Measurement and control method and device suitable for source network load storage collaborative management and control and storage medium
The LSTM algorithm predicts load demand and combines the genetic algorithm to generate collaborative control strategies, which solves the problem that traditional power grid system regulation methods cannot achieve equipment linkage, realizes precise collaborative control of the power network system, and ensures efficient and stable power supply.
Patent Information
- Application Number
- CN202411572792.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-06
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional power grid system regulation methods cannot achieve the linkage between control and equipment, and cannot accurately coordinate the control of each specific device according to the control strategy, resulting in an imbalance in supply and demand that affects the safe operation of the power grid.
The load demand prediction model is constructed using the LSTM algorithm, and the power supply data of power supply equipment and charging and discharging data of energy storage equipment are calculated by combining genetic algorithms to generate the optimal power supply distribution of power supply equipment and charging and discharging distribution of energy storage equipment as collaborative control strategies, through automation The control system adjusts the equipment status in real time.
Accurate coordinated control of the power network system is achieved, ensuring efficient, stable and sustainable power supply, avoiding supply and demand imbalance, and improving the operational safety of the power grid.
Smart Images

Figure CN119093503A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power systems, and in particular to a measurement and control device and method suitable for coordinated control of sources, networks, loads and storage. Background Art
[0002] The coordinated control of sources, grids, loads and storage is an emerging energy system dispatching and management method that aims to achieve the coordinated operation and optimization of renewable energy, power grids and energy storage systems. With the rapid development and popularization of renewable energy, the amount of renewable energy power generation in the power system has gradually increased, but its intermittent and volatile nature has brought new challenges to the stability and reliability of the power system. At the same time, the rapid development of energy storage technology has provided flexibility and dispatchability to the power system, making energy storage equipment an important means to balance the supply and demand of renewable energy, regulate the frequency of the power system and respond to power system failures.
[0003] Traditional power grid system control methods mainly adopt the "source follows load" model, which is unable to predict the future power demand at the load end. When the power demand at the load end suddenly increases, once the power generation capacity on the power supply side is insufficient, there will be an imbalance between supply and demand, which will seriously affect the safe operation of the power grid. In addition, traditional methods only provide some control strategies through algorithm solutions, but cannot achieve the linkage between control and equipment, and cannot accurately coordinate the control of each specific device according to the control strategy provided. Summary of the invention
[0004] In order to solve the problem that the linkage between control and equipment cannot be achieved and each specific device cannot be accurately coordinated and controlled according to the given control strategy, the present invention provides a measurement and control device and method suitable for coordinated control of source, grid, load and storage.
[0005] In the first aspect, the present invention provides a measurement and control method suitable for source-grid-load-storage coordinated management and control, which adopts the following technical solution: A measurement and control method suitable for source-grid-load-storage coordinated management and control, comprising the following steps: S1, real-time acquisition of power supply data of power supply equipment, charging and discharging data of energy storage equipment and load demand data and storage in the database; S2, builds a load demand forecasting model using the LSTM algorithm to output the predicted load demand; S3, using a genetic algorithm to calculate the power supply data of the power supply equipment, the charging and discharging data of the energy storage equipment and the load demand, and obtain the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal coordinated control strategy; S4, generating control instructions according to the optimal control strategy, and adjusting the power supply state and the charging and discharging state of the energy storage device in real time according to the control instructions.
[0006] Optionally, the specific steps of step S3 include: S3-1, construct multiple individuals and randomly generate an initial population, each individual includes a set of current power supply data of the power supply device and charging and discharging data of the energy storage device; S3-2, calculate the fitness value of each individual in combination with the predicted load demand; S3-3, based on the fitness value, select multiple excellent individuals from the current population as the parents of the next generation; S3-4, perform a crossover operation on the selected parent generation to generate new offspring individuals; S3-5, when it is determined that the improvement in fitness is greater than the threshold, return to S3-3, when it is determined that the improvement in fitness is less than the threshold, obtain the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal collaborative control strategy.
