Source network load storage system operation control method, system, equipment and medium

Abstract

The invention relates to a source network load storage system operation control method, system and device and a medium. The operation control method comprises the steps of generating a predicted load curve of a preset time period based on historical load data; according to the predicted load curve, each power generation operation characteristic and each power generation cost, determining a power supply power generation plan; constructing an energy storage charging and discharging model according to the energy storage loss, the charging and discharging efficiency and the electricity price curve; constructing a power grid power flow optimization model according to the power grid line loss, the line safety constraint and the line balance constraint; and obtaining a power generation scheme of each power supply, a charging and discharging scheme of the energy storage system and a power flow direction control scheme in a power grid which meet preset target conditions, and controlling the operation of the source grid load storage system. According to the scheme, deep coordination of load source network storage is realized, the energy utilization efficiency is improved, the system stability is enhanced, the power generation cost is reduced, and the reliability, economy and flexibility of a power system are improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of smart grids, and particularly relates to an operation control method, system, electronic device, and storage medium for a source-grid-load-storage system. Background Art

[0002] With the steady progress of the pilot work on the reform of incremental distribution business, the incremental distribution business has started to open to social capital; the construction and planning of the distribution network are no longer solely dominated by grid enterprises, but jointly responsible by multiple investment entities.

[0003] In the operation of the power system, with the continuous increase in the proportion of renewable energy access, its intermittency, volatility, and the complexity of power load demand have made it difficult for the traditional operation mode to coordinate the relationship among power sources, the grid, loads, and energy storage, resulting in problems such as low energy utilization efficiency, poor system stability, and difficult control of power generation costs. Summary of the Invention

[0004] To solve the above problems, the present disclosure provides an operation control method, system, electronic device, and storage medium for a source-grid-load-storage system. This solution uses load forecasting algorithms, power generation plan formulation methods for power sources, energy storage charge-discharge strategies, grid power flow optimization and control means, and collaborative optimization to achieve deep coordination among load, source, grid, and storage.

[0005] To solve the above technical problems, in the first aspect of the present invention, an operation control method for a source-grid-load-storage system is proposed, and the method includes:

[0006] Obtain historical load data, and generate a predicted load curve for a preset time period based on the historical load data;

[0007] Obtain the power generation operation characteristics and power generation costs of each power source, and determine the power generation plan of the power source according to the predicted load curve, each of the power generation operation characteristics, and each of the power generation costs;

[0008] Obtain the energy storage loss, charge-discharge efficiency, and electricity price curve of the energy storage system, and construct an energy storage charge-discharge model according to the energy storage loss, charge-discharge efficiency, and electricity price curve;

[0009] Obtain the grid line loss, line safety constraints, and line balance constraints, and construct a grid power flow optimization model according to the grid line loss, line safety constraints, and line balance constraints;

[0010] Through the predicted load curve, the power generation plan of the power source, the energy storage charge-discharge model, and the grid power flow optimization model, obtain the power generation plan of each power source, the charge-discharge plan of the energy storage system, and the power flow control plan in the grid that meet the preset target conditions;

[0011] Control the operation of the source-network-load-storage system based on the power generation plan, charge-discharge plan, and power flow control plan.

[0012] According to a preferred embodiment of the present invention, the operation control method further includes:

[0013] Calculate the operation benefit after the operation of the source-network-load-storage system;

[0014] Every time a preset time interval passes, optimize the predicted load curve, power generation plan of the power source, charge-discharge model of the energy storage, and the power grid power flow optimization model according to the operation benefit.

[0015] According to a preferred embodiment of the present invention, the calculation of the operation benefit after the operation of the source-network-load-storage system includes:

[0016] Calculate at least one of the energy utilization efficiency, reduction rate of power generation cost of the power source, reduction rate of power grid loss, comprehensive efficiency of the energy storage system, and system operation reliability after the operation of the source-network-load-storage system as the operation benefit.

[0017] According to a preferred embodiment of the present invention, the obtaining of historical load data and generating a predicted load curve for a preset time period based on the historical load data includes:

[0018] Obtain historical load data, date data corresponding to the historical load data, and meteorological data corresponding to each of the date data;

[0019] Perform feature engineering processing on the historical load data, date data, and meteorological data;

[0020] Based on the historical load data, date data, and meteorological data after feature engineering processing, use the backpropagation algorithm to construct a load prediction model for predicting load data;

[0021] Obtain real-time date data and real-time meteorological data, and input them into the load prediction model to generate the predicted load curve for the preset time period.

[0022] According to a preferred embodiment of the present invention, the obtaining of the power generation operation characteristics and power generation costs of each power source, and determining the power generation plan of the power source according to the predicted load curve, each of the power generation operation characteristics, and each of the power generation costs includes:

[0023] Obtain the operation characteristics and power generation costs of each power source;

[0024] Based on the operation characteristics and power generation costs of each power source, use the linear programming algorithm to construct a power generation plan optimization model for the power source;

[0025] Based on the predicted load curve, the operation plan of each power source is obtained by solving through the power generation plan optimization model of the power source, and the operation characteristics of each power source in the operation plan conform to the preset operation characteristic constraints, the generated power conforms to the preset load balance constraints, conforms to the renewable energy generation priority constraints, and the total power generation cost of each power source is optimal;

[0026] Generate a power generation plan for the power source through the operation plan.

[0027] According to a preferred embodiment of the present invention, the obtaining of the energy storage loss, charge-discharge efficiency and electricity price curve of the energy storage system, and the construction of the energy storage charge-discharge model according to the energy storage loss, charge-discharge efficiency and electricity price curve include:

[0028] Obtain the energy storage loss, charge-discharge efficiency and electricity price curve of the energy storage system;

[0029] Determine the charge-discharge power of the energy storage system at each time period according to the predicted load curve;

[0030] Through the dynamic programming algorithm, taking the charge-discharge power as the input, calculate the comprehensive benefits corresponding to different charge-discharge powers under the energy storage loss, charge-discharge efficiency and electricity price curve;

[0031] Construct an energy storage charge-discharge model based on the comprehensive benefits corresponding to the different charge-discharge powers.

