New energy grid-connected regional power grid control method, system and equipment and storage medium
By identifying the power grid operation mode through LSTM networks and deep learning algorithms, and combining the optimal power flow model with security constraints and the interior point method to generate power grid control strategies, the problem of power grid stability caused by the volatility of new energy power generation is solved, and precise protection and control of the power grid is achieved, thereby improving the adaptability and stability of the power grid.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ANHUI ELECTRIC POWER DESIGN INST CEEC
- Filing Date
- 2026-02-13
- Publication Date
- 2026-05-15
AI Technical Summary
In existing technologies, the intermittency, volatility, and uncertainty of new energy power generation pose challenges to the safe and stable operation of the power grid. Traditional control methods lack adaptive capabilities, have slow responses, and are difficult to accurately capture the complex and ever-changing operating state of the power grid, resulting in insufficient system regulation capabilities.
LSTM networks and deep learning algorithms are used to identify power grid operation modes. Power grid control strategies are generated by combining a safety-constrained optimal power flow model and the interior-point method. Machine learning algorithms are used to accurately identify power grid operation modes and states and dynamically adjust control strategies.
It enables precise protection and control of the power grid in areas with new energy grid connection under multiple operating modes, improves the adaptability, stability and control accuracy of the power grid, and provides technical support for the safe and stable operation of the power grid in areas with high penetration of new energy.
Smart Images
Figure CN122052014A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power system automation technology, and in particular to a power grid control method, system, equipment and storage medium for new energy grid-connected areas. Background Technology
[0002] As the global energy transition deepens, the penetration rate of new energy sources (such as wind power and photovoltaics) in the power system continues to increase. However, the intermittent, volatile, and uncertain characteristics of new energy power generation pose significant challenges to the safe and stable operation of the power grid.
[0003] In existing technologies, traditional power grid protection and control methods are mostly designed based on fixed operating modes, lacking the ability to adapt to multiple operating modes. For example, traditional constant power control methods lack frequency response capability when the frequency exceeds the limit, which may exacerbate system imbalance and fail to provide inertial support or primary frequency regulation services, thereby weakening the system's equivalent inertia under high penetration rates. At the same time, traditional PI (Proportional-Integral) and PR (Proportional-Resonant) controllers have fixed parameters and cannot adjust their strategies in real time according to the dynamic changes of the power grid, resulting in slow response and limited control performance.
[0004] Furthermore, in terms of operating mode identification, existing methods mainly rely on single indicators or simple threshold judgments, making it difficult to accurately capture the complex and ever-changing operating states of the power grid. Traditional grid-connected control strategies are often based on a single dimension of frequency or voltage stability, ignoring the uncertainty of renewable energy output, resulting in insufficient system regulation capabilities in complex power grid environments.
[0005] Therefore, more reliable solutions are needed in power grid protection and control. Summary of the Invention
[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, system, device and storage medium for controlling a regional power grid in a new energy grid-connected area, which can improve the protection and control of the regional power grid under multiple operating modes and enhance the adaptability and stability of the power grid.
[0007] To achieve the above objectives, the present invention employs the following technical solution:
[0008] On one hand, the present invention provides a power grid control method for a new energy grid-connected area, the method comprising:
[0009] Collect grid operation parameters of the power grid in the area where new energy is connected to the grid, as well as obtain historical grid operation data and historical weather forecast data;
[0010] The power grid operation parameters are input into the power grid operation identification network for operation mode identification processing to generate the current power grid operation mode;
[0011] The historical power grid operation data and historical weather forecast data are input into the power grid operation prediction model for prediction processing, generating a new energy output prediction sequence and a load prediction sequence for the power grid in the new energy grid-connected area for a future preset time period.
[0012] Based on the current power grid operation mode and the predicted power output and load sequences for future preset time periods, a safety-constrained optimal power flow model is constructed.
[0013] The interior-point method is used to solve the security-constrained optimal power flow model to generate a power grid control strategy;
[0014] The power grid control strategy is sent to the new energy power plant controller and the substation control equipment so that the new energy power plant controller and the substation control equipment execute the power grid control strategy.
[0015] In some possible implementations, the power grid operation identification network is an LSTM network comprising an input layer, L hidden layers, and an output layer; the step of inputting the power grid operation parameters into the power grid operation identification network for operation mode identification processing to generate the current power grid operation mode includes:
[0016] The power grid operation parameters are processed through the input layer to generate power grid operation processing parameters.
