Power distribution optimization method for source network load storage system

Abstract

The invention provides a power distribution optimization method for a source network load storage system. Wherein the real-time operation data of the source network load storage system is obtained, and the real-time operation data at least comprises the generating capacity, the electrical load and the energy storage state; according to the real-time operation data, predicting the generating capacity, the electrical load and the energy storage demand in a future time period; and adjusting the working states of a power generation unit, a power utilization unit and an energy storage unit of the source network load storage system based on the prediction result so as to realize power supply and demand balance, wherein the adjustment of the working state at least comprises the steps of changing the output power of the power generation unit, adjusting the consumption power of the power utilization unit and controlling the charging and discharging behaviors of the energy storage unit. According to the technical scheme provided by the invention, the response speed of the source network load storage system is improved, and the power supply and demand balance is effectively optimized.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of power distribution optimization, and in particular to a power distribution optimization method for a source-grid-load-storage system. Background Art

[0002] As the proportion of renewable energy continues to increase, the management of source-grid-load-storage systems faces increasing challenges. Especially for hybrid energy systems that include intermittent energy sources such as wind and solar energy, how to ensure a dynamic balance between power supply and demand has become one of the key issues. Therefore, a technical solution that can monitor the system status in real time and respond quickly is needed.

[0003] Traditional SCADA systems may have data update delays, affecting system response speed. Existing prediction methods are limited by model accuracy and data quality and cannot provide sufficiently accurate prediction results. In addition, existing control logic is difficult to cope with complex and changeable supply and demand situations, especially when dealing with sudden supply and demand fluctuations. Summary of the invention

[0004] The embodiment of the present application provides a power distribution optimization method for a source-grid-load-storage system, which is used to solve the problem that the prior art cannot ensure a dynamic balance between power supply and demand.

[0005] In a first aspect, an embodiment of the present application provides a power distribution optimization method for a source-grid-load-storage system, comprising: Acquire real-time operation data of the source-grid-load-storage system, wherein the real-time operation data at least includes power generation, power load, and energy storage status; Predicting the power generation, power load, and energy storage demand in a future time period according to the real-time operation data; adjusting the working states of the power generation unit, power consumption unit, and energy storage unit of the source-grid-load-storage system based on the prediction results to achieve a balance between power supply and demand; The adjustment of the working state at least includes changing the output power of the power generation unit, adjusting the power consumption of the power consumption unit, and controlling the charging and discharging behavior of the energy storage unit.

[0006] Optionally include: Collecting status information of each unit in the source-grid-load-storage system through a sensor network; The state information is aggregated and preprocessed to form the real-time operation data.

[0007] Optionally include: Use historical data analysis and machine learning algorithms to predict future power generation and load; According to the prediction result and the current energy storage state, a charging and discharging plan of the energy storage unit is determined.

[0008] Optionally include: Establish a multi-objective optimization model; Solving the multi-objective optimization model using a mixed integer linear programming method to obtain the optimal working state of each unit; The multi-objective optimization model includes at least three objective functions: cost minimization, carbon emission minimization, and power supply and demand balance maximization. The calculation formulas corresponding to the three objective functions are defined as follows:

[0009] in, represents the minimum total operating cost, Indicates The cost factor of each unit, Indicates The power of each unit, Indicates The fixed cost of a unit, is the total number of units in the system, represents the minimum emission, Indicates The emission factor for each unit, Indicates the maximum power supply. Indicates the maximum power demand, The balance between electricity supply and demand is maximized. Indicates The power supply of each power supply unit, Indicates The power consumption of each power unit.

[0010] Optionally, it also includes: After adjusting the working state, the actual operating effect of the source-grid-load-storage system is monitored and fed back to the control system for iterative optimization.

[0011] Optionally, it also includes: Dynamically adjust the output power of the power generation unit according to weather forecast information and seasonal changes; Intelligently schedule the usage time of power units based on users' power usage habits and demand forecasts.

[0012] Optionally, it also includes: Applying a multi-objective optimization algorithm to determine a comprehensive optimization strategy for the power generation unit, the power consumption unit, and the energy storage unit; The formula is defined as follows:

[0013] in, represents the objective function value corresponding to the comprehensive optimization strategy, , , are the weight coefficients of cost, emission and power supply-demand gap, Indicates the minimum power demand. Indicates the maximum power limit of the system. Indicates the maximum allowable emission.