[0032] According to a preferred embodiment of the present invention, the obtaining of the power generation plan of each power source, the charge-discharge plan of the energy storage system and the power flow control plan in the power grid that meet the preset target conditions through the predicted load curve, the power generation plan of the power source, the energy storage charge-discharge model and the power grid power flow optimization model includes:

[0033] Based on the predicted load curve, the power generation plan of the power source, the energy storage charge-discharge model and the power grid power flow optimization model, comprehensively generate a collaborative optimization model;

[0034] At every preset time, obtain the power generation data, load data, energy storage data and power grid operation data of each power source, and input them into the collaborative optimization model to generate the power generation plan of each power source, the charge-discharge plan of the energy storage system and the power flow control plan in the power grid.

[0035] To solve the above technical problems, a second aspect of the present invention proposes an operation control system for a source-grid-load-energy storage system, and the system includes:

[0036] A load prediction module, configured to obtain historical load data and generate a predicted load curve for a preset time period based on the historical load data;

[0037] A power generation plan generation module, configured to obtain the power generation operation characteristics and power generation costs of each power source, and determine a power source power generation plan according to the predicted load curve, each of the power generation operation characteristics, and each of the power generation costs;

[0038] A energy storage charge-discharge model generation module, configured to obtain the energy storage loss, charge-discharge efficiency, and electricity price curve of an energy storage system, and construct an energy storage charge-discharge model according to the energy storage loss, charge-discharge efficiency, and electricity price curve;

[0039] A power grid power flow optimization model generation module, configured to obtain the power grid line loss, line safety constraints, and line balance constraints, and construct a power grid power flow optimization model according to the power grid line loss, line safety constraints, and line balance constraints;

[0040] A solution simulation module, configured to obtain, through the predicted load curve, the power source power generation plan, the energy storage charge-discharge model, and the power grid power flow optimization model, a power generation plan for each of the power sources, a charge-discharge plan for the energy storage system, and a power flow control plan in the power grid that meet preset target conditions;

[0041] A system control module, configured to control the operation of the source-network-load-storage system based on the power generation plan, charge-discharge plan, and power flow control plan.

[0042] To solve the above technical problems, a third aspect of the present invention proposes an electronic device, including:

[0043] A processor; and

[0044] A memory storing computer-executable instructions, where the computer-executable instructions, when executed, cause the processor to execute the method described in any one of the above embodiments.

[0045] To solve the above technical problems, a fourth aspect of the present invention proposes a computer storage medium, where the computer storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method described in any one of the above embodiments is implemented.

[0046] Compared with the prior art, the present disclosure has the following advantages: The present disclosure generates a prediction curve based on historical load data, formulates an economically optimal power source combination output plan in combination with power source characteristics and generation costs. Considering energy storage losses, charge-discharge efficiency, and electricity price fluctuations comprehensively, a dynamic charge-discharge model is constructed to achieve electricity price arbitrage or load peak shaving and valley filling. By introducing constraints such as line losses, safe current-carrying capacity, and node power balance, a power grid power flow optimization model is established to ensure the safety and economy of power transmission. By coupling predicted load, generation plan, energy storage model, and power grid constraints, a comprehensive solution that meets preset goals such as the lowest cost, the least emissions, or the highest reliability is solved, and a power source generation strategy, an energy storage charge-discharge plan, and a power grid power dispatch instruction are output. The optimized solution is fed back to the actual operation system to dynamically adjust the power source output, energy storage state, and power grid power flow, forming a closed-loop management of "prediction - decision - control". This solution adopts advanced load prediction algorithms, optimized power source generation plan formulation methods, intelligent energy storage charge-discharge strategies, efficient power grid power flow optimization and control means, and a collaborative optimization and real-time adjustment mechanism to achieve deep coordination of load, power source, power grid, and energy storage, improve energy utilization efficiency, enhance system stability, reduce generation costs, and improve the reliability, economy, and flexibility of the power system.

[0047] Other features and advantages of the present disclosure will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present disclosure. The objectives and other advantages of the present disclosure can be realized and obtained through the structures pointed out in the specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 FIG. 1 shows a schematic flow diagram of a method for operating and controlling a source-grid-load-energy storage system according to an embodiment of the present disclosure;

[0050] Figure 2 FIG. 2 shows a schematic flow diagram of a benefit evaluation and feedback method according to an embodiment of the present disclosure;

[0051] Figure 3 FIG. 3 shows a schematic flow diagram of a method for operating and controlling a source-grid-load-energy storage system according to another embodiment of the present disclosure;

[0052] Figure 4 FIG. 4 shows a schematic flow diagram of a method for operating and controlling a source-grid-load-energy storage system according to yet another embodiment of the present disclosure;

[0053] Figure 5 Shows the fourth schematic diagram of the operation control method of a source-network-load-storage system according to an embodiment of the present disclosure;

[0054] Figure 6 Shows the fifth schematic diagram of the operation control method of a source-network-load-storage system according to an embodiment of the present disclosure;

[0055] Figure 7 Shows the schematic diagram of the structure of a source-network-load-storage system operation control system according to an embodiment of the present disclosure;

[0056] Figure 8 Shows the schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Specific embodiments

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts shall fall within the scope of protection of the present disclosure.