[0007] Optionally, the power supply data of the power supply device includes the power generation cost and the output power of each power supply device, and the energy storage device charging and discharging data includes the energy storage cost and the charging and discharging power of each energy storage device; the calculation of the fitness value specifically includes: Calculate the cost of electricity generation:
[0008] Calculate energy storage costs:
[0009] Calculate the supply-demand imbalance penalty cost:
[0010] Where N is the number of power supply devices. The output power of the power supply device is , is the cost of the power supply equipment, M is the number of energy storage devices, The charging and discharging power of an energy storage device is , is the cost of energy storage equipment, is the penalty cost caused by the difference between the actual power supply data and the demand data. The predicted load demand is ; Calculate the fitness function :
[0011]
[0012] in, is the total cost, α, β, and γ are weight factors, It is a positive number between (0,0.1].
[0013] Optionally, step S3-4 further includes: randomly changing the genes of offspring individuals with a preset mutation probability to increase the diversity of the population.
[0014] Optionally, the specific steps of the tournament selection are as follows: Randomly select multiple individuals from the current population as contestants; Compare the fitness values between the contestants and select the individual with the best fitness as the winner; Repeat the above steps until the preset number of winners is reached.
[0015] Optionally, the crossover operation includes a single-point crossover, and the charge and discharge data of the energy storage devices of two parent individuals are exchanged to complete the crossover.
[0016] Optionally, in step S2, building the model specifically includes: The historical load demand data in the database is used as a data set, and the data set is divided into a training set and a validation set, and the training set and the validation set are processed into input and output variables respectively; The neural network model is trained through the training set to obtain the initial prediction model; Validate the initial prediction model using the validation set; Determine a corresponding loss value based on the predicted load demand output by the model and the mean square error loss function, and judge whether the loss value is less than a threshold value; If it is less than the threshold, the prediction model is obtained; If it is not less than the threshold, the parameters corresponding to the initial prediction model are corrected based on the loss value, and the prediction model is updated.
[0017] In the second aspect, a measurement and control method for coordinated control of source, grid, load and storage includes: The information acquisition module acquires the power supply data of the power supply equipment, the available power and charging and discharging data of the energy storage equipment, and the load demand data in real time and stores them in the database; The load forecasting module uses the LSTM algorithm to build a load demand forecasting model to output the predicted load demand; The strategy generation module uses a genetic algorithm to calculate the power supply data of the power supply equipment, the charging and discharging data of the energy storage equipment, and the load demand, and obtains the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal collaborative control strategy; The control module generates control instructions according to the optimal control strategy, and adjusts the power supply status and the charging and discharging status of the energy storage device in real time according to the control instructions.
[0018] In a third aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned measurement and control method for coordinated management and control of source, grid, load and storage.
[0019] In summary, the present invention has the following beneficial technical effects: According to the collaborative control strategy formulated by the genetic algorithm, the power supply equipment and energy storage equipment are precisely and collaboratively controlled using advanced automation control systems to ensure that the power network system always maintains the best operating state. At the same time, a more efficient, stable and sustainable power supply is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 It is a flow chart of a measurement and control method suitable for coordinated management and control of source, grid, load and storage according to an embodiment of the present invention.
[0021] Figure 2 It is a structural schematic diagram of a measurement and control device suitable for coordinated control of source, grid, load and storage according to an embodiment of the present invention. DETAILED DESCRIPTION
[0022] The following is combined with Figure 1-2 The present invention is described in further detail.
[0023] Example 1 Reference Figure 1 A measurement and control method suitable for source-grid-load-storage coordinated management and control in this embodiment includes the following steps: S1, real-time acquisition of power supply data of power supply equipment, charging and discharging data of energy storage equipment and load demand data and storage in the database; in this embodiment, the power supply data of power supply equipment includes power supply power, power supply voltage, etc., and the charging and discharging data of energy storage equipment includes charging and discharging power, charging and discharging voltage, etc. Obtain the real-time operation data of the power network system in an all-round way, and these data are continuously transmitted to the central control center through the high-speed communication network. Using advanced data analysis technology, the real-time data is intelligently preprocessed to remove noise and outliers to ensure the accuracy and reliability of the data. At the same time, the data are analyzed in detail to accurately determine the current power supply of the power supply equipment and the available power of the energy storage equipment. For power supply equipment, not only its current output power is considered, but also its operating status, maintenance history and potential failure risks are comprehensively evaluated to more accurately estimate its sustainable power supply capacity. For energy storage equipment, by real-time monitoring of indicators such as battery status, charging and discharging efficiency and remaining life, the available power is accurately calculated, providing a solid foundation for subsequent collaborative control.