[0014] Optionally, it also includes: Adjust the charging and discharging strategy of the energy storage unit to minimize the peak power of the grid; Among them, the calculation formula corresponding to minimizing the peak power of the power grid is defined as follows:

[0015] in, represents the peak power of the power grid, Indicates A power supply unit at time The power supply Indicates The power consumption unit at time of electricity consumption, Indicates that the energy storage unit is at time The charge and discharge capacity changes, Indicates the maximum charge and discharge power of the energy storage unit.

[0016] In an embodiment of the present application, the real-time operation data of the source-grid-load-storage system is obtained, and the real-time operation data at least includes power generation, power load, and energy storage status; the power generation, power load, and energy storage demand in the future time period are predicted based on the real-time operation data; based on the prediction results, the working states of the power generation unit, power unit, and energy storage unit of the source-grid-load-storage system are adjusted to achieve a balance between power supply and demand; wherein, the adjustment of the working state at least includes changing the output power of the power generation unit, adjusting the power consumption of the power unit, and controlling the charging and discharging behavior of the energy storage unit. The technical solution provided by the present application improves the response speed of the source-grid-load-storage system and effectively optimizes the balance between power supply and demand.

[0017] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1A flow chart of a power distribution optimization method for a source-grid-load-storage system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0021] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0023] Figure 1 A flow chart of a power distribution optimization method for a source-grid-load-storage system is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes: 101. Acquire real-time operation data of the source-grid-load-storage system, wherein the real-time operation data at least includes power generation, power load, and energy storage status; Optionally, the obtaining of real-time operation data of the source-grid-load-storage system in step 101 includes: collecting status information of each unit in the source-grid-load-storage system through a sensor network; and aggregating and preprocessing the status information to form the real-time operation data.

[0024] In this step, we focus on how to effectively obtain the real-time operation data of the source-grid-load-storage system. This process mainly includes two sub-steps: first, collect the status information of each unit in the system through the sensor network; second, summarize and pre-process the collected status information to form real-time operation data for subsequent analysis and control.

[0025] Sensor network: It consists of a series of sensors deployed in the network to monitor and record the real-time status of each part of the source-grid-load-storage system. These sensors can be temperature sensors, current sensors, voltage sensors, etc., which are used to measure key parameters such as power generation, power load and energy storage status.

[0026] Status information: refers to the raw data collected by sensors, which reflects the actual working conditions of each component in the system.

[0027] Aggregation and preprocessing: refers to the process of integrating, cleaning and formatting the raw data collected from the sensor network in order to generate real-time operating data with unified standards to facilitate further data analysis and processing.

[0028] In the embodiment of the present application, it is assumed that there is a typical source-grid-load-storage system, which includes a wind turbine, a photovoltaic panel, a user load, and a battery energy storage system. Our goal is to obtain the real-time operation data of the system for subsequent prediction and control.

[0029] The status information of each unit in the source-grid-load-storage system is collected through the sensor network: Wind turbine generator set: Current sensors (CS) and voltage sensors (VS) are installed at key locations of each wind turbine generator to monitor the output current and voltage of the generator in real time.

[0030] Photovoltaic panels: Install light intensity sensors (LIS) and temperature sensors (TS) to measure light intensity and panel surface temperature.

[0031] User load: Current sensors (CS) and voltage sensors (VS) are installed at the user's incoming line to monitor the user's power load.

[0032] Battery energy storage system: Current sensors (CS), voltage sensors (VS) and temperature sensors (TS) are installed at the input and output ends of the battery pack to monitor the charge and discharge status and temperature of the battery.

[0033] The state information is aggregated and preprocessed to form the real-time operation data: Data aggregation: All data collected by sensors are sent to the central data processing center via wireless transmission technology (such as Wi-Fi or LoRa). For example, assuming the output current of a wind turbine is 100A and the voltage is 400V, the output power of the generator is The formula can be Calculated, among which Indicates power, Indicates voltage, represents the current. In this example, the power calculated is .

[0034] Data preprocessing: In the central data processing center, the raw data undergoes cleaning (removing outliers and missing values), format conversion (unifying all data into the same unit and format), and preliminary analysis (such as calculating power). The preprocessed data will form a standardized real-time operating data set that contains key information such as power generation, power load, and energy storage status.

[0035] Through the above embodiments, we can see how to collect real-time status information from the sensor network and convert it into real-time operation data that can be used for subsequent analysis and control through aggregation and preprocessing steps. These data will then be used to predict future power generation, power load and energy storage requirements, and adjust the working state of the source-grid-load-storage system accordingly to achieve a balance between power supply and demand.