[0058] The same reference numerals in the drawings represent the same or similar elements, components, or parts. Therefore, the repeated description of the same or similar elements, components, or parts may be omitted below. It should also be understood that although the first, second, third, etc. used herein may be used as attributives with numbers to describe various devices, elements, components, or parts, these devices, elements, components, or parts should not be limited by these attributives. That is, these attributives are only used to distinguish one from another. For example, the first device may also be called the second device without departing from the technical solution of the essence of the present invention. In addition, the terms "and / or", "or / and" refer to all combinations including any one or more of the listed items.

[0059] Please refer to Figure 1 , Figure 1 is the first schematic diagram of the operation control method of a source-network-load-storage system provided by the present invention. As Figure 1 shown, the operation control method includes:

[0060] S11. Obtain historical load data and generate a predicted load curve for a preset time period based on the historical load data.

[0061] In this embodiment, historical load data, meteorological data (such as temperature, humidity, light intensity, etc.), and date type data are collected, and feature engineering is performed on these data. For example, the date type is converted into one-hot encoding (such as encoding Monday to Sunday as 0000001 - 1000000 respectively), and the meteorological data is normalized.

[0062] Specifically, for example, smart meters and load characteristic monitoring devices are equipped for various types of electricity loads such as industrial users, commercial users, and residential users, and data such as real-time power demand, load characteristics (such as power factor and harmonic content of the load), and electricity consumption time distribution (statistics of electricity consumption of the load in different periods) are collected.

[0063] In this embodiment, different meteorological data and date type data will affect the electricity use on the load side. For example, when the temperature is too high or too low, the usage of air conditioners will increase significantly, and the electricity consumption of residential users will decrease from Monday to Friday and increase on Saturday and Sunday. The electricity consumption of industrial users and commercial users will also change over time.

[0064] In this embodiment, a load prediction model can be constructed based on the long short-term memory network. The long short-term memory network (LSTM, Long Short-Term Memory) is a time-recurrent neural network, which is specifically designed to solve the long-term dependence problem existing in general RNNs (recurrent neural networks). All RNNs have a chain form of repeating neural network modules. The load prediction model is trained with historical load data, and then the predicted load curve for a preset time period is output through the load prediction model. Specifically, the structure of the LSTM network includes an input layer, a hidden layer, and an output layer. By adjusting hyperparameters such as the number of neurons in the hidden layer and the learning rate, the network weights are continuously optimized using the backpropagation algorithm until the error of the model on the validation set reaches the preset accuracy requirement. After training, the relevant features of real-time meteorological data, date type data, and historical load data are input into the model to obtain the load prediction curve for a future period of time (such as short-term 24 hours, medium-term one week).

[0065] In this embodiment, a load prediction model can also be constructed through other deep learning algorithms in this solution. For example, a convolutional neural network (CNN) can be used to replace the LSTM network for load prediction. CNN extracts features through convolutional operations on data and is suitable for processing data with spatial or temporal local correlations. When constructing the CNN model, after appropriate preprocessing of historical load data, meteorological data, and date type data, they are used as input data and processed through convolutional layers, pooling layers, and fully connected layers to obtain the load prediction result.

[0066] S12. Obtain the power generation operation characteristics and power generation costs of each power source, and determine the power source power generation plan according to the predicted load curve, each power generation operation characteristic, and each power generation cost.

[0067] In this embodiment, different power sources have different power generation operation characteristics and power generation costs. For example, the power generation operation characteristics include: the start-up time, ramp rate, and minimum stable operation output of thermal power generation, the relationship between the reservoir water level and power generation power of hydropower generation, the predicted power generation power of wind power generation and photovoltaic power generation, and the power generation costs include: fuel costs, equipment maintenance costs, carbon emission costs, etc.

[0068] In this embodiment, according to the load prediction curve, combined with the operation characteristics and power generation costs of various power sources, a linear programming algorithm is used to construct an optimization model for the power source power generation plan. The decision variables of the model are the power generation powers of each power generation equipment at different time periods, the objective function is to minimize the total power generation cost, and the constraint conditions include load balance constraints (the sum of the power generation powers of power sources and the charge-discharge power of energy storage at each time period is equal to the load demand power), power generation equipment operation characteristic constraints (such as the upper and lower limits of the output of each power generation equipment, ramp rate limit), and renewable energy power generation priority constraints (under the condition of meeting other constraint conditions, renewable energy power generation is preferentially arranged). By solving this linear programming model, the power source power generation plan is obtained.

[0069] In this embodiment, the above solution requires preferentially arranging renewable energy power generation. For example, wind power generation, hydropower generation, etc. Hydropower generation may not be able to work in time due to water storage requirements, while wind power generation has the problem of being uncontrollable. In this solution, when determining the power source power generation plan, the power generation requirements for power sources of renewable energy power generation can also be reduced to ensure meeting the load demand.

[0070] S13. Obtain the energy storage loss, charge-discharge efficiency, and electricity price curve of the energy storage system, and construct an energy storage charge-discharge model according to the energy storage loss, charge-discharge efficiency, and electricity price curve.

[0071] In this embodiment, the energy storage loss of the energy storage system can consider the influence of charge-discharge depth and cycle times on the battery life. For example, the rain flow counting method is used to calculate the equivalent cycle times of the battery, and the life loss is calculated according to the battery attenuation characteristic curve.

[0072] In this embodiment, the energy storage system has different efficiency curves at different charge-discharge powers, which can be obtained through experimental tests or determined through historical data, and the electricity price curve can obtain the information of peak-valley electricity price periods or the real-time electricity price change curve announced by the local power grid.

[0073] In this embodiment, an energy storage charge-discharge optimization model is established with the life loss of the energy storage system, charge-discharge efficiency, and the fluctuation law of electricity market prices as constraints. The energy storage charge-discharge optimization model can determine the charge-discharge power requirements of the energy storage system for each period. The goal is to maximize the economic benefits of the entire source-grid-load-energy storage system within a certain period. For example, since the energy storage system is used for energy storage, it can charge during the period when the electricity price is at the bottom and discharge during the period when the electricity price is at the peak, so as to achieve the goal of maximizing benefits. At the same time, the charge-discharge requirements of the energy storage system are also affected by the load demand on the load side and the energy storage loss during the charge-discharge operation of the energy storage system, etc.

