Scheduling optimization method and system for source-network-load-storage integrated system

Abstract

The invention relates to a scheduling optimization method and system for a source-grid-load-storage integrated system. The method comprises the following steps: collecting historical load and power generation data of the source-grid-load-storage integrated system; training a prediction model by using the historical load and the power generation data; outputting the state of the source-network-load-storage integrated system by using the prediction model; constructing a comprehensive objective function according to the state of the source-network-load-storage integrated system; and solving the comprehensive objective function to obtain an optimal scheduling strategy. According to the method, the comprehensive objective function is constructed based on the predicted system state, multiple objectives such as economy, reliability and environmental benefits can be considered at the same time, scheduling result one-sidedness caused by single objective optimization is avoided, and multi-objective balance is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of source network load storage integration power supply, in particular to a scheduling optimization method and system of a source network load storage integration system. BACKGROUND

[0002] With the increasing global energy demand and the growing environmental problems, the development and utilization of renewable energy become particularly important. Photovoltaic power generation as an important renewable energy technology has the characteristics of clean, efficient and sustainable. However, the intermittency and instability of photovoltaic power generation bring challenges to the dispatching and management of power systems. In order to improve the utilization rate of photovoltaic power generation and ensure the stable operation of power systems, energy storage systems have gradually become a research and application hotspot. Energy storage systems can store excess power when power demand is low and release it when demand is high, thereby balancing power supply and demand. The introduction of energy storage systems not only improves the utilization efficiency of photovoltaic power generation, but also reduces the dependence of power systems on fossil fuels and reduces carbon emissions.

[0003] In actual operation, in order to play the comprehensive benefits of photovoltaic and energy storage systems, the energy storage system needs to be optimized and dispatched. Such scheduling is often influenced by multiple factors, including photovoltaic power prediction, power load prediction, state of charge (SOC) of energy storage system, charge and discharge power limit, real-time electricity price fluctuation, grid operation constraint, etc. Especially in the environment of introducing power market mechanism, the real-time change of electricity price further increases the complexity of energy storage scheduling. Some existing energy storage scheduling methods still have deficiencies in prediction accuracy, economic benefit trade-off, dynamic price response, etc., resulting in that the economic benefit and operation efficiency of the energy storage system cannot be optimized at the same time.

[0004] Therefore, how to optimize the charge and discharge strategy of the energy storage system considering various operation constraints and market fluctuations, and realize the maximization of economic benefit and energy storage utilization rate, has become a technical problem to be solved. SUMMARY

[0005] To solve the above problems, the purpose of the embodiments of the present application is to provide a scheduling optimization method and system of a source network load storage integration system.

[0006] A scheduling optimization method of a source network load storage integration system, comprising: Step 1: Collecting historical load and power generation data of the source network load storage integration system; Step 2: Training a prediction model using the historical load and power generation data; Step 3: Using the prediction model to output the state of the source network load storage integration system; Step 4: Constructing a comprehensive objective function according to the state of the source network load storage integration system; Step 5: solving the comprehensive objective function to obtain an optimal scheduling strategy.

[0007] Preferably, in the step 1, the historical load and power generation data include: power consumption load history records, electricity price data, power generation of photovoltaic power stations at different time periods, environmental factors of photovoltaic power generation, and charging and discharging power and state of the energy storage system.

[0008] Preferably, in the step 2, the power generation of photovoltaic power stations at different time periods, environmental factors of photovoltaic power generation, and electricity price data are used as samples to train a photovoltaic power generation amount prediction model.

[0009] Preferably, in the step 2, the power consumption load history records are used as samples to train a power consumption load prediction model.

[0010] Preferably, in the step 2, the charging and discharging power and state of the energy storage system are used as samples to train an energy storage system state prediction model.

[0011] Preferably, in the step 3, the comprehensive objective function is: wherein, is the power discharged at time t, is the power charged at time t, is the electricity price sold at time t, is the electricity price purchased at time t, is the state of the energy storage system at time t, and is a weight coefficient.

[0012] Preferably, the comprehensive objective function is solved to obtain an optimal scheduling strategy with the goal of maximizing economic benefits.