[0036] 102. Predicting power generation, power load, and energy storage demand in a future time period based on the real-time operation data; Optionally, the prediction of power generation, power load, and energy storage demand in a future time period in step 102 includes: using historical data analysis and machine learning algorithms to predict power generation and power load in future time periods; and determining a charging and discharging plan for the energy storage unit based on the prediction results and the current energy storage status.

[0037] In this step, the power generation, power load and energy storage demand in the future are predicted based on real-time operation data. This process is divided into two parts: first, the power generation and power load are predicted using historical data combined with machine learning algorithms; second, the charging and discharging plan of the energy storage unit is formulated based on the prediction results and the current energy storage status.

[0038] Historical data analysis: Statistical analysis of data collected over a period of time in the past to discover patterns and trends in the data.

[0039] Machine learning algorithm: an artificial intelligence technology that can learn and build models from given historical data to predict the behavior or results of unknown data. Commonly used prediction algorithms include Linear Regression (LR), Support Vector Machine (SVM), Random Forest (RF), etc.

[0040] Energy storage unit charging and discharging plan: Based on the predicted power generation and power load, combined with the current state of the energy storage unit (such as the remaining power percentage), formulate a reasonable charging and discharging strategy to ensure the balance of power supply and demand.

[0041] In the present application example, we will continue to use the previous source-grid-load-storage system as an example. The system includes wind turbines, photovoltaic panels, user loads, and battery energy storage systems. The goal is to predict the power generation and power load in the next 24 hours, and plan the charging and discharging plan of the energy storage unit accordingly.

[0042] Use historical data analysis and machine learning algorithms to predict power generation and load in future periods: Historical data analysis: Collect power generation and power load data for the same time period every day in the past year, including the impact of weather conditions, seasonal changes and other factors.

[0043] Machine Learning Algorithm: Use the Random Forest algorithm to train a prediction model. Random Forest is an ensemble learning method that improves prediction accuracy by building multiple decision trees and combining their prediction results.

[0044] Assume that we have trained a random forest model RF whose input features include: Light Intensity Temperature Wind Speed; Time Slot; The output is the predicted power generation and power load.

[0045] According to the prediction results and the current energy storage status, the charging and discharging plan of the energy storage unit is determined: Current energy storage status: Assume that the remaining power of the current energy storage unit is 30%.

[0046] Forecast results: According to the model prediction, photovoltaic power generation is expected to reach its peak during the day tomorrow, while there will be a large power surplus at night; at the same time, users are expected to have a wave of higher electricity demand at night.

[0047] Based on the above information, we can formulate the following charging and discharging plan: Charging plan: During the period when the power generation is predicted to be greater than the power load, the excess power is stored in the energy storage unit first. For example, it is predicted that the photovoltaic power generation will be higher during the day tomorrow, while the user's power consumption will be lower at this time, so the energy storage unit can be charged during this period.

[0048] Discharge plan: During the period when the power generation is predicted to be lower than the power load, the energy storage unit is released to make up for the shortfall. For example, if the power consumption of users is predicted to be high tomorrow night and the power generation is reduced at this time, the energy storage unit can be discharged during this period. Embodiment 1;

[0049] Assume that the forecast results show that the photovoltaic power generation will reach 200kWh tomorrow, and the user's daytime power load is expected to be 100kWh. Considering that the current remaining power of the energy storage unit is 30%, that is, 30kWh. We can make the following plan: Charging: If the photovoltaic power generation is expected to exceed the user's power load by 100kWh during the day, the excess 100kWh can be used for charging, plus the 30kWh of the current energy storage unit, the total power can reach 130kWh. However, for safety reasons, it is usually not fully charged. Assuming that it is fully charged to 90% of the energy storage unit capacity, the maximum charging capacity is 90kWh. Therefore, a maximum of 60kWh can be charged during the day.

[0050] Discharge: It is expected that the user's electricity consumption will increase to 150kWh at night, while the photovoltaic power generation will drop to 50kWh. This means that an additional 100kWh is needed to meet the electricity demand at night. Therefore, 100kWh can be discharged from the energy storage unit to make up for the shortfall.

