power distribution strategy is applied to grid management.

[0182] In an optional manner, when the preset optimization period is reached, a power grid resource dynamic optimization algorithm is used to perform dynamic optimization of the power grid resources according to the current power grid operation status and real-time resource data to obtain an optimized power grid resource optimization plan, including:

[0183] Determine a multi-objective function based on traditional power generation fuel costs, energy storage loss costs, penalties for renewable energy curtailment, and voltage deviations. This includes setting power balance constraints, energy storage dynamic constraints, and grid equipment restriction constraints.

[0184] When the preset optimization cycle is reached, the multi-objective function is optimized using a reinforcement learning adaptive strategy according to the current grid operation status and real-time resource data to obtain an optimized grid resource optimization plan.

[0185] In an optional manner, the method further includes: displaying the current grid operation status and the optimized grid resource optimization plan in a user interface.

[0186] The embodiment of the present invention collects real-time grid data of the current period of grid equipment; inputs the real-time grid data into a grid state prediction model to predict the current grid operation state; inputs the current grid operation state and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy; sets grid control parameters according to the new power distribution strategy and the real-time grid data, and executes the new power distribution strategy; when a preset optimization cycle is reached, a grid resource dynamic optimization algorithm is used to dynamically optimize the grid resources according to the current grid operation state and real-time resource data to obtain an optimized grid resource optimization solution, which can improve the data processing capability, prediction accuracy and adaptability of the grid management system, while optimizing the user interaction interface, enhancing the integration and management of new energy, and realizing real-time monitoring of the grid operation state, load forecasting, fault diagnosis and optimal allocation of power resources, thereby reducing operating costs, improving energy utilization, and supporting the development of sustainable energy.

[0187] An embodiment of the present invention provides an artificial intelligence-based power grid management and control device for executing the above-mentioned artificial intelligence-based power grid management and control method.

[0188] An embodiment of the present invention provides a computer program that can be called by a processor to enable a computer device to execute the artificial intelligence-based power grid management and control method in any of the above method embodiments.

[0189] An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed on a computer, the computer executes the artificial intelligence-based power grid management and control method in any of the above-mentioned method embodiments.

[0190] The algorithm or demonstration provided herein are not inherently relevant to any particular computer, virtual system or other equipment. Various general-purpose systems may also be used together with the teachings based on this. According to the above description, it is apparent that the structure required for constructing this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0191] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0192] Similarly, it should be understood that in order to streamline the present invention and facilitate understanding of one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.

[0193] Those skilled in the art will appreciate that the modules in the devices of the embodiments can be adaptively modified and installed in one or more devices different from the embodiments. The modules, units, or components in the embodiments can be combined into a single module, unit, or component, or they can be divided into multiple sub-modules, sub-units, or sub-components. All features disclosed in this specification (including the accompanying claims, abstract, and drawings), and all processes or units of any method or device disclosed therein, can be combined in any combination, unless at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0194] It should be noted that the above embodiments illustrate rather than limit the invention, and that alternative embodiments may be devised by a person skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments should not be understood as limiting the order of execution unless otherwise specified.

Claims

1. A power grid management and control method based on artificial intelligence, characterized in that: The method comprises: Collecting real-time grid data of the grid equipment during the current period; the real-time grid data includes power production, load demand, voltage fluctuation data and weather condition data; The real-time power grid data is input into the power grid state prediction model to predict the current power grid operation state; the current power grid operation state includes load peak period, anomaly detection information and power grid fault location information; wherein the power grid state prediction model is obtained by pre-training a deep learning network based on power grid state sample data, and the power grid state sample data includes historical power grid operation data and corresponding sample labels; the deep learning network includes a time series prediction module, a spatial association prediction module and an anomaly detection module; wherein the time series prediction module includes one of a self-attention mechanism and a CNN-LSTM hybrid model; the spatial association prediction module includes a GNN algorithm; and the anomaly detection module includes a variational autoencoder; The grid state sample data is input into a deep learning network for iterative training, and the parameters of the deep learning network are adjusted to obtain a trained grid state prediction model, including: inputting the grid state sample data into a self-attention mechanism or a CNN-LSTM hybrid model for training to obtain a time series prediction module for predicting load peak period prediction results; inputting the grid state sample data into a GNN algorithm for training to obtain a spatial correlation prediction module for locating grid faults; and inputting the grid state sample data into a variational autoencoder for training to obtain an anomaly detection module for detecting abnormal events. Inputting the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy; According to the new power distribution strategy and the real-time power grid data, setting power grid control parameters and executing the new power distribution strategy; When the preset optimization cycle is reached, the grid resources are dynamically optimized using a grid resource dynamic optimization algorithm based on the current grid operating status and real-time resource data to obtain an optimized grid resource optimization plan; wherein, the grid resource dynamic optimization algorithm includes a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data includes load demand information, renewable energy power generation, remaining capacity of the energy storage system, grid topology structure and external factor data.