[0013] The application also provides a scheduling optimization system of a source-grid-load-storage integrated system, comprising: a data acquisition module configured to collect historical load and power generation data of the source-grid-load-storage integrated system; a prediction model training module configured to train a prediction model using the historical load and power generation data; a state prediction module configured to output a state of the source-grid-load-storage integrated system using the prediction model; an objective function construction module configured to construct a comprehensive objective function according to the state of the source-grid-load-storage integrated system; a function solving module configured to solve the comprehensive objective function to obtain an optimal scheduling strategy.

[0014] The application further provides an electronic device, including a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, the transceiver, the memory and the processor being connected through the bus, characterized in that the computer program, when executed by the processor, implements the steps in the dispatch optimization method of the source-network-load-storage integrated system.

[0015] The application further provides a storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps in the dispatch optimization method of the source-network-load-storage integrated system.

[0016] According to the specific embodiments of the application, the following technical effects are achieved: The application relates to a dispatch optimization method of a source-network-load-storage integrated system, and compared with the prior art, the application constructs a comprehensive target function based on a predicted system state, can simultaneously consider multiple targets such as economy, reliability and environmental benefits, avoids one-sidedness of a dispatch result caused by single-target optimization, and realizes multi-target balance.

[0017] In order to make the above objectives, characteristics and advantages of the present application more apparent, clear and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are referred to for detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0019] Figure 1 A dispatch optimization method flow chart of a source-network-load-storage integrated system provided by the present application is shown in the figure. Figure 2 A prediction model construction principle diagram provided by the present application is shown in the figure. Figure 3 A multi-target optimization principle diagram provided by the present application is shown in the figure. Figure 4 A dispatch optimization system principle diagram of a source-network-load-storage integrated system provided by the present application is shown in the figure. DETAILED DESCRIPTION

[0020] In the description of the present application, it needs to be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise" and the like indicate the orientation or positional relationship shown in the drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0021] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0022] In the present application, unless otherwise specifically defined and limited, the terms "mounting", "connection", "connection", "fixing" and the like should be broadly understood, for example, it can be fixedly connected, or it can be detachably connected, or it can be integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0023] Please refer to Figure 1 A scheduling optimization method of a source network load storage integrated system, comprising: Step 1: Collecting historical load and power generation data of the source network load storage integrated system; In the step 1, the historical load and power generation data include: electricity load history record, electricity price data, power generation of photovoltaic power station in different time periods, environmental factors of photovoltaic power generation, and charging and discharging power and state of energy storage system.

[0024] Step 2: Training a prediction model using the historical load and power generation data; In the step 2, the power generation of photovoltaic power station in different time periods, the environmental factors of photovoltaic power generation and the electricity price data are used as samples to train the photovoltaic power generation prediction model. The electricity load history record is used as a sample to train the electricity load prediction model. The charging and discharging power and state of the energy storage system are used as samples to train the energy storage system state prediction model.

[0025] Step 3: Outputting the state of the source network load storage integrated system using the prediction model; In the step 3, the comprehensive objective function is: wherein, is the power discharged at time t, is the power charged at time t, is the electricity price sold at time t, is the electricity price purchased at time t, is the state of the energy storage system at time t, and is the weight coefficient.

[0026] Step 4: constructing a comprehensive objective function according to the state of the source network load storage integrated system; Step 5: solving the comprehensive objective function to obtain an optimal scheduling strategy.

[0027] The application of the source network load storage integrated system scheduling optimization method will be further described below in combination with a specific application scenario: Step S101. Constructing a model and optimizing the model based on real-time data, the method comprising: Based on the model prediction technology, the application obtains data through sensors, databases and other information sources. These data include historical records of electricity load, power generation of photovoltaic power stations at different time periods, and charging and discharging power and state of the energy storage system. In addition, environmental factors affecting photovoltaic power generation, such as solar irradiance, temperature, wind speed, etc., and real-time and historical electricity price data are also included. By collecting and analyzing these data in detail, the patterns and rules of electricity consumption and power generation can be identified, the accuracy of photovoltaic power generation prediction can be improved, and an optimized scheduling strategy can be developed to maximize economic benefits and efficient use of the energy storage system.

[0028] Model initialization and adjustment are important steps for realizing comprehensive energy scheduling optimization. In the model initialization stage, the basic parameters of the model need to be defined and configured first. Secondly, the original data collected usually contains noise and missing values, which need to be filtered out and the missing information needs to be filled in through the cleaning process. Then, the data of different time scales are uniformly processed to ensure time alignment and consistency. In addition, continuous variables such as photovoltaic power generation, electricity load and electricity price are normalized to eliminate the influence of dimension and make different data types comparable in the model. For environmental factors, smoothing processing is also needed to reduce the impact of mutations on the model. Finally, the model is initially trained through the collected historical data to establish the basic prediction ability and scheduling strategy.