[0017] The power grid operation processing parameters are processed by extracting features through the L hidden layers and the time dependency relationship between the power grid operation processing parameters is learned to generate power grid operation features.
[0018] The power grid operation characteristics are processed by the output gate to identify the current power grid operation mode.
[0019] In some possible implementations, the power grid operation prediction model includes an encoder and a decoder; the step of inputting the historical power grid operation data and historical weather forecast data into the power grid operation prediction model for prediction processing, and generating a new energy output prediction sequence and a load prediction sequence for the power grid in the new energy grid-connected area for a future preset time period, includes:
[0020] The historical power grid operation data and its corresponding historical weather forecast data are input into the encoder for encoding processing to generate context features. The encoding process includes parallel analysis of the global dependency between the historical power grid operation data and the historical weather forecast data through a multi-head self-attention mechanism, and processing the historical power grid operation data and the historical weather forecast data in chronological order through a gated loop unit to capture the local evolution patterns between the historical power grid operation data and the historical weather forecast data, thereby generating the context features.
[0021] The context features are input into the decoder for decoding processing to generate a new energy output prediction sequence and a load prediction sequence for the future preset time period. During the decoding process, an attention mechanism is used to take the context features as the initial state and generate the new energy output prediction sequence and load prediction sequence for the future preset time period step by step in an autoregressive manner.
[0022] In some possible implementations, the step of constructing a safety-constrained optimal power flow model based on the current power grid operation mode and the predicted output sequence of new energy sources and the predicted load sequence for a future preset time period includes:
[0023] Based on the current power grid operation mode, construct an objective function;
[0024] Based on the predicted sequence of new energy output and the predicted sequence of load for the future preset time period, a power balance constraint is constructed.
[0025] Based on the objective function, the power balance constraints, and the safety constraints including equality constraints, inequality constraints, and N-1 safety constraints, a safety-constrained optimal power flow model is constructed.
[0026] In some possible implementations, the step of solving the security-constrained optimal power flow model using the interior-point method to generate a power grid control strategy includes:
[0027] By introducing nonnegative relaxation variables, the inequality constraint is transformed into a first constraint in the form of an equality constraint.
[0028] By adding a logarithmic barrier term to the objective function, the safety-constrained optimal power flow model is transformed into a series of approximate subproblems. The logarithmic barrier term is used to handle the non-negativity of the slack variables.
[0029] By constructing the Lagrange function and applying Newton's method, the series of approximate subproblems are transformed into a system of linear corrected equations;
[0030] Under the power balance constraint, equality constraint, first constraint and N-1 security constraint, the linear modified equation system is solved iteratively. In each iteration, the original variables of the optimal power flow model under the security constraint, the non-negative relaxation variables and the corresponding Lagrange multipliers are optimized simultaneously until the convergence condition is reached and the optimal power flow solution is determined.
[0031] The power grid control strategy is determined based on the optimal power flow solution.
[0032] In some possible implementations, after sending the power grid control strategy to the renewable energy power plant controller and the substation control equipment, the method further includes:
[0033] The power grid control strategy is dynamically adjusted based on the collected execution feedback data; the execution feedback data is generated by the new energy power plant controller and substation control equipment executing the power grid control strategy.
[0034] The step of dynamically adjusting the power grid control strategy based on the collected execution feedback data includes:
[0035] When the new energy power station controller and the substation control equipment execute the power grid control strategy, the execution feedback data is collected;
[0036] Based on the execution feedback data, identify the power grid operation mode;
[0037] Based on the power grid operation mode, the safety constraint optimal power flow model is adjusted to adjust the power grid control strategy.
[0038] In some possible implementations, collecting grid operating parameters includes collecting data on voltage at each node, line current, active power, reactive power, renewable energy output, load data, and grid topology parameters. The accuracy requirements for collecting these grid operating parameters are: measurement error of the 2nd to 50th harmonic content ≤ ±5%, and inter-harmonic error of the 0.1 to 99.9th harmonics ≤ ±5%. The response time requirements are: reactive power adjustment response time ≤ 2s, dynamic reactive current rise time ≤ 30ms. The adjustment accuracy requirements are: active power control error of photovoltaic systems connected to the grid at ≥ 10kV ≤ 1% of rated power, and response time ≤ 5s.