[0051] Through the above examples, we can see how to use real-time operation data and historical data analysis combined with machine learning algorithms to predict future power generation and power load, and formulate reasonable energy storage unit charging and discharging plans based on these prediction results. This dynamic management strategy helps to maximize the use of renewable energy while ensuring the balance of power supply and demand.

[0052] 103. Based on the prediction results, adjust the working states of the power generation unit, the power consumption unit and the energy storage unit of the source-grid-load-storage system to achieve a balance between power supply and demand; wherein, adjusting the working state at least includes changing the output power of the power generation unit, adjusting the power consumption of the power consumption unit and controlling the charging and discharging behavior of the energy storage unit.

[0053] Optionally, the step 103 of adjusting the working states of the power generation unit, the power consumption unit and the energy storage unit of the source-grid-load-storage system based on the prediction result includes: establishing a multi-objective optimization model; solving the multi-objective optimization model using a mixed integer linear programming method to obtain the optimal working state of each unit; The multi-objective optimization model includes at least three objective functions: cost minimization, carbon emission minimization, and power supply and demand balance maximization. The calculation formulas corresponding to the three objective functions are defined as follows:

[0054] in, represents the minimum total operating cost, Indicates The cost factor of each unit, Indicates The power of each unit, Indicates The fixed cost of a unit, is the total number of units in the system, represents the minimum emission, Indicates The emission factor for each unit, Indicates the maximum power supply. Indicates the maximum power demand, The balance between electricity supply and demand is maximized. Indicates The power supply of each power supply unit, Indicates The power consumption of each power unit.

[0055] In this step, we adjust the working status of the power generation unit, power consumption unit and energy storage unit of the source-grid-load-storage system based on the prediction results to achieve a balance between power supply and demand. This process involves establishing a multi-objective optimization model and solving the model using a mixed integer linear programming method to ultimately obtain the optimal working status of each unit. Specifically, the objective functions of the model include minimizing costs, minimizing carbon emissions, and maximizing the balance between power supply and demand.

[0056] Multi-objective optimization model: A mathematical model that aims to optimize multiple conflicting objective functions simultaneously. In this case, the objective functions include minimizing costs, minimizing carbon emissions, and maximizing the balance between electricity supply and demand.

[0057] Mixed Integer Linear Programming: A method for solving multi-objective optimization problems that can handle linear constraints and objective functions where some variables must take integer values. This method is suitable for solving optimization problems with discrete decision variables.

[0058] Objective function: Cost minimization: The goal is to minimize the total operating cost, including variable and fixed costs of each unit.

[0059] Carbon emissions minimization: The goal is to minimize the overall carbon emissions.

[0060] Maximizing the balance between electricity supply and demand: The goal is to make the power supply as close as possible to the power demand in order to achieve a balance between electricity supply and demand.

[0061] In the embodiment of this application, we continue to use the source-grid-load-storage system mentioned above as an example. The system includes a wind turbine, a photovoltaic panel, a user load, and a battery energy storage system. Our goal is to adjust the working state of each unit of the system based on the predicted power generation, power load, and energy storage demand to achieve a balance between power supply and demand.

[0062] Build a multi-objective optimization model: We establish a multi-objective optimization model, and the objective function of the model is as follows: Cost minimization:

[0063] in, Indicates The cost factor of each unit, Indicates The power of each unit, Indicates Fixed cost per unit.

[0064] Minimizing Carbon Emissions:

[0065] in, Indicates The emission factor of each unit.

[0066] Maximizing the balance between electricity supply and demand:

[0067] in, Indicates The power supply of each power supply unit, Indicates The power consumption of each power unit.

[0068] The multi-objective optimization model is solved using a mixed integer linear programming method: To solve this multi-objective optimization problem, we employ a mixed-integer linear programming approach that can handle both discrete decision variables (e.g., whether to turn on a unit) and continuous variables (e.g., power level).

[0069] Get the best working state of each unit: By solving the above optimization model, we can obtain the optimal output power of the power generation unit, the optimal power consumption of the power consumption unit, and the optimal charging and discharging behavior of the energy storage unit.

[0070] Embodiment 2; Assume we have the following information: There are 5 units in the system: 2 wind turbines (cost factor , fixed costs Yuan / day, emission coefficient ); 2 photovoltaic panels (cost factor , fixed costs Yuan / day, emission coefficient ); 1 battery storage unit (cost factor , fixed costs Yuan / day, emission coefficient ).

[0071] The user's electricity load is predicted to be 100kWh during the day and 150kWh at night.