2. The method according to claim 1, characterized in that Before inputting the real-time power grid data into the power grid state prediction model to predict the current power grid operation state, the method further includes: Collecting historical grid operation data; the historical grid operation data includes historical power production, historical load demand, historical voltage fluctuation data, and historical weather condition data; Adding corresponding sample tags to the historical operation data of the power grid to obtain power grid status sample data; the sample tags include the corresponding historical operation status of the power grid, and the historical operation status tags of the power grid include a load peak period tag, an anomaly detection information tag, and a power grid fault location information tag; The grid state sample data is input into a deep learning network for iterative training, and the parameters of the deep learning network are adjusted to obtain a trained grid state prediction model.

3. The method according to any one of claims 1 or 2, characterized in that The real-time grid data collected from the grid equipment during the current period includes: Collecting power generation information of each power generation device in the power grid to obtain power generation data; the power generation equipment includes thermal power plants, hydropower stations, wind power stations and solar photovoltaic systems; Obtain real-time load data from load monitoring equipment in substations and distribution networks to obtain load demand; Voltage fluctuations are monitored and recorded by voltage sensors installed at key nodes of the power grid, and voltage fluctuation data is collected; Obtain weather data that affects energy production and consumption through communication with meteorological service centers.

4. The method according to any one of claims 1 or 2, characterized in that The step of inputting the current grid operation status and the real-time grid data into a grid strategy dynamic optimization module to generate a new power distribution strategy includes: Evaluate the effectiveness of the current power distribution strategy and identify areas for improvement based on the current power grid operating status and the real-time power grid data; Generating a new power distribution strategy according to a preset adjustment strategy based on the improvement points and the current power grid operation status; Conducting simulation tests on the new power distribution strategy; When the test passes, the new power distribution strategy is applied to grid management.

5. The method according to any one of claims 1 or 2, characterized in that When the preset optimization period is reached, the grid resources are dynamically optimized using a grid resource dynamic optimization algorithm according to the current grid operation status and real-time resource data to obtain an optimized grid resource optimization solution, including: Determine a multi-objective function based on traditional power generation fuel costs, energy storage loss costs, and voltage deviations; among these, set power balance constraints, energy storage dynamic constraints, and grid equipment restriction constraints; When the preset optimization cycle is reached, the multi-objective function is optimized using a reinforcement learning adaptive strategy according to the current grid operation status and real-time resource data to obtain an optimized grid resource optimization plan.

6. The method according to any one of claims 1 or 2, characterized in that The method further comprises: The current grid operation status and the optimized grid resource optimization plan are displayed on the user interface.

7. An artificial intelligence-based power grid management and control system, characterized in that: The system comprises: An acquisition module is used to collect real-time grid data of the grid equipment during the current period; the real-time grid data includes power production, load demand, voltage fluctuation data, and weather condition data; A prediction module, configured to input the real-time grid data into a grid state prediction model to predict the current grid operating state; the current grid operating state includes load peak period, anomaly detection information, and grid fault location information; wherein the grid state prediction model is obtained by pre-training a deep learning network based on grid state sample data, wherein the grid state sample data includes historical grid operating data and corresponding sample labels; A power strategy module, configured to input the current power grid operation status and the real-time power grid data into a power grid strategy dynamic optimization module to generate a new power distribution strategy; an execution module, configured to set power grid control parameters and execute the new power distribution strategy according to the new power distribution strategy and the real-time power grid data; The resource optimization module is used to dynamically optimize the power grid resources using a power grid resource dynamic optimization algorithm based on the current power grid operating status and real-time resource data when a preset optimization cycle is reached, thereby obtaining an optimized power grid resource optimization plan; wherein the power grid resource dynamic optimization algorithm includes a hybrid algorithm combining model predictive control and reinforcement learning, and the real-time resource data includes load demand information, renewable energy power generation, remaining capacity of the energy storage system, power grid topology structure and external factor data.

8. A computer device, characterized in that: include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the artificial intelligence-based power grid management and control method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that The storage medium stores at least one executable instruction, and when the executable instruction is executed on a computer device, the computer device executes the operation of the artificial intelligence-based power grid management and control method according to any one of claims 1 to 6.

Images