[0039] On the other hand, a power grid control system for a new energy grid-connected area is provided, the system comprising:
[0040] The data acquisition module is used to collect grid operation parameters of the power grid in the area where new energy is connected to the grid, as well as to acquire historical grid operation data and historical weather forecast data;
[0041] The power grid operation mode identification module is used to input the power grid operation parameters into the power grid operation identification network for operation mode identification processing and generate the current power grid operation mode;
[0042] The prediction module is used to input the historical power grid operation data and historical weather forecast data into the power grid operation prediction model for prediction processing, and generate a new energy output prediction sequence and a load prediction sequence for the power grid in the new energy grid-connected area for a future preset time period.
[0043] The control strategy generation module is used to construct a safety-constrained optimal power flow model based on the current power grid operation mode and the predicted output sequence and load sequence of new energy sources for a preset time period in the future; solve the safety-constrained optimal power flow model using the interior point method to generate a power grid control strategy; and send the power grid control strategy to the new energy power station controller and the substation control equipment so that the new energy power station controller and the substation control equipment execute the power grid control strategy.
[0044] On the other hand, an electronic device is provided, the device including a processor and a memory, the memory storing at least one instruction and at least one program, the at least one instruction and the at least one program being loaded and executed by the processor to realize the new energy grid-connected area power grid control method as described above.
[0045] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction and at least one program are stored in the computer storage medium, and the at least one instruction and the at least one program are loaded and executed by a processor to implement the new energy grid-connected area power grid control method as described above.
[0046] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:
[0047] In this invention, power grid operation parameters of the renewable energy grid-connected area are collected, along with historical power grid operation data and historical weather forecast data. The power grid operation parameters are input into a power grid operation identification network for operation mode identification processing to generate the current power grid operation mode. Historical power grid operation data and historical weather forecast data are input into a power grid operation prediction model for prediction processing to generate a renewable energy output prediction sequence and a load prediction sequence for the renewable energy grid-connected area power grid over a preset future time period. Based on the current power grid operation mode and the renewable energy output prediction sequence and load prediction sequence for the preset future time period, a safety-constrained optimal power flow model is constructed. The interior-point method is used to solve the safety-constrained optimal power flow model to generate a power grid control strategy. The power grid control strategy is sent to the renewable energy power station controller and substation control equipment so that the renewable energy power station controller and substation control equipment execute the power grid control strategy. This allows for accurate identification of the power grid operation mode and operating status through machine learning algorithms, thereby enabling the generation of a power grid control strategy. This achieves accurate protection and control of the renewable energy grid-connected area under multiple operation modes, and improves the adaptability, stability, and control accuracy of the power grid, thus providing strong technical support for the safe and stable operation of the power grid in areas with high renewable energy penetration. Attached Figure Description
[0048] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. 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.
[0049] Figure 1 This is a flowchart illustrating a power grid control method for a new energy grid-connected area provided in an embodiment of the present invention;
[0050] Figure 2 This is a schematic diagram of the structure of a new energy grid-connected regional power grid control system provided in an embodiment of the present invention. Detailed Implementation
[0051] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0052] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.
[0053] In this embodiment of the invention, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.
[0054] Various exemplary embodiments, features, and aspects of the present invention will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.
[0055] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.
[0056] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.
[0057] Furthermore, to better illustrate the present invention, numerous specific details are set forth in the following detailed embodiments. Those skilled in the art will understand that the present invention can be practiced without certain specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order to highlight the spirit of the invention.
[0058] Figure 1 This is a flowchart illustrating a power grid control method for a new energy grid-connected area provided by an embodiment of the present invention. This specification provides the method operation steps as shown in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operation steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual system or server product execution, the method can be executed sequentially according to the embodiments or drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown... Figure 1 As shown, the above method may include:
[0059] S101: Collect grid operation parameters of the power grid in the area where new energy is connected to the grid, and obtain historical grid operation data and historical weather forecast data;
[0060] In an optional embodiment, the above-mentioned collection of power grid operating parameters may include collecting data on voltage at each node, line current, active power, reactive power, renewable energy output, load data, and power grid topology parameters. The accuracy requirements for collecting power grid operating parameters are as follows: the measurement error of the 2nd to 50th harmonic content is ≤ ±5%, and the error of the 0.1 to 99.9th harmonic is ≤ ±5%. The response time requirements are: reactive power adjustment response time ≤ 2s, dynamic reactive current rise time ≤ 30ms. The adjustment accuracy requirements are: active power control error of photovoltaic systems with a voltage greater than or equal to 10kV is ≤ 1% of rated power, and the response time is ≤ 5s.