[0072] The predicted power generation is 200kWh during the day and 50kWh at night.

[0073] Next, we build the optimization model: Cost minimization:

[0074] in, , , , , Represents the power of each unit respectively.

[0075] Minimizing Carbon Emissions:

[0076] Since all units are powered by clean energy, the carbon emissions here are zero.

[0077] Maximizing the balance between electricity supply and demand:

[0078] in, and It is the electricity load during the day and night.

[0079] Solution process: Set up constraints: Upper power limit of the generator set: , , ,

[0080] Power range of energy storage unit:

[0081] The power supply is equal to the predicted power generation:

[0082] Electricity consumption is equal to the predicted electricity load:

[0083] Solve the optimization model: Use the mixed integer linear programming method to solve the above model to find the best working state that satisfies all constraints.

[0084] Solution result: Assume that the best working state after solving is as follows: daytime: Wind turbines:

[0085] Photovoltaic panels:

[0086] Battery energy storage unit: (Not working because the power generation is greater than the power load) night: Wind turbines:

[0087] Photovoltaic panels:

[0088] Battery energy storage unit: (Discharge to supplement insufficient power generation) Through the above examples, we can see how to adjust the working status of power generation units, power consumption units and energy storage units based on the prediction results and multi-objective optimization model to achieve a balance between power supply and demand. This optimization strategy helps to reduce operating costs, reduce carbon emissions, and ensure the stable operation of the power system.

[0089] Optionally, the method further includes: after adjusting the working state, monitoring the actual operating effect of the source-grid-load-storage system, and feeding back to the control system for iterative optimization.

[0090] In this step, we discuss an important link in the smart grid - optimizing the actual operation effect of the source-grid-load-storage system (SGLS) through monitoring and feedback mechanisms.

[0091] In the embodiment of this application, it is assumed that we are managing a SGLS system that includes renewable energy generation, traditional power grids, industrial users, and battery energy storage systems. Our goal is to maximize system efficiency while ensuring stable power supply.

[0092] Monitoring phase: Use sensors and smart metering devices to collect data on: The amount of electricity generated by the wind farm per hour (e.g. 150 kWh between 10am and 11am).

[0093] The total output of the solar PV panels during a specific time period (e.g. 200kWh was generated between 2pm and 3pm).

[0094] Real-time electricity demand of industrial users (e.g., electricity consumption is 300kWh at 3pm).

[0095] The current charging and discharging status of the energy storage system (for example, the remaining capacity of the battery pack is 500kWh).

[0096] Analysis phase: Data analysis algorithms are used to evaluate this data, for example, to calculate the gap between supply and demand to determine whether energy storage systems need to be activated or the generation schedule needs to be adjusted.

[0097] If it is found that supply exceeds demand, then the excess energy can be stored; conversely, if demand exceeds supply, the shortage can be supplemented by dispatching the energy storage system.

[0098] Feedback and optimization phase: The results of the analysis are fed back to the central control system. For example, if it finds that demand surges in the evening when solar power generation drops, the system can automatically dispatch the energy storage system to balance supply and demand.

[0099] The control system adjusts parameters such as the storage system's charging and discharging strategies to optimize overall performance. For example, if sufficient solar power is predicted for the next morning, the system can charge at night so that it can be released in the morning.

[0100] Specific calculation in the embodiment: Assume that during a certain period of time in a day (assuming it is 15:00-16:00), the system predicts a demand of 350kWh, and the predicted output of renewable energy during this period is 200kWh. The current remaining power of the energy storage system is 400kWh, and the maximum discharge capacity is 200kWh / h.

[0101] Calculate the difference between supply and demand: 350kWh-200kWh=150kWh; Determine the energy storage system discharge capacity: To meet the additional demand, the energy storage system needs to discharge 150kWh of electricity.

[0102] Update energy storage system status: Remaining power = 400kWh - 150kWh = 250kWh In this way, we can ensure that the system can operate efficiently and stably under different conditions.

[0103] Optionally, the method further includes: dynamically adjusting the output power of the power generation unit according to weather forecast information and seasonal changes; and intelligently scheduling the usage time of the power consumption unit according to the user's power consumption habits and demand forecasts.

[0104] In this step, we focus on how to dynamically adjust the output power of power generation units based on weather forecast information and seasonal changes, and how to intelligently schedule the usage time of power units based on user electricity usage habits and demand predictions. These strategies help improve energy efficiency, reduce energy waste, and enhance user experience.