[0074] In this embodiment, according to the power generation plan of the power source, the load forecasting results, and the real-time power output of the power source and load demand, the charge-discharge target of the energy storage is determined. When the renewable energy generation is excessive (such as the wind power generation power is greater than the sum of the load demand and the planned power generation power of other power sources) and the load demand is low, the energy storage charge target is set to store the excess electric energy to improve the energy utilization rate; when the load demand is at a peak (such as exceeding a certain proportion of the historical peak load in the same period) and the power generation of the power source is insufficient (such as the renewable energy generation power is low and the conventional energy generation has reached the upper limit), the energy storage discharge target is set to supplement the power gap and maintain the power balance of the system.

[0075] S14. Obtain the grid line loss, line safety constraints, and line balance constraints, and construct a grid power flow optimization model based on the grid line loss, line safety constraints, and line balance constraints.

[0076] In this embodiment, the interior point method is used for optimal power flow calculation. First, a grid power flow optimization model is constructed. The decision variables of the model are the output power distribution of each power generation device and energy storage device (such as the active power and reactive power of each generator, the charge-discharge power of the energy storage device) and the power flow direction in the grid (the active power and reactive power of each line). The objective function is to minimize the grid loss (calculate the line loss based on the line resistance and power and sum them). The constraint conditions include the safety constraints of the grid (such as the line capacity limit, that is, the transmission power of each line cannot exceed its rated capacity; the voltage stability range constraint, the voltage amplitude of each node needs to be within the specified upper and lower limits) and the power balance constraint (the injected power of each node is equal to the outflow power). By solving this model with the interior point method, the optimal output power of each power generation device and energy storage device and the power flow direction distribution in the grid are obtained to achieve the efficient operation of the grid.

[0077] In this embodiment, the interior point method is used to implement grid power flow optimization calculation and the real-time monitoring and control platform responds to faults. The interior point method is an algorithm for solving linear programming or nonlinear convex optimization problems.

[0078] In this embodiment, in addition to the interior point method, the Newton method can also be used for power flow optimization calculation of the power grid. The Newton method iteratively solves the optimal power flow problem by solving the Jacobian matrix of the power flow equation. When constructing the power grid power flow optimization model, the minimum power grid loss is also used as the objective function, considering the power grid security constraints and power balance constraints, and using the iterative calculation mechanism of the Newton method to gradually approach the optimal solution, so as to obtain the optimal output of the power generation equipment and energy storage device and the power flow direction in the power grid.

[0079] S15. Through the predicted load curve, power generation plan of the power source, charge-discharge model of the energy storage, and power grid power flow optimization model, obtain the power generation plans of each power source, charge-discharge plans of the energy storage system, and power flow control plans in the power grid that meet the preset target conditions.

[0080] In this embodiment, based on the dynamic update of the real-time monitoring data, the model predictive control algorithm is used to perform real-time rolling solution on the working plans of each component in the source-grid-load-storage system, so as to ensure that each power source works according to the power generation plan, the energy storage system works according to the charge-discharge plan, and the power grid works according to the power flow control plan.

[0081] For example, at a certain time interval (such as 15 minutes), the latest data such as the power output of the power source, load demand, energy storage state, and power grid operation parameters can be obtained, and these data are input into the collaborative optimization model to re-solve the optimized operation strategies of each link. According to the solution results, the operation strategies of each link are adjusted immediately and accurately.

[0082] S16. Control the operation of the source-grid-load-storage system based on the power generation plan, charge-discharge plan, and power flow control plan.

[0083] In this embodiment, the corresponding devices in the source-grid-load-storage system are controlled by the determined power generation plan, charge-discharge plan, and power flow control plan.

[0084] In this embodiment, if there is a large deviation between the actual load and the predicted value (such as the deviation exceeds 10% of the predicted value), the correction mechanism can also be immediately started to re-determine the power generation plan of the power source and adjust the charge-discharge strategy of the energy storage according to the new load situation; if the power grid operation state changes due to external interference or internal faults (such as a new line fault), quickly re-optimize the power grid power flow distribution plan and adjust the output of the power generation equipment and energy storage device to ensure the stable operation of the power system.

[0085] In this embodiment, when obtaining data, the data can be cleaned, outliers removed, and the data format unified. Specifically, data cleaning: Using data filtering algorithms to remove noise data (such as abnormal data caused by sensor failures or electromagnetic interference) and duplicate data in the collected data. Outlier removal: By setting a data threshold range and combining data statistical analysis methods, identify and remove outliers that significantly deviate from the normal range. For example, for voltage data, if it exceeds ±10% of the normal voltage fluctuation range, it is determined as an outlier and removed. Data format unification: Convert data from different sources and in different formats into a unified data format to facilitate subsequent data processing and analysis. For example, convert all time data into the standard timestamp format.

[0086] As Figure 2 shown, in this embodiment, the solution can also establish a benefit evaluation and feedback mechanism, establish a comprehensive benefit evaluation index system and use it for optimization and improvement of each link, specifically including the following steps:

[0087] S21. Calculate the operating benefit after the operation of the source-grid-load-storage system.

[0088] In this embodiment, regularly (such as monthly or quarterly), use professional evaluation methods to comprehensively and deeply evaluate and analyze the operating benefits of the system. Obtain the specific values of each evaluation index through methods such as data statistical analysis and model calculation.

[0089] In this embodiment, specifically, the operating benefit can be one or more of the energy utilization efficiency, power generation cost reduction rate, power grid loss reduction rate, comprehensive efficiency of the energy storage system, and system operation reliability after the operation of the source-grid-load-storage system.