[0061] In one specific embodiment, data acquisition devices deployed in substations and renewable energy power plants within the renewable energy grid can collect grid operating parameters in real time. Real-time data transmission can be achieved using high-speed communication interfaces. Specifically, these high-speed communication interfaces employ IEC 61850, IEC 60870-5-104, Modbus TCP, or DNP3.0 communication protocols, achieving communication rates exceeding 100 Mbps and end-to-end transmission delays of less than 200 ms. The data acquisition devices can include power parameter acquisition devices for substations and renewable energy output acquisition devices for renewable energy power plants, with acquisition frequencies exceeding 50 Hz.
[0062] In one specific embodiment, historical power grid operation data may include renewable energy output and load data covering at least 24 hours in the past, and the corresponding weather forecast data may include irradiance, temperature, and wind speed.
[0063] S102: Input the power grid operation parameters into the power grid operation identification network for operation mode identification processing, and generate the current power grid operation mode;
[0064] In one specific embodiment, an operating state feature vector can be constructed based on power grid operating parameters. Specifically, the power grid operating parameters are normalized and combined into a high-dimensional vector to obtain the operating state feature vector. Optionally, the operating state feature vector can be input into a power grid operation identification network to identify the current power grid operating mode. Optionally, the power grid operating mode can include the output level of new energy sources, the load distribution type, and the power grid topology connection status. Specifically, based on a preset new energy output threshold range, the output level of new energy sources is divided into low output, medium output, and high output, and the preset energy output threshold range can be set according to actual applications; the load distribution type can include centralized loads and distributed loads; the power grid topology connection status can include network closed loops and partial closed loops. Optionally, the power grid operation identification network is used to identify the current power grid operating mode based on the power grid operating parameters.
[0065] In an optional embodiment, the aforementioned power grid operation identification network can be an LSTM network comprising an input layer, L hidden layers, and an output layer; the aforementioned inputting power grid operation parameters into the power grid operation identification network for operation mode identification processing to generate the current power grid operation mode may include:
[0066] The power grid operation parameters are processed by the input layer to generate power grid operation processing parameters through time-series data processing.
[0067] By using L hidden layers, feature extraction processing is performed on the power grid operation processing parameters, and the time dependency relationship between the power grid operation processing parameters is learned to generate power grid operation features;
[0068] The power grid operation mode is identified and processed by the output gate to generate the current power grid operation mode.
[0069] In one specific embodiment, the network structure of the power grid operation identification network can be set according to the actual application; optionally, the power grid operation identification network is an LSTM network, which can capture the temporal dependencies of power grid operation parameters. The number of hidden layers can be set according to the actual application; specifically, L hidden layers can be 2 or 3 hidden layers.
[0070] In one specific embodiment, the continuously collected power grid operation parameters arranged in a time series are processed by the input layer using a sliding time window of a preset window length to obtain power grid operation processing parameters. Each hidden layer contains a forget gate, an input gate, an output gate, and a cell state, which can control the memory and forgetting of information. At each time step, the hidden layer receives the data features of the current time step and the hidden state and cell state of the previous time step. It calculates and outputs the hidden state of the current time step through a gating mechanism. Specifically, the forget gate discards information from the data features and hidden state of the previous time step based on the cell state of the previous time step, and outputs the data. The input gate updates the data features and hidden state of the current time step, and outputs the data. The cell state of the previous time step is updated based on the data output of the forget gate and the data output of the input gate to obtain the cell state of the current time step. The output gate processes the cell state of the current time step to generate the hidden state of the current time step. The hidden state of the last time step is processed by a fully connected layer and a Softmax activation function, and outputs a probability distribution vector. Each dimension of this vector corresponds to the predicted probability of an operating mode category. The operating mode category with the highest predicted probability is taken as the current power grid operating mode.
[0071] In the above embodiments, the use of deep learning neural networks to identify the current power grid operation mode can achieve real-time identification of power grid operation mode and adaptive identification of multiple operation modes, thereby improving the accuracy and efficiency of power grid operation mode identification.
[0072] S103: Input historical power grid operation data and historical weather forecast data into the power grid operation prediction model for prediction processing, and generate a new energy output prediction sequence and load prediction sequence for the power grid in the new energy grid-connected area for a future preset time period;
[0073] In one specific embodiment, the preset time period can be set according to the actual application, specifically, it can be the next 12 hours. The power grid operation prediction model is used to predict the output and load of new energy sources. Using a deep learning-based prediction model, the power output and load of the new energy grid in the grid-connected area are predicted for the next 12 hours, which facilitates the subsequent generation of forward-looking control strategies, thereby improving the adaptability and stability of the power grid system.