[0105] Weather forecast information: refers to data on future weather conditions obtained from meteorological service providers, including temperature, humidity, wind speed, light intensity, etc.

[0106] Seasonal variation: refers to the impact of different seasons of the year on energy production and consumption. For example, high temperatures in summer may increase the frequency of air conditioning use, while low temperatures in winter may increase heating demand.

[0107] Output power of power generation unit: refers to the actual power generation capacity of power generation units such as wind turbines, photovoltaic panels, etc. Adjusting their output power according to weather forecasts and seasonal changes can better match actual demand.

[0108] User electricity usage habits: refers to the user's electricity usage patterns and preferences during a specific time period, such as higher electricity consumption during peak hours in the morning and evening.

[0109] Demand forecasting: refers to predicting future electricity demand based on historical data and current information to guide the scheduling of electricity-consuming units.

[0110] In the embodiment of this application, we continue to use the previous source-grid-load-storage system as an example. The system includes a wind turbine, a photovoltaic panel, a user load, and a battery energy storage system. Our goal is to dynamically adjust the output power of the power generation unit according to weather forecast information and seasonal changes, and intelligently schedule the usage time of the power unit according to the user's electricity usage habits and demand predictions.

[0111] Dynamically adjust the output power of the power generation unit according to weather forecast information and seasonal changes: Weather forecast information: Assume that you have obtained weather forecast data for the next week from a meteorological service provider, including daily temperature, humidity, wind speed, and light intensity.

[0112] Seasonal changes: Assuming it is currently summer, higher temperatures are expected during the day and lower temperatures at night.

[0113] Adjust the output power of the power generation unit: Wind turbines: Adjust the output power of wind turbines based on the predicted wind speed. For example, if higher wind speeds are predicted tomorrow during the day, the output power of wind turbines can be increased.

[0114] Photovoltaic panels: The power generation of photovoltaic panels is adjusted according to the predicted light intensity. For example, if the light intensity is predicted to be strong during the day tomorrow, the photovoltaic panels can be fully utilized to generate electricity.

[0115] Intelligently schedule the usage time of power units based on the user's power usage habits and demand forecasts: Electricity usage habits: Assume that users consume more electricity between 7:00-9:00 in the morning and 6:00-8:00 in the evening every day.

[0116] Demand forecasting: Predict electricity demand in the future based on historical data, for example, predicting that electricity demand will be higher from 7:00 to 9:00 tomorrow morning.

[0117] Smart scheduling: Adjust the usage time of power units in advance based on demand forecast results. For example, high-power appliances such as air conditioners or water heaters can be turned on in advance to avoid peak hours. Specific embodiments

[0118] Assume we have the following information: The weather forecast shows that tomorrow's daytime temperature will be high, the wind speed will be moderate, and the light intensity will be strong.

[0119] Seasonal variation: Currently in summer, daytime temperatures are expected to be around 30°C and nighttime temperatures around 20°C.

[0120] User electricity usage habits: 7:00-9:00 in the morning and 6:00-8:00 in the evening are peak electricity usage periods.

[0121] Demand forecast: It is predicted that the electricity demand will be high from 7:00 to 9:00 tomorrow morning, and the electricity demand will also be very high from 6:00 to 8:00 in the evening.

[0122] Dynamically adjust the output power of the power generation unit according to weather forecast information and seasonal changes: Wind turbine: Assuming the wind speed is predicted to be 5m / s tomorrow, the output power of the wind turbine can be adjusted to 90% of the maximum capacity.

[0123] Photovoltaic panels: Assuming the predicted daytime sunlight intensity tomorrow is 800W / m², the power generation of the photovoltaic panels can be adjusted to 95% of the maximum capacity.

[0124] Intelligently schedule the usage time of power units based on the user's power usage habits and demand forecasts: Electricity unit: Assume that the user has an air conditioner and a water heater at home.

[0125] Intelligent Scheduling: Air conditioning: Considering that 7:00-9:00 in the morning and 6:00-8:00 in the evening are peak electricity consumption periods, the air conditioning can be turned on in advance for pre-cooling, for example, starting the air conditioning at 6:30 in the morning and 5:30 in the evening.

[0126] Water heater: Again, considering the peak electricity usage, you can turn on the water heater at 6:30 in the morning and 5:30 in the evening to avoid peak hours.