[0090] In this embodiment, for example, establish an integrated operation benefit evaluation index system for the load-source-grid-storage, including energy utilization efficiency (energy comprehensive utilization rate = actual energy utilization amount / total energy supply, renewable energy consumption rate = actual renewable energy power generation amount / renewable energy power generation capacity), power generation cost reduction rate (calculate the reduction ratio of power generation cost compared with the traditional operation mode), power grid loss reduction rate (compare the reduction ratio of power grid loss before and after optimization), comprehensive benefit of the energy storage system (economic benefit = income obtained by the energy storage through the peak-valley electricity price difference - energy storage investment and operation and maintenance costs, technical benefit = quantitative index for improving system stability due to the participation of the energy storage, environmental benefit = quantitative index for reducing carbon emissions due to the energy storage assisting in the consumption of renewable energy), system reliability index (power outage time, power outage frequency, ability index of the power system to resist extreme events, such as the probability of the system remaining normal operation under extreme weather conditions), etc.

[0091] S22. Every time a preset time interval elapses, optimize the predicted load curve, power generation plan, energy storage charge-discharge model, and power grid power flow optimization model according to the operating benefits.

[0092] In this embodiment, the evaluation results are fed back to each operation link, providing valuable basis for optimizing the load prediction model (such as adjusting the hyperparameters of the LSTM network and adding new feature variables according to the evaluation results), adjusting the power generation plan formulation strategy (such as optimizing the power generation resource allocation rules and improving the cost accounting method), improving the energy storage charge-discharge optimization algorithm (such as optimizing the life loss model and adjusting the constraint conditions), and perfecting the power grid power flow optimization and control method (such as improving the security constraint model and optimizing the response speed of the control strategy), so as to achieve the continuous iterative improvement and optimization upgrade of the integrated operation method of load-source-grid-energy storage, and continuously improve the overall operation level and performance of the power system.

[0093] Please refer to Figure 3 , Figure 3 FIG. 2 is the second schematic flow chart of the operation control method for the source-grid-load-energy storage system provided by the present invention. As Figure 3 shown, the operation control method includes the following steps:

[0094] S31. Obtain historical load data, date data corresponding to the historical load data, and meteorological data corresponding to each date data.

[0095] In this embodiment, the load data generally refers to information related to the load of the power system or equipment. In the power system, the load data reflects the power demand of the power grid, substation, distribution station or specific user at a certain moment or within a certain period of time. These data are crucial for the stable operation, load prediction, planning and management of the power system.

[0096] In this embodiment, the date data and the corresponding meteorological data include: temperature, humidity, light intensity, etc.

[0097] S32. Perform feature engineering processing on the historical load data, date data, and meteorological data.

[0098] In this embodiment, the date type is converted into one-hot encoding, and the meteorological data is normalized. Feature engineering processing may also include data cleaning, outlier removal, and data format unification, etc. Data cleaning: Use a data filtering algorithm to remove noise data (such as abnormal data caused by sensor failures or electromagnetic interference) and duplicate data in the collected data. Outlier removal: By setting a data threshold range and combining data statistical analysis methods, identify and remove outliers that significantly deviate from the normal range. For example, for voltage data, if it exceeds ±10% of the normal voltage fluctuation range, it is determined as an outlier and removed. Data format unification: Convert data from different sources and different formats into a unified data format for subsequent data processing and analysis. For example, convert all time data into a standard timestamp format.

[0099] S33. Based on the historical load data, date data, and meteorological data after feature engineering processing, use the backpropagation algorithm to construct a load prediction model for predicting load data.

[0100] In this embodiment, a load prediction model is constructed based on the long short-term memory network (LSTM). The structure of the LSTM network includes an input layer, a hidden layer, and an output layer. By adjusting hyperparameters such as the number of neurons in the hidden layer and the learning rate, use the backpropagation algorithm to continuously optimize the network weights until the error of the model on the validation set reaches the preset accuracy requirement.

[0101] S34. Obtain real-time date data and real-time meteorological data, and input them into the load prediction model to generate a predicted load curve for a preset time period.

[0102] In this embodiment, relevant features of real-time meteorological data, date type data, and historical load data are input into the model to obtain a load prediction curve for a future period of time (such as short-term 24 hours, medium-term one week).

[0103] Please refer to Figure 4 , Figure 4 which is the third schematic diagram of the operation control method of the source-network-load-storage system provided by the present invention. As Figure 4 shown, the operation control method includes the following steps:

[0104] S41. Obtain the operation characteristics and power generation costs of each power source.

[0105] In this embodiment, different power sources have different power generation operation characteristics and power generation costs. For example, the power generation operation characteristics include: the startup time, ramp rate, and minimum stable operation output of thermal power generation, the relationship between the reservoir water level and power generation power of hydropower generation, the predicted power generation power of wind power generation and photovoltaic power generation, and the power generation costs include: fuel costs, equipment maintenance costs, carbon emission costs, etc.

[0106] S42. Based on the operating characteristics and generation costs of each power source, a linear programming algorithm is used to construct an optimization model for the power generation plan of the power sources.

[0107] In this embodiment, a linear programming algorithm is used to construct an optimization model for the power generation plan of the power sources. The decision variables of the model are the power generation powers of each power generation device at different time periods, the objective function is to minimize the total power generation cost, and the constraint conditions include load balance constraints, operating characteristic constraints of power generation devices, and priority constraints for renewable energy power generation.

[0108] S43. Based on the predicted load curve, the operating plans of each power source are obtained by solving the optimization model for the power generation plan of the power sources. In the operating plan, the operating characteristics of each power source meet the preset operating characteristic constraints, the power generation power meets the preset load balance constraints, meets the priority constraints for renewable energy power generation, and the total power generation cost of each power source is optimal.

[0109] S44. A power generation plan for the power sources is generated through the operating plan.

[0110] In this embodiment, by solving the optimization model for the power generation plan of the power sources, a power generation plan for the power sources is obtained. The operation of the power sources in the power generation plan meets various constraints. The preset operating characteristic constraints can be the upper and lower limits of the output of each power generation device and the ramp rate limit. The load balance constraint can be that the sum of the power generation power of each power source and the charge-discharge power of the energy storage at each time period is equal to the load demand power. The priority constraint for renewable energy power generation can be to preferentially select power sources of renewable energy for power generation under the condition of meeting other constraints. The operating plan with the lowest total power generation cost is selected from the operating plans of the power sources that meet each constraint as the operating plan in this solution.

[0111] Please refer to Figure 5 , Figure 5 which is the fourth schematic diagram of the operation control method for the source-network-load-storage system provided by the present invention. As shown in Figure 5 , the operation control method includes the following steps:

[0112] S51. Obtain the energy storage loss, charge-discharge efficiency, and electricity price curve of the energy storage system.

[0113] In this embodiment, the energy storage loss of the energy storage system can consider the influence of the charge-discharge depth and the number of cycles on the battery life. For example, the rain flow counting method is used to calculate the equivalent cycle number of the battery, and the life loss is calculated according to the attenuation characteristic curve of the battery.

[0114] In this embodiment, the energy storage system has different efficiency curves at different charge-discharge powers, which can be obtained through experimental tests or determined through historical data. The electricity price curve can obtain the peak-valley electricity price period information or the real-time electricity price change curve announced by the local power grid.

[0115] S52. Determine the charging and discharging power of the energy storage system for each time period according to the predicted load curve.

[0116] S53. Using the dynamic programming algorithm, take the charging and discharging power as the input, and calculate the comprehensive benefits corresponding to different charging and discharging powers under the energy storage loss, charging and discharging efficiency, and electricity price curve.

[0117] In this embodiment, the dynamic programming algorithm is used to solve this model. By dividing the entire operation cycle into multiple stages, calculate the optimal charging and discharging decisions according to the current state (such as the SOC of the energy storage, electricity price, power supply, and load conditions) in each stage, and gradually deduce the optimal charging and discharging strategy for the entire cycle.

[0118] S54. Construct an energy storage charging and discharging model based on the comprehensive benefits corresponding to different charging and discharging powers.

[0119] In this embodiment, summarize the comprehensive benefits corresponding to each charging and discharging power to obtain the energy storage charging and discharging model.

[0120] In this embodiment, the model predictive control algorithm can be used to replace the dynamic programming algorithm for optimizing the energy storage charging and discharging strategy. The model predictive control algorithm is based on the current state of the system and the prediction model, and solves an optimization problem with a finite time domain in each control cycle to obtain the control strategy at the current moment. In the optimization of the energy storage charging and discharging strategy, according to the current energy storage SOC, power generation plan of the power supply, load prediction, and electricity market price prediction and other information, construct a prediction model, take the maximization of the comprehensive benefits of the energy storage system within a finite time domain as the objective function, solve to obtain the current energy storage charging and discharging strategy, and recalculate according to the new state information in the next cycle.

[0121] Please refer to Figure 6 , Figure 6 which is the fifth schematic diagram of the flow of the operation control method for the source-grid-load-storage system provided by the present invention. As Figure 6 shown, the operation control method includes the following steps:

[0122] S61. Based on the predicted load curve, power generation plan of the power supply, energy storage charging and discharging model, and power grid power flow optimization model, comprehensively generate a collaborative optimization model.

[0123] In this embodiment, load forecasting, power generation plan formulation, energy storage charging and discharging strategy optimization, and power grid power flow optimization and control are synergistically integrated to construct an integrated coordinated optimization model for the power grid, power sources, loads, and energy storage systems. The objective function of the model is a multi-objective optimization of the overall reliability (measured by indicators such as system average outage frequency and system average outage duration), economy (comprehensive cost indicators such as power generation cost, power grid operation cost, energy storage investment and operation and maintenance costs), and environmental friendliness (indicators such as total carbon emissions and renewable energy utilization rate) of the power system. The constraint conditions include interaction constraints between various links (such as the balance constraint between the power generation power of power sources, the charging and discharging power of energy storage, and load demand, and the power balance constraint in power grid power flow calculation), as well as the physical and technical constraints of each link itself (such as the operation characteristics constraints of power generation equipment, energy storage system constraints, and power grid safety constraints).

[0124] S62. At every preset time, obtain the power generation data, load data, energy storage data, and power grid operation data of each power source, and input them into the coordinated optimization model to generate the power generation plan of each power source, the charging and discharging plan of the energy storage system, and the power flow control plan in the power grid.

[0125] In this embodiment, based on the dynamic update of real-time monitoring data, the model predictive control algorithm is used to perform real-time rolling solution on the working plans of each component in the power grid, power sources, loads, and energy storage systems, so as to ensure that each power source works according to the power generation plan, the energy storage system works according to the charging and discharging plan, and the power grid works according to the power flow control plan.

[0126] Please refer to Figure 7 , Figure 7 FIG. is an operation control system for a power grid, power sources, loads, and energy storage systems provided by the present invention. The system includes: a load forecasting module 11, a power generation plan generation module 12, an energy storage charging and discharging model generation module 13, a power grid power flow optimization model generation module 14, a scheme simulation module 15, and a system control module 16.

[0127] In this embodiment, the load forecasting module 11 is used to obtain historical load data and generate a predicted load curve for a preset time period based on the historical load data.

[0128] In this embodiment, the power generation plan generation module 12 is used to obtain the power generation operation characteristics and power generation costs of each power source, and determine the power generation plan of the power source according to the predicted load curve, the power generation operation characteristics of each power source, and the power generation costs of each power source.