[0074] In an optional embodiment, the aforementioned power grid operation prediction model may include an encoder and a decoder; the process of inputting historical power grid operation data and historical weather forecast data into the power grid operation prediction model for prediction processing to generate a new energy output prediction sequence and a load prediction sequence for the new energy grid-connected area power grid for a future preset time period may include:
[0075] Historical power grid operation data and their corresponding historical weather forecast data are input into an encoder for encoding processing to generate contextual features. The encoding process includes parallel analysis of the global dependency between historical power grid operation data and historical weather forecast data through a multi-head self-attention mechanism, and processing historical power grid operation data and historical weather forecast data in chronological order through a gated loop unit to capture the local evolution patterns between historical power grid operation data and historical weather forecast data, thereby generating contextual features.
[0076] The context features are input into the decoder for decoding processing to generate a new energy output forecast sequence and a load forecast sequence for a future preset time period. During the decoding process, an attention mechanism is used to take the context features as the initial state and generate the new energy output forecast sequence and load forecast sequence for the future preset time period step by step in an autoregressive manner.
[0077] In one specific embodiment, the encoder can be used to capture the long-range dependencies and temporal patterns between historical power grid operation data and historical weather forecast data; the decoder can be used to focus on the most relevant information output by the encoder to determine the renewable energy output sequence and load forecast sequence for a preset future time period in an autoregressive manner. The contextual features generated by the encoder contain rich spatiotemporal features; during the prediction process, at each prediction step, the decoder dynamically selects the most relevant information from the contextual features output by the encoder through an attention mechanism, combines it with previously predicted partial sequences, and calculates the prediction information (renewable energy output and load) for the next time point. Specifically, when predicting renewable energy output and load for the next 12 hours, the decoder can sequentially output the prediction information for the next 48 time points at 15-minute intervals to obtain the renewable energy output prediction sequence and load prediction sequence for the next 12 hours.
[0078] S104: Based on the current power grid operation mode and the predicted output and load sequences of new energy sources for a future time period, construct a safety-constrained optimal power flow model;
[0079] In an optional embodiment, the construction of the safety-constrained optimal power flow model based on the current power grid operation mode and the predicted output and load sequences of new energy sources for a preset future time period may include:
[0080] Construct an objective function based on the current power grid operation mode;
[0081] Power balance constraints are constructed based on the predicted power output and load sequences of new energy sources for a predetermined time period in the future.
[0082] Based on the objective function, power balance constraints, and safety constraints including equality constraints, inequality constraints, and N-1 safety constraints, a safety-constrained optimal power flow model is constructed.
[0083] In a specific embodiment, the optimal power flow model under security constraints can be one that minimizes the optimization objective under security constraints; alternatively, it can be one that minimizes operating losses, curtailment rate, or voltage deviation under security constraints; alternatively, when the current grid operation mode is high output from new energy sources, an objective function with the goal of minimizing curtailment rate can be constructed. Equality constraints are used to ensure that control variables and state variables satisfy the power flow equations. Inequality constraints can be allowable ranges defined by security conditions that control variables and state variables should satisfy, including upper and lower limits of active and reactive power generation, and upper and lower limits of node voltage, etc. Specifically, inequality constraints can include voltage stability constraints, power flow transmission capacity constraints, and equipment capacity constraints.
[0084] S105: The interior point method is used to solve the optimal power flow model with security constraints and generate a power grid control strategy.
[0085] In one specific embodiment, the power grid control strategy can be used to regulate the output of new energy sources, control the control of substation circuit breakers and reactive power compensation equipment, and optimize power grid flow.
[0086] In an optional embodiment, the above-described solution of the security-constrained optimal power flow model using the interior-point method to generate a power grid control strategy may include:
[0087] By introducing nonnegative slack variables, the inequality constraint is transformed into the first constraint in the form of an equality constraint;
[0088] By adding a logarithmic barrier term to the objective function, the safety-constrained optimal power flow model is transformed into a series of approximate subproblems. The logarithmic barrier term is used to handle the non-negativity of the slack variables.
[0089] By constructing the Lagrange function and applying Newton's method, a series of approximate subproblems are transformed into a system of linear corrected equations;
[0090] Under power balance constraints, equality constraints, first constraints, and N-1 security constraints, the linear modified equation system is solved iteratively. In each iteration, the original variables, non-negative relaxation variables, and corresponding Lagrange multipliers of the optimal power flow model under security constraints are optimized simultaneously until the convergence condition is met and the optimal power flow solution is determined.