[0127] Specific adjustments: Wind turbines: According to the predicted wind speed of 5m / s, assuming the maximum output power of the wind turbine is 100kW, adjust its output power to 90kW.

[0128] Photovoltaic panels: Based on the predicted light intensity of 800W / m², assuming the maximum power generation of the photovoltaic panel is 50kW, adjust its power generation to 47.5kW.

[0129] Intelligent dispatching of power consumption units: Air conditioner: Assume that the rated power of the air conditioner is 2kW.

[0130] Morning: Turn on the air conditioner at 6:30 and keep it on for 1.5 hours until 8:00.

[0131] Evening: Turn on the air conditioner at 5:30 and keep it on for 1.5 hours until 7:00.

[0132] Water heater: Assume the rated power of the water heater is 3kW.

[0133] Morning: Turn on the water heater at 6:30 and keep it running for 1.5 hours until 8:00.

[0134] Evening: Turn on the water heater at 5:30 and keep it running for 1.5 hours until 7:00.

[0135] Through the above examples, we can see how to dynamically adjust the output power of the power generation unit according to weather forecast information and seasonal changes, and how to intelligently schedule the usage time of the power unit according to the user's electricity usage habits and demand prediction. This intelligent scheduling strategy helps to improve energy utilization efficiency, reduce energy waste, and enhance user experience.

[0136] Optionally, the method further comprises: applying a multi-objective optimization algorithm to determine a comprehensive optimization strategy for the power generation unit, the power consumption unit and the energy storage unit; The formula is defined as follows:

[0137] in, represents the objective function value corresponding to the comprehensive optimization strategy, , , are the weight coefficients of cost, emission and power supply-demand gap, , , are the weight coefficients of cost, emission and electricity supply-demand gap respectively.

[0138] Indicates the minimum power demand.

[0139] Indicates the maximum power limit of the system.

[0140] Indicates the maximum allowable emission.

[0141] Constraints: Make sure the total power supply at least meets the minimum power requirements.

[0142] : Ensure that the total power of all power generation units does not exceed the maximum power limit of the system.

[0143] : Ensure that total emissions do not exceed the maximum allowable emissions.

[0144] In this embodiment of the application, it is assumed that we manage a microgrid that includes solar photovoltaic panels, wind turbines, industrial users, residential users, and battery energy storage systems. Our goal is to minimize costs and emissions while ensuring a balance between power supply and demand.

[0145] Parameter settings: , the weight coefficient of cost.

[0146] , the weight coefficient of emissions.

[0147] , the weight coefficient of the power supply and demand difference.

[0148] , minimum electricity demand.

[0149] , system maximum power limit.

[0150] , Maximum permissible discharge.

[0151] Specific calculation in the embodiment: Power generation unit: The solar PV panels are expected to generate 150kW.

[0152] The wind turbine is expected to generate 200kW.

[0153] Power unit: Industrial users are expected to consume 250kW of electricity.

[0154] Residential users are expected to consume 100kW of electricity.

[0155] Energy storage unit: The battery energy storage system can store up to 100kW.

[0156] The current remaining capacity of the energy storage system is 50kW.

[0157] Calculation process: Total power supply .

[0158] Total power consumption .

[0159] Assumed Cost Yuan.

[0160] Assumed emissions .

[0161] Electricity supply and demand gap .

[0162] Objective function value calculation: Constraint verification: (Not satisfied, but a simplified model is used here. In actual situations, supply and demand need to be adjusted to meet the constraints).

[0163]

[0164] Through such calculations and analysis, we can find the optimal power generation, power consumption and energy storage strategies to meet the established goals.

[0165] Optionally, the method further comprises: Adjust the charging and discharging strategy of the energy storage unit to minimize the peak power of the grid; Among them, the calculation formula corresponding to minimizing the peak power of the power grid is defined as follows:

[0166] in, represents the peak power of the power grid, Indicates A power supply unit at time The power supply Indicates The power consumption unit at time of electricity consumption, Indicates that the energy storage unit is at time The charge and discharge capacity changes, Indicates the maximum charge and discharge power of the energy storage unit.

[0167] In this step, we discuss how to minimize the peak power of the grid by adjusting the charging and discharging strategies of energy storage units. This process is crucial to improving the stability and efficiency of the grid.

[0168] Key concepts explained: Energy storage unit: A device that can store and release electrical energy, such as a battery storage system.

[0169] Grid peak power: the maximum power demand reached by the grid in a certain period of time.