[0029] As real-time data is continuously fed back during actual operation, the model needs to be dynamically adjusted and optimized. By updating the input data and adjusting the model parameters, it can more accurately reflect the current load demand and photovoltaic power generation status, thereby optimizing the charging and discharging strategy of the energy storage system, maximizing economic benefits, and achieving efficient utilization of the energy storage system.

[0030] The model's negative feedback mechanism is a crucial element in ensuring the continuous improvement and self-correction of the integrated energy dispatch optimization system. During actual operation, the model continuously evaluates its prediction accuracy and the effectiveness of its dispatch strategy based on real-time data feedback. If the predicted photovoltaic power generation or electricity load deviates significantly from the actual situation, the model triggers the negative feedback mechanism to reduce errors by adjusting parameters or retraining parts of the model. Furthermore, when the charging and discharging behavior of the energy storage system fails to achieve the expected economic benefits or energy storage optimization goals, the negative feedback mechanism analyzes the causes of these deviations and updates the dispatch strategy in real time to improve the model's responsiveness and adaptability. This continuous negative feedback adjustment not only corrects deviations and optimizes performance but also maintains the system's efficient operation in a constantly changing environment, ultimately maximizing energy utilization and optimizing economic benefits.

[0031] Step S102. Determine the future state based on the model output results, and simultaneously construct a multi-objective optimization function model, the method of which includes: like Figure 2 As shown, by accurately predicting photovoltaic power generation, electricity load, and the status of energy storage systems, the model can provide detailed energy allocation plans for various future time periods. Using this output data, the system can predict the potential future status of the integrated power generation, grid, load, and energy storage system. For example, if the prediction shows a significant increase in photovoltaic power generation in the future, i.e., output far exceeds load, it is called a state of oversupply; conversely, if the expected load demand exceeds power generation capacity, i.e., load far exceeds output, it is called a state of undersupply; or if output and load are equal, it is called a state of supply and demand balance.

[0032] Based on the above results, a multi-objective function model is constructed. This model aims to balance and optimize multiple competing objectives. First, an economic benefit objective function is constructed, which maximizes the overall economic benefit by calculating the revenue and cost of photovoltaic power generation, energy storage system charging and discharging, and electricity trading.

[0033] In the formula, It is the power (kW) discharged at time t. It is the charging power at time t. It is the electricity price at time t ($ / kWh). It refers to the electricity price when purchasing electricity at time t.

[0034] Secondly, a storage maximization objective function is constructed, aiming to maintain a high state of the storage system as much as possible to ensure sufficient power support during peak demand periods.

[0035] where, is the state of the storage system at time t (in percentage).

[0036] Finally, a comprehensive objective function is constructed, which combines the above objectives through a weighted sum method to balance the economic benefits and storage maximization, the two core objectives.

[0037] where, and is the weight coefficient, used to balance the relative importance of economic benefits and storage maximization, and its value is dynamically adjusted according to the calculated source-grid-load-storage integrated system state.

[0038] The model needs to consider multiple constraints, including the charge and discharge power limits of the storage system and the state limits of the storage system, to ensure the feasibility of the optimization results. By using a suitable optimization algorithm, the comprehensive objective function is solved to obtain the optimal scheduling strategy. This multi-objective function model not only effectively coordinates energy supply and demand, but also improves the economic benefits and energy utilization efficiency of the system.

[0039] Step S103. Obtain the benefit maximization strategy, and the method comprises: As shown in Figure 3 , by accurately predicting the amount of photovoltaic power generation, electricity load and real-time electricity price, the model can provide detailed energy supply and demand information for each time period in the future. Based on these prediction data, the system uses a multi-objective optimization algorithm to maximize economic benefits and efficient use of the storage system. The benefit maximization strategy is achieved by adjusting the photovoltaic power generation, charging and discharging operations of the storage system, and electricity trading decisions in real time: charging at low electricity prices to store energy, and discharging or selling electricity at peak electricity prices to maximize profits. At the same time, the optimization algorithm dynamically adjusts the strategy to ensure that the storage system can provide sufficient power support at critical moments, preventing excessive discharge or excessive charging. By integrating these optimization operations, the benefit maximization strategy not only significantly improves overall economic benefits, but also enhances the stability and reliability of the system, fully utilizing renewable energy while responding to fluctuations in electricity demand.