[0091] Based on the optimal power flow solution, determine the power grid control strategy.
[0092] In one specific embodiment, a logarithmic barrier term is introduced into the objective function to handle the nonnegativity of slack variables, thereby transforming the safety-constrained optimal power flow model into a series of approximate subproblems. The convergence condition can be that both the optimality and feasibility conditions of the solution simultaneously satisfy a preset convergence tolerance. The optimal power flow solution may include a set of optimal setpoints for key control variables such as the active / reactive power output setpoints of each generator, control commands for new energy power plants, and transformer tap positions. Optionally, the interior-point method maintains the feasibility of the solution throughout the entire solution process and has polynomial-time computational complexity, enabling the solution of large-scale power grid problems within seconds and achieving real-time generation of power grid control strategies.
[0093] S106: The power grid control strategy is sent to the new energy power plant controller and the substation control equipment so that the new energy power plant controller and the substation control equipment execute the power grid control strategy.
[0094] In an optional embodiment, after sending the power grid control strategy to the renewable energy power plant controller and the substation control equipment, the method further includes:
[0095] The power grid control strategy is dynamically adjusted based on the collected execution feedback data; the execution feedback data is generated by the new energy power plant controller and substation control equipment executing the power grid control strategy.
[0096] Dynamic adjustments to the power grid control strategy based on the collected execution feedback data can include:
[0097] Collect execution feedback data when the new energy power station controller and substation control equipment execute the power grid control strategy;
[0098] Identify the power grid operation mode based on execution feedback data;
[0099] Adjust the optimal power flow model with security constraints according to the power grid operation mode in order to adjust the power grid control strategy.
[0100] In one specific embodiment, after determining the power grid control strategy, it can be distributed to the new energy power plant controller and substation control equipment for execution, and execution feedback data can be collected in real time to dynamically adjust the power grid control strategy. Optionally, based on the execution feedback data, the power grid control strategy can be adjusted or regenerated. During the execution of the power grid control strategy, the effects can be monitored in real time, such as voltage deviation, frequency deviation, power factor, and other indicators, and the control process and effects can be recorded for system optimization and experience accumulation.
[0101] In a specific embodiment, adjusting the optimal power flow model with security constraints according to the power grid operation mode may include:
[0102] When the power grid operates under the condition of high output from new energy sources, the limit on the output of new energy sources in the optimal power flow model with security constraints will be adjusted upwards.
[0103] When the power grid operates in a partially open-loop mode, the network topology parameters in the security-constrained optimal power flow model are updated.
[0104] When the power grid operates under a concentrated load mode, the detection of the load center node voltage in the optimal power flow model with security constraints will be enhanced.
[0105] In the above embodiments, by adjusting the optimal power flow model with security constraints according to the power grid operation mode, the power grid control strategy can achieve precise adaptation to the operation mode.
[0106] As can be seen from the technical solutions provided in the embodiments of this specification above, this specification collects grid operation parameters of the power grid in the renewable energy grid-connected area, as well as historical grid operation data and historical weather forecast data; inputs the grid operation parameters into the grid operation identification network for operation mode identification processing to generate the current grid operation mode; inputs the historical grid operation data and historical weather forecast data into the grid operation prediction model for prediction processing to generate a renewable energy output prediction sequence and a load prediction sequence for the renewable energy grid-connected area power grid in the future preset time period; constructs a safety-constrained optimal power flow model based on the current grid operation mode and the renewable energy output prediction sequence and load prediction sequence for the future preset time period; solves the safety-constrained optimal power flow model using the interior point method to generate a grid control strategy; and sends the grid control strategy to... The system transmits data to the controllers of new energy power plants and substations to enable them to execute power grid control strategies. Based on collected execution feedback data, the system dynamically adjusts these strategies. This execution feedback data is generated by the controllers and substations executing the power grid control strategies. Machine learning algorithms can accurately identify the power grid's operating mode and status, thereby generating power grid control strategies and dynamically adjusting them. This enables precise protection and control of new energy grid-connected areas under multiple operating modes, improving the grid's adaptability, stability, and control accuracy. This provides strong technical support for the safe and stable operation of power grids in areas with high new energy penetration, effectively ensuring the safe and stable operation of the power grid and enhancing the capacity for new energy absorption.