[0024] S2, builds a load demand forecasting model using the LSTM algorithm to output the predicted load demand; The load demand of the power grid has time series characteristics and is affected by many factors such as season, weather, and time. LSTM can analyze historical load data, explore the laws of load changes, and predict future load demand. For example, by inputting hourly load data, date type (weekdays, weekends, holidays, etc.), temperature and other information over a period of time, the LSTM model can learn the impact of different factors on load demand, predict the load demand at a certain moment in the future, and help virtual power plants reasonably arrange the operation of power generation and energy storage equipment to meet user needs.
[0025] The construction of the model specifically includes: The historical load demand data in the database is used as a data set, and the data set is divided into a training set and a validation set, and the training set and the validation set are processed into input and output variables respectively; The neural network model is trained through the training set to obtain the initial prediction model; Validate the initial prediction model using the validation set; Determine a corresponding loss value based on the predicted load demand output by the model and the mean square error loss function, and judge whether the loss value is less than a threshold value; If it is less than the threshold, the prediction model is obtained; If it is not less than the threshold, the parameters corresponding to the initial prediction model are corrected based on the loss value, and the prediction model is updated.
[0026] S3, using genetic algorithms to calculate the power supply data of power supply equipment, the charging and discharging data of energy storage equipment and the load demand, and obtain the optimal power supply distribution of power supply equipment and the charging and discharging distribution of energy storage equipment as the optimal collaborative control strategy; Genetic Algorithms (GA) is a search algorithm that simulates natural selection and genetics mechanisms, and it searches for the optimal solution through an iterative process. In the dynamic collaborative optimization of power grid systems, genetic algorithms can be used to determine the output of power supply equipment, the charging and discharging strategy of energy storage equipment, etc., to minimize costs, maximize reliability, or meet other multi-objective optimization requirements.
[0027] The specific steps include: S3-1, construct multiple individuals and randomly generate an initial population, each individual includes a set of current power supply data of the power supply device and charging and discharging data of the energy storage device; S3-2, calculate the fitness value of each individual in combination with the predicted load demand; The power supply data of the power supply equipment includes the power generation cost and the output power of each power supply equipment, and the energy storage equipment charging and discharging data includes the energy storage cost and the charging and discharging power of each energy storage equipment; the calculation of the fitness value specifically includes: Calculate the cost of power generation: The cost of power generation usually consists of two parts: fixed cost and variable cost. Fixed cost (such as equipment depreciation, maintenance cost, etc.) has no direct relationship with the power generation, while variable cost (such as fuel cost, operation and maintenance cost, etc.) increases with the increase of power generation;
[0028]
[0029] Calculate energy storage cost: The energy storage cost function also involves multiple aspects, including the investment cost, operation cost, maintenance cost and charging and discharging efficiency loss of energy storage equipment;
[0030]
[0031] Calculation of supply-demand imbalance penalty costs: The calculation of supply-demand imbalance penalty costs is usually to encourage the system to achieve supply-demand balance as much as possible and reduce waste, losses or additional costs caused by supply-demand mismatch. This penalty cost can be designed to be proportional to the degree of supply-demand imbalance, or a more complex function can be used to reflect the economic impact of different imbalance levels.
[0032]
[0033] Where N is the number of power supply devices. The output power of the power supply device is , The cost of the power supply equipment, For the The cost coefficient of a power supply device, M is the number of energy storage devices, The charging and discharging power of an energy storage device is , is the cost of energy storage equipment, and No. The cost coefficient of each energy storage device, is the penalty cost caused by the difference between the actual power supply data and the demand data. The predicted load demand is ; Calculate the fitness function :
[0034]
[0035] in, is the total cost, α, β, γ are all weight factors, α+β+γ=1, is a very small positive number used to ensure that the denominator is not 0. In this embodiment, a positive number between (0, 0.1] is used.
[0036] In actual applications, these weights and specific calculation methods may need to be adjusted according to the specific conditions of the power network system and the preferences of the operator.
[0037] In addition, if there are other important optimization objectives (such as voltage stability, frequency deviation, etc.), they can also be added to the fitness function in a similar way and assigned corresponding weights.