[0129] In this embodiment, the energy storage charging and discharging model generation module 13 is used to obtain the energy storage loss, charging and discharging efficiency, and electricity price curve of the energy storage system, and construct an energy storage charging and discharging model according to the energy storage loss, charging and discharging efficiency, and electricity price curve.

[0130] In this embodiment, the power grid power flow optimization model generation module 14 is configured to obtain power grid line losses, line safety constraints, and line balance constraints, and construct a power grid power flow optimization model based on the power grid line losses, line safety constraints, and line balance constraints.

[0131] In this embodiment, the solution simulation module 15 is configured to obtain a power generation solution for each power source, a charge-discharge solution for the energy storage system, and a power flow control solution in the power grid that meet preset target conditions by predicting load curves, power generation plans of power sources, charge-discharge models of energy storage, and the power grid power flow optimization model.

[0132] In this embodiment, the system control module 16 is configured to control the operation of the source-grid-load-storage system based on the power generation solution, the charge-discharge solution, and the power flow control solution.

[0133] In this embodiment, the system further includes an evaluation and feedback module, configured to calculate the operation benefit after the operation of the source-grid-load-storage system; and optimize the predicted load curve, the power generation plan of the power source, the charge-discharge model of the energy storage, and the power grid power flow optimization model according to the operation benefit every preset time interval.

[0134] In this embodiment, the evaluation and feedback module is specifically configured to calculate at least one of the energy utilization efficiency, the reduction rate of the power generation cost of the power source, the reduction rate of the power grid loss, the comprehensive efficiency of the energy storage system, and the operation reliability of the system after the operation of the source-grid-load-storage system as the operation benefit.

[0135] In this embodiment, the load prediction module 11 is specifically configured to obtain historical load data, date data corresponding to the historical load data, and meteorological data corresponding to each date data; perform feature engineering processing on the historical load data, date data, and meteorological data; construct a load prediction model for predicting load data by using the backpropagation algorithm based on the historical load data, date data, and meteorological data after feature engineering processing; obtain real-time date data and real-time meteorological data, and input them into the load prediction model to generate a predicted load curve for a preset time period.

[0136] In this embodiment, the power generation plan generation module 12 is specifically configured to obtain the operation characteristics and power generation costs of each power source; construct a power generation plan optimization model for the power source by using the linear programming algorithm based on the operation characteristics and power generation costs of each power source; solve the operation plan of each power source through the power generation plan optimization model based on the predicted load curve, where the operation characteristics of each power source in the operation plan meet the preset operation characteristic constraints, the power generation power meets the preset load balance constraints, meets the renewable energy generation priority constraints, and the total power generation cost of each power source is optimal; and generate a power generation plan for the power source through the operation plan.

[0137] In this embodiment, the energy storage charge-discharge model generation module 13 is specifically configured to obtain the energy storage loss, charge-discharge efficiency, and electricity price curve of the energy storage system; determine the charge-discharge power of the energy storage system at each time period according to the predicted load curve; use the dynamic programming algorithm, take the charge-discharge power as the input, and calculate the comprehensive benefits corresponding to different charge-discharge powers under the energy storage loss, charge-discharge efficiency, and electricity price curve; and construct an energy storage charge-discharge model based on the comprehensive benefits corresponding to different charge-discharge powers.

[0138] In this embodiment, the scheme simulation module 15 is specifically configured to comprehensively generate a collaborative optimization model based on the predicted load curve, power generation plan of the power sources, energy storage charge-discharge model, and power grid power flow optimization model; every preset time, obtain the power generation data, load data, energy storage data, and power grid operation data of each power source, and input them into the collaborative optimization model to generate the power generation scheme of each power source, the charge-discharge scheme of the energy storage system, and the power flow control scheme in the power grid.

[0139] As Figure 8 shown, an embodiment of the present invention provides an electronic device, including a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140. Among them, the processor 1110, the communication interface 1120, and the memory 1130 complete mutual communication through the communication bus 1140;

[0140] The memory 1130 is used to store a computer program;

[0141] The processor 1110 is configured to implement any of the above methods when executing the program stored on the memory 1130.

[0142] For the electronic device provided in the embodiment of the present invention, the processor 1110 obtains historical load data by executing the program stored on the memory 1130, generates a predicted load curve for a preset time period based on the historical load data; obtains the power generation operation characteristics and power generation costs of each power source, and determines the power generation plan of the power sources according to the predicted load curve, each power generation operation characteristic, and each power generation cost; obtains the energy storage loss, charge-discharge efficiency, and electricity price curve of the energy storage system, and constructs an energy storage charge-discharge model according to the energy storage loss, charge-discharge efficiency, and electricity price curve; obtains the power grid line loss, line safety constraints, and line balance constraints, and constructs a power grid power flow optimization model according to the power grid line loss, line safety constraints, and line balance constraints; through the predicted load curve, power generation plan of the power sources, energy storage charge-discharge model, and power grid power flow optimization model, obtains the power generation scheme of each power source, the charge-discharge scheme of the energy storage system, and the power flow control scheme in the power grid that meet the preset target conditions; and controls the operation of the source-network-load-storage system based on the power generation scheme, charge-discharge scheme, and power flow control scheme.

[0143] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity in illustration, only a thick line is used in the figure to represent it, but it does not mean that there is only one bus or one type of bus.

[0144] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0145] The memory 1130 may include a Random Access Memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory 1130 may also be at least one storage device located far from the aforementioned processor 1110.

[0146] The above-mentioned processor 1110 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0147] An embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors 1110 to implement the method of any of the above embodiments.