[0107] This invention also provides a power grid control system for a new energy grid-connected area, and correspondingly, Figure 2 This is a schematic diagram of the structure of a new energy grid-connected regional power grid control system provided in an embodiment of the present invention; as shown below. Figure 2 As shown, the above system includes:
[0108] The data acquisition module 210 is used to collect the power grid operation parameters of the power grid in the area where new energy is connected to the grid, as well as to acquire historical power grid operation data and historical weather forecast data.
[0109] The power grid operation mode identification module 220 is used to input the power grid operation parameters into the power grid operation identification network for operation mode identification processing, and generate the current power grid operation mode.
[0110] Prediction module 230 is used to input the historical power grid operation data and historical weather forecast data into the power grid operation prediction model for prediction processing, and generate a new energy output prediction sequence and a load prediction sequence for the new energy grid-connected area power grid for a future preset time period.
[0111] The control strategy generation module 240 is used to construct a safety-constrained optimal power flow model based on the current power grid operation mode and the predicted output sequence and load sequence of new energy sources for the future preset time period; solve the safety-constrained optimal power flow model using the interior point method to generate a power grid control strategy; and send the power grid control strategy to the new energy power station controller and the substation control equipment so that the new energy power station controller and the substation control equipment execute the power grid control strategy.
[0112] This invention also provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the new energy grid-connected area power grid control method as described in any of the method embodiments.
[0113] Embodiments of the present invention also provide a computer storage medium, which can be disposed in a server to store at least one instruction, at least one program, code set, or instruction set for implementing the method embodiments. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the new energy grid-connected area power grid control method as described in any of the method embodiments.
[0114] Optionally, in embodiments of the present invention, the storage medium may be located at at least one of a plurality of network servers in a computer network. Optionally, in embodiments of the present invention, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0115] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0116] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more flowcharts and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0117] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more flowcharts and / or boxes Figure 1 The function specified in one or more boxes.
[0118] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more flowcharts and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0120] Finally, it should be noted that the embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.
Claims
1. A power grid control method for a new energy grid-connected area, characterized in that, The method includes: Collect grid operation parameters of the power grid in the area where new energy is connected to the grid, as well as obtain historical grid operation data and historical weather forecast data; The power grid operation parameters are input into the power grid operation identification network for operation mode identification processing to generate the current power grid operation mode; The historical power grid operation data and historical weather forecast data are input into the power grid operation prediction model for prediction processing, generating a new energy output prediction sequence and a load prediction sequence for the power grid in the new energy grid-connected area for a future preset time period. Based on the current power grid operation mode and the predicted power output and load sequences for future preset time periods, a safety-constrained optimal power flow model is constructed. The interior-point method is used to solve the security-constrained optimal power flow model to generate a power grid control strategy; The power grid control strategy is sent to the new energy power plant controller and the substation control equipment so that the new energy power plant controller and the substation control equipment execute the power grid control strategy.
2. The power grid control method for new energy grid-connected areas according to claim 1, characterized in that, The power grid operation identification network is an LSTM network comprising an input layer, L hidden layers, and an output layer; the process of inputting the power grid operation parameters into the power grid operation identification network for operation mode identification processing to generate the current power grid operation mode includes: The power grid operation parameters are processed through the input layer to generate power grid operation processing parameters. The power grid operation processing parameters are processed by extracting features through the L hidden layers and the time dependency relationship between the power grid operation processing parameters is learned to generate power grid operation features. The power grid operation characteristics are processed by the output gate to identify the current power grid operation mode.
3. The power grid control method for new energy grid-connected areas according to claim 1, characterized in that, The power grid operation prediction model includes an encoder and a decoder; the process of inputting the historical power grid operation data and historical weather forecast data into the power grid operation prediction model for prediction processing, generating a new energy output prediction sequence and a load prediction sequence for the power grid in the new energy grid-connected area for a future preset time period, includes: The historical power grid operation data and its corresponding historical weather forecast data are input into the encoder for encoding processing to generate context features. The encoding process includes parallel analysis of the global dependency between the historical power grid operation data and the historical weather forecast data through a multi-head self-attention mechanism, and processing the historical power grid operation data and the historical weather forecast data in chronological order through a gated loop unit to capture the local evolution patterns between the historical power grid operation data and the historical weather forecast data, thereby generating the context features. The context features are input into the decoder for decoding processing to generate a new energy output prediction sequence and a load prediction sequence for the future preset time period. During the decoding process, an attention mechanism is used to take the context features as the initial state and generate the new energy output prediction sequence and load prediction sequence for the future preset time period step by step in an autoregressive manner.