[0040] Please refer to Figure 4 , the present application also provides a source-grid-load-storage integrated system scheduling optimization system, comprising: The data acquisition module is configured to collect historical load and power generation data of the source-grid-load-storage integrated system. The prediction model training module is configured to train a prediction model using the historical load and power generation data. The state prediction module is configured to output a state of the source-grid-load-storage integrated system using the prediction model. The objective function construction module is configured to construct a comprehensive objective function according to the state of the source-grid-load-storage integrated system. The function solving module is configured to solve the comprehensive objective function to obtain an optimal scheduling strategy.

[0041] Compared with the prior art, the scheduling optimization system of the source-grid-load-storage integrated system has the same beneficial effects as the scheduling optimization method of the source-grid-load-storage integrated system, and thus repeated description is omitted here.

[0042] The application further provides an electronic device, which comprises a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected through the bus, and the computer program is executed by the processor to implement the steps of the scheduling optimization method of the source-grid-load-storage integrated system.

[0043] The application further provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the scheduling optimization method of the source-grid-load-storage integrated system.

[0044] The above description is merely a specific implementation of the application, and the protection scope of the application is not limited thereto, and any person skilled in the art can easily think of changes or replacement technical solutions within the technical range disclosed by the application, which should be covered in the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A scheduling optimization method for an integrated source-grid-load-storage system, characterized in that, include: Step 1: Collect historical load and power generation data of the integrated power generation, grid, load and storage system; Step 2: Train the prediction model using the historical load and power generation data; Step 3: Use the prediction model to output the status of the integrated source-grid-load-storage system; Step 4: Construct a comprehensive objective function based on the status of the integrated power generation, grid, load, and storage system; Step 5: Solve the comprehensive objective function to obtain the optimal scheduling strategy.

2. The scheduling optimization method for an integrated source-grid-load-storage system according to claim 1, characterized in that, In step 1, the historical load and power generation data include: historical electricity load records, electricity price data, power generation of the photovoltaic power station in different time periods, environmental factors of photovoltaic power generation, and charging and discharging power and status of the energy storage system.

3. The scheduling optimization method for an integrated source-grid-load-storage system according to claim 2, characterized in that, In step 2, the photovoltaic power generation prediction model is trained using data on the power generation of the photovoltaic power plant at different time periods, environmental factors of photovoltaic power generation, and electricity prices.

4. The scheduling optimization method for an integrated source-grid-load-storage system according to claim 2, characterized in that, In step 2, the historical electricity load data is used as a sample to train the electricity load prediction model.

5. The scheduling optimization method for an integrated source-grid-load-storage system according to claim 2, characterized in that, In step 2, the charging and discharging power and state of the energy storage system are used as samples to train the energy storage system state prediction model.

6. The scheduling optimization method for an integrated source-grid-load-storage system according to claim 1, characterized in that, In step 3, the comprehensive objective function is: in, It is the power discharged at time t. It is the charging power at time t. The price of electricity sold at time t. The price of electricity purchased at time t. This refers to the state of the energy storage system at time t. and It is the weighting coefficient.

7. The scheduling optimization method for an integrated source-grid-load-storage system according to claim 6, characterized in that, The optimal scheduling strategy is obtained by solving the comprehensive objective function with the goal of maximizing economic benefits.

8. A scheduling optimization system for an integrated power generation, grid, load, and storage system, characterized in that, include: The data acquisition module is used to collect historical load and power generation data of the integrated power generation, grid, load and storage system; A prediction model training module is used to train a prediction model using the historical load and power generation data. The state prediction module is used to output the state of the integrated source-grid-load-storage system using the prediction model; The objective function construction module is used to construct a comprehensive objective function based on the state of the integrated source-grid-load-storage system. The function solving module is used to solve the comprehensive objective function to obtain the optimal scheduling strategy.

9. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that, When the computer program is executed by the processor, it implements the steps in the scheduling optimization method of the integrated source-grid-load-storage system as described in any one of claims 1-7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the scheduling optimization method of the integrated source-grid-load-storage system as described in any one of claims 1-7.

Images