[0148] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in the form of a computer program product in whole or in part. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

[0149] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A source-grid-load-storage system operation control method, characterized in that: The method comprises: Acquiring historical load data, and generating a predicted load curve for a preset time period based on the historical load data; Obtaining the power generation operation characteristics and power generation costs of each power source, and determining a power generation plan based on the predicted load curve, each power generation operation characteristic, and each power generation cost; Obtaining energy storage loss, charge and discharge efficiency, and electricity price curve of the energy storage system, and constructing an energy storage charge and discharge model based on the energy storage loss, charge and discharge efficiency, and electricity price curve; Obtaining power grid line losses, line safety constraints, and line balance constraints, and constructing a power grid power flow optimization model based on the power grid line losses, line safety constraints, and line balance constraints; Obtaining, through the predicted load curve, the power generation plan of the power source, the energy storage charging and discharging model, and the power grid flow optimization model, a power generation plan for each of the power sources, a charging and discharging plan for the energy storage system, and a power flow control plan in the power grid that meet preset target conditions; The operation of the source-grid-load-storage system is controlled based on the power generation scheme, charging and discharging scheme, and power flow control scheme.

2. The operation control method according to claim 1, characterized in that: The operation control method further includes: Calculate the operating benefits of the source-grid-load-storage system after operation; At every preset time interval, the predicted load curve, power generation plan, energy storage charging and discharging model, and the power grid flow optimization model are optimized according to the operating benefits.

3. The operation control method according to claim 2, characterized in that: The calculation to obtain the operating benefits of the source-grid-load-storage system after operation includes: Calculate at least one of the energy utilization efficiency, power generation cost reduction rate, grid loss reduction rate, energy storage system comprehensive efficiency and system operation reliability after the source-grid-load-storage system is put into operation as the operation benefit.

4. The operation control method according to claim 1, characterized in that: The acquiring of historical load data and generating a predicted load curve for a preset time period based on the historical load data includes: Acquire historical load data, date data corresponding to the historical load data, and meteorological data corresponding to each date data; Performing feature engineering processing on the historical load data, date data, and meteorological data; Based on the historical load data, date data and meteorological data processed by feature engineering, a load forecasting model for forecasting load data is constructed using a back propagation algorithm; Real-time date data and real-time meteorological data are acquired and input into the load forecasting model to generate the forecast load curve for a preset time period.

5. The operation control method according to claim 1, characterized in that: The obtaining of the power generation operation characteristics and power generation costs of each power source, and determining a power generation plan based on the predicted load curve, each power generation operation characteristic, and each power generation cost, includes: Obtain the operating characteristics and power generation costs of each power source; Based on the operating characteristics and power generation costs of each of the power sources, a linear programming algorithm is used to construct a power generation plan optimization model; Based on the predicted load curve, an operation plan for each of the power sources is obtained by solving the power generation plan optimization model, wherein the operating characteristics of each of the power sources in the operation plan meet preset operating characteristic constraints, the generated power meets preset load balance constraints, meets renewable energy generation priority constraints, and the total power generation cost of each of the power sources is optimal; A power generation plan is generated based on the operation plan.

6. The operation control method according to claim 1, characterized in that: The acquiring of energy storage loss, charge and discharge efficiency, and electricity price curve of the energy storage system, and constructing an energy storage charge and discharge model based on the energy storage loss, charge and discharge efficiency, and electricity price curve, includes: Obtain the energy storage loss, charging and discharging efficiency, and electricity price curve of the energy storage system; Determine the charging and discharging power of the energy storage system in each period based on the predicted load curve; By using a dynamic programming algorithm, the charge and discharge power is used as input to calculate the comprehensive benefits corresponding to different charge and discharge powers under the energy storage loss, charge and discharge efficiency and electricity price curves; An energy storage charging and discharging model is constructed based on the comprehensive benefits corresponding to the different charging and discharging powers.

7. The operation control method according to any one of claims 1 to 6, characterized in that: The method of obtaining a power generation scheme for each power source, a charge and discharge scheme for the energy storage system, and a power flow control scheme in the power grid that meet preset target conditions through the predicted load curve, the power source power generation plan, the energy storage charge and discharge model, and the power grid flow optimization model includes: Comprehensively generating a collaborative optimization model based on the predicted load curve, the power generation plan, the energy storage charging and discharging model, and the power grid flow optimization model; At preset intervals, the power generation data, load data, energy storage data, and grid operation data of each power source are obtained and input into the collaborative optimization model to generate power generation plans for each power source, charging and discharging plans for the energy storage system, and power flow control plans in the grid.

8. A source-grid-load-storage system operation control system, characterized in that: The system comprises: A load forecasting module, configured to obtain historical load data and generate a forecast load curve for a preset time period based on the historical load data; a power generation plan generating module, configured to obtain the power generation operation characteristics and power generation costs of each power source, and determine a power generation plan based on the predicted load curve, each power generation operation characteristic, and each power generation cost; An energy storage charge and discharge model generation module is used to obtain the energy storage loss, charge and discharge efficiency and electricity price curve of the energy storage system, and to construct an energy storage charge and discharge model based on the energy storage loss, charge and discharge efficiency and electricity price curve; A power flow optimization model generation module is used to obtain power line losses, line safety constraints, and line balance constraints, and to construct a power flow optimization model based on the power line losses, line safety constraints, and line balance constraints; a scheme simulation module, configured to obtain, through the predicted load curve, the power generation plan of the power source, the energy storage charging and discharging model, and the power grid flow optimization model, a power generation scheme for each of the power sources, a charging and discharging scheme for the energy storage system, and a power flow control scheme in the power grid that meet preset target conditions; A system control module is used to control the operation of the source-grid-load-storage system based on the power generation plan, charging and discharging plan, and power flow control plan.

9. An electronic device, characterized in that: include: processor; as well as A memory storing computer executable instructions which, when executed, cause the processor to perform the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that in, The computer storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images