4. The power grid control method for new energy grid-connected areas according to claim 1, characterized in that, The step of constructing a safety-constrained optimal power flow model based on the current power grid operation mode and the predicted output sequence of new energy sources and the predicted load sequence for a future preset time period includes: Based on the current power grid operation mode, construct an objective function; Based on the predicted sequence of new energy output and the predicted sequence of load for the future preset time period, a power balance constraint is constructed. Based on the objective function, the power balance constraints, and the safety constraints including equality constraints, inequality constraints, and N-1 safety constraints, a safety-constrained optimal power flow model is constructed.
5. The power grid control method for new energy grid-connected areas according to claim 4, characterized in that, The step of solving the security-constrained optimal power flow model using the interior-point method to generate a power grid control strategy includes: By introducing nonnegative relaxation variables, the inequality constraint is transformed into a first constraint in the form of an equality constraint. By adding a logarithmic barrier term to the objective function, the safety-constrained optimal power flow model is transformed into a series of approximate subproblems. The logarithmic barrier term is used to handle the non-negativity of the slack variables. By constructing the Lagrange function and applying Newton's method, the series of approximate subproblems are transformed into a system of linear corrected equations; Under the power balance constraint, equality constraint, first constraint and N-1 security constraint, the linear modified equation system is solved iteratively. In each iteration, the original variables of the optimal power flow model under the security constraint, the non-negative relaxation variables and the corresponding Lagrange multipliers are optimized simultaneously until the convergence condition is reached and the optimal power flow solution is determined. The power grid control strategy is determined based on the optimal power flow solution.
6. The power grid control method for new energy grid-connected areas according to claim 1, characterized in that, After sending the power grid control strategy to the new energy power plant controller and the substation control equipment, the method further includes: The power grid control strategy is dynamically adjusted based on the collected execution feedback data; the execution feedback data is generated by the new energy power plant controller and substation control equipment executing the power grid control strategy. The step of dynamically adjusting the power grid control strategy based on the collected execution feedback data includes: When the new energy power station controller and the substation control equipment execute the power grid control strategy, the execution feedback data is collected; Based on the execution feedback data, identify the power grid operation mode; Based on the power grid operation mode, the safety constraint optimal power flow model is adjusted to adjust the power grid control strategy.
7. The power grid control method for new energy grid-connected areas according to claim 1, characterized in that, The collection of power grid operating parameters includes collecting data on voltage at each node, line current, active power, reactive power, renewable energy output, load data, and power grid topology parameters. The accuracy requirements for collecting these parameters are: 2nd to 50th harmonic content measurement error ≤ ±5%, and 0.1 to 99.9th harmonic error ≤ ±5%. Response time requirements are: reactive power adjustment response time ≤ 2s, dynamic reactive current rise time ≤ 30ms. Adjustment accuracy requirements are: active power control error ≤ 1% of rated power for photovoltaic systems connected to the grid at ≥ 10kV, and response time ≤ 5s.
8. A power grid control system for a new energy grid-connected area, characterized in that, The system includes: The data acquisition module is used to collect grid operation parameters of the power grid in the area where new energy is connected to the grid, as well as to acquire historical grid operation data and historical weather forecast data; The power grid operation mode identification module is used to input the power grid operation parameters into the power grid operation identification network for operation mode identification processing and generate the current power grid operation mode; The prediction module is used to input the historical power grid operation data and historical weather forecast data into the power grid operation prediction model for prediction processing, and generate a new energy output prediction sequence and a load prediction sequence for the power grid in the new energy grid-connected area for a future preset time period. The control strategy generation module is used to construct a safety-constrained optimal power flow model based on the current power grid operation mode and the predicted output sequence and load sequence of new energy sources for a preset time period in the future; solve the safety-constrained optimal power flow model using the interior point method to generate a power grid control strategy; and send the power grid control strategy to the new energy power station controller and the substation control equipment so that the new energy power station controller and the substation control equipment execute the power grid control strategy.
9. An electronic device comprising a processor and a memory, the memory storing at least one instruction and at least one program, the at least one instruction and the at least one program being loaded and executed by the processor to implement the new energy grid-connected regional power grid control method as described in any one of claims 1 to 7.
10. A computer storage medium storing at least one instruction and at least one program, wherein the at least one instruction and the at least one program are loaded and executed by a processor to implement the new energy grid-connected regional power grid control method as described in any one of claims 1 to 7.