[0170] Change in charge and discharge capacity: The change in the charge and discharge capacity of the energy storage unit at a certain moment relative to the previous moment.

[0171] Maximum charge and discharge power: the maximum charge and discharge power that the energy storage unit can provide.

[0172] Formula definition and explanation:

[0173] Indicates the peak power of the power grid.

[0174] Indicates A power supply unit at time of power supply.

[0175] Indicates The power consumption unit at time of electricity consumption.

[0176] Indicates that the energy storage unit is at time The charge and discharge capacity changes.

[0177] Indicates the maximum charge and discharge power of the energy storage unit.

[0178] Constraints:

[0179] This means that the change in charge and discharge capacity of the energy storage unit at any time cannot exceed its maximum charge and discharge power.

[0180] In the present application embodiment: Suppose we manage a microgrid that includes solar photovoltaic panels, wind turbines, industrial users, residential users, and battery energy storage systems. Our goal is to minimize the peak power of the grid by adjusting the charging and discharging strategies of the energy storage units.

[0181] Parameter settings: Assume that the maximum charge and discharge power of the energy storage unit is .

[0182] The solar PV panels are expected to generate 150kW per hour.

[0183] The wind turbine is expected to generate 200kW per hour.

[0184] Industrial users are expected to consume 250kW of electricity per hour.

[0185] Residential users are expected to use 100kW of electricity per hour.

[0186] Assume that the current remaining power of the energy storage unit is 50kW.

[0187] Specific calculation in the embodiment: We consider four key moments of the day to show how grid peak power can be minimized by adjusting the charging and discharging strategies of energy storage units.

[0188] Time 1 (10:00 AM): Total power supply .

[0189] Total electricity consumption .

[0190] Considering the supply and demand balance at this time, the energy storage unit does not need to be charged or discharged, that is, .

[0191] Grid peak power .

[0192] Time 3 (16:00): Total power supply .

[0193] Total electricity consumption .

[0194] At this time, the electricity demand increases, and the energy storage unit needs to discharge to reduce the peak power of the grid. Assuming the discharge is 50kW, that is .

[0195] Grid peak power (Considering that negative numbers represent excess supply, positive values ​​are taken).

[0196] Time 4 (20:00 pm): Total power supply (Assuming reduced solar power generation).

[0197] Total electricity consumption .

[0198] As the electricity demand increases further, the energy storage unit continues to discharge to reduce the peak power of the grid. Assuming that the discharge is 50kW, that is .

[0199] Grid peak power

[0200] Result analysis: Through the above adjustments, we can keep the peak power of the grid at 0kW even during peak power consumption periods. This is because the energy storage unit performs charging and discharging operations in a timely manner, thus avoiding the occurrence of peak power in the grid.

[0201] Constraint verification: In the above embodiment, the charge and discharge capacity of the energy storage unit is always within the range of the maximum charge and discharge power, that is, .

[0202] Through such calculations and analysis, we can effectively manage the charging and discharging strategies of energy storage units to achieve the goal of minimizing the peak power of the power grid.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A power distribution optimization method for a source-grid-load-storage system, characterized in that: include: Acquire real-time operation data of the source-grid-load-storage system, wherein the real-time operation data at least includes power generation, power load, and energy storage status; Predicting power generation, power load, and energy storage demand in a future time period based on the real-time operation data; Based on the prediction results, the working states of the power generation unit, the power consumption unit and the energy storage unit of the source-grid-load-storage system are adjusted to achieve a balance between power supply and demand; wherein the adjustment of the working state at least includes changing the output power of the power generation unit, adjusting the power consumption of the power consumption unit and controlling the charging and discharging behavior of the energy storage unit; The adjusting the working states of the power generation unit, the power consumption unit and the energy storage unit of the source-grid-load-storage system also includes: Applying a multi-objective optimization algorithm to determine a comprehensive optimization strategy for the power generation unit, the power consumption unit, and the energy storage unit; The formula is defined as follows: ； in, represents the objective function value corresponding to the comprehensive optimization strategy, , , are the weight coefficients of cost, emission and power supply-demand gap, Indicates the minimum power demand, Indicates the maximum power limit of the system. Indicates the maximum allowable emission.

2. The method according to claim 1, characterized in that The obtaining of real-time operation data of the source-grid-load-storage system comprises: Collecting status information of each unit in the source-grid-load-storage system through a sensor network; The state information is aggregated and pre-processed to form the