[0038] Finally, it should be noted that the design of the fitness function is an iterative and optimization process, which may need to be adjusted according to actual operation data and feedback to obtain the best optimization effect.
[0039] S3-3, based on the fitness value, select multiple excellent individuals from the current population as the parents of the next generation; use the tournament selection to select multiple excellent individuals from the current population as the parents of the next generation. The specific steps are as follows: Randomly select multiple individuals from the current population as contestants; Compare the fitness values between the contestants and select the individual with the best fitness as the winner; Repeat the above steps until the preset number of winners is reached.
[0040] S3-4, crossover operation is performed on the selected parent generation to generate new child individuals; the crossover operation includes single-point crossover, which exchanges the charging and discharging data of the energy storage devices of the two parent generation individuals to complete the crossover. When more content is considered, other crossover methods can also be used.
[0041] S3-5, when it is determined that the improvement in fitness is greater than the threshold, return to S3-3, when it is determined that the improvement in fitness is less than the threshold, obtain the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal collaborative control strategy.
[0042] S4, generating control instructions according to the optimal control strategy, and adjusting the power supply state and the charging and discharging state of the energy storage device in real time according to the control instructions.
[0043] According to the collaborative control strategy formulated by the genetic algorithm, the power supply equipment and energy storage equipment are precisely and collaboratively controlled using advanced automation control systems. The operating status of the power network system is monitored in real time, and the control effect is continuously fed back. If the actual operating conditions deviate from the predicted results, the dynamic adjustment mechanism of the genetic algorithm is immediately activated. By re-evaluating the current status and future needs, the collaborative control strategy is adjusted and optimized in real time to ensure that the power network system always remains in the best operating state. At the same time, actively explore interactive modes with users, encourage users to participate in demand response, and jointly participate in the collaborative control of the power network system to achieve more efficient, stable and sustainable power supply.
[0044] Example 2 The difference between this embodiment and embodiment 1 is that this embodiment provides a measurement and control device for source-grid-load-storage coordinated control, referring to Figure 2 ,include: The information acquisition module acquires the power supply data of the power supply equipment, the available power and charging and discharging data of the energy storage equipment, and the load demand data in real time and stores them in the database; The load forecasting module uses the LSTM algorithm to build a load demand forecasting model to output the predicted load demand; The strategy generation module uses a genetic algorithm to calculate the power supply data of the power supply equipment, the charging and discharging data of the energy storage equipment, and the load demand, and obtains the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal collaborative control strategy; The control module generates control instructions according to the optimal control strategy, and adjusts the power supply status and the charging and discharging status of the energy storage device in real time according to the control instructions.
[0045] Example 3 The difference between this embodiment and embodiment 1 is that this embodiment provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned measurement and control method for coordinated management and control of source, grid, load and storage.
[0046] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. As for the method disclosed in the embodiment, since it corresponds to the system disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0047] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0048] The above disclosure is only a preferred embodiment of the present invention, but the present invention is not limited thereto. Any non-creative changes that can be thought of by a person skilled in the art, as well as several improvements and modifications made without departing from the principle of the present invention, should fall within the protection scope of the present invention.
Claims
1. A measurement and control method suitable for coordinated management and control of source, grid, load and storage. It is characterized in that The following steps are involved: S1, real-time acquisition of power supply data of power supply equipment, available power and charging and discharging data of energy storage equipment, and load demand data and storage in the database; S2, builds a load demand forecasting model using the LSTM algorithm to output the predicted load demand; S3, using a genetic algorithm to calculate the power supply data of the power supply equipment, the charging and discharging data of the energy storage equipment and the load demand, and obtain the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal coordinated control strategy; S4, generating control instructions according to the optimal control strategy, and adjusting the power supply state and the charging and discharging state of the energy storage device in real time according to the control instructions.
2. According to claim 1, the measurement and control method suitable for source-grid-load-storage coordinated management and control, It is characterized in that The specific steps of step S3 include: S3-1, construct multiple individuals and randomly generate an initial population, each individual includes a set of current power supply data of the power supply device and charging and discharging data of the energy storage device; S3-2, calculate the fitness value of each individual in combination with the predicted load demand; S3-3, based on the fitness value, select multiple excellent individuals from the current population as the parents of the next generation; S3-4, perform a crossover operation on the selected parent generation to generate new offspring individuals; S3-5, when it is determined that the improvement in fitness is greater than the threshold, return to S3-3, when it is determined that the improvement in fitness is less than the threshold, obtain the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal collaborative control strategy.
3. According to claim 2, the measurement and control method suitable for source-grid-load-storage coordinated management and control, It is characterized in that The power supply data of the power supply equipment includes the power generation cost and the output power of each power supply equipment, and the energy storage equipment charging and discharging data includes the energy storage cost and the charging and discharging power of each energy storage equipment; the calculation of the fitness value specifically includes: Calculate the cost of electricity generation: Calculate energy storage costs: Calculate the supply-demand imbalance penalty cost: Where N is the number of power supply devices. The output power of the power supply device is , is the cost of the power supply equipment, M is the number of energy storage devices, The charging and discharging power of an energy storage device is , is the cost of energy storage equipment, is the penalty cost caused by the difference between the actual power supply data and the demand data. The predicted load demand is ; Calculate the fitness function : in, is the total cost, α, β, and γ are weight factors, It is a positive number between (0,0.1].
4. The measurement and control method adapted for source-grid-load-storage coordinated management and control according to claim 2, It is characterized in that Step S3-4 also includes: randomly changing the genes of offspring individuals with a preset mutation probability to increase the diversity of the population.
5. The measurement and control method suitable for source-grid-load-storage coordinated management and control according to claim 2, It is characterized in that In step S3-3, tournament selection is used to select multiple excellent individuals from the current population as the parents of the next generation. The specific steps are as follows: Randomly select multiple individuals from the current population as contestants; Compare the fitness values between the contestants and select the individual with the best fitness as the winner; Repeat the above steps until the preset number of winners is reached.
6. The measurement and control method adapted for coordinated management and control of source, grid, load and storage according to claim 2, It is characterized in that The crossover operation includes a single-point crossover, which completes the crossover by exchanging the charging and discharging data of the energy storage devices of two parent individuals.
7. The measurement and control method adapted for source-grid-load-storage coordinated management and control according to claim 1, It is characterized in that In step S2, the construction of the model specifically includes: The historical load demand data in the database is used as a data set, and the data set is divided into a training set and a validation set, and the training set and the validation set are processed into input and output variables respectively; The neural network model is trained through the training set to obtain the initial prediction model; Validate the initial prediction model using the validation set; Determine a corresponding loss value based on the predicted load demand output by the model and the mean square error loss function, and judge whether the loss value is less than a threshold value; If it is less than the threshold, the prediction model is obtained; If it is not less than the threshold, the parameters corresponding to the initial prediction model are corrected based on the loss value, and the prediction model is updated.
8. A measurement and control device for coordinated control of source, grid, load and storage. It is characterized in that include: The information acquisition module acquires the power supply data of the power supply equipment, the available power and charging and discharging data of the energy storage equipment, and the load demand data in real time and stores them in the database; The load forecasting module uses the LSTM algorithm to build a load demand forecasting model to output the predicted load demand; The strategy generation module uses a genetic algorithm to calculate the power supply data of the power supply equipment, the charging and discharging data of the energy storage equipment, and the load demand, and obtains the optimal power supply distribution of the power supply equipment and the charging and discharging distribution of the energy storage equipment as the optimal collaborative control strategy; The control module generates control instructions according to the optimal control strategy, and adjusts the power supply status and the charging and discharging status of the energy storage device in real time according to the control instructions.
9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the measurement and control method for coordinated management and control of source, grid, load and storage as described in any one of claims 1 to 8.
Citation Information
Patent Citations
Multi-energy complementary optimization scheduling method and system in electricity market environment
CN117578409A
Regional energy scheduling method and system based on source network load storage cooperative control
CN117674274A
Power system partition load demand prediction method, system and device and storage medium
CN117713084A
Cooperative operation control method and device of power grid equipment, equipment and storage medium
CN117895579A
Cited By
User side energy storage operation monitoring analysis method based on source network load cooperation
CN119382134A
Micro-grid management method and system based on source grid load storage
CN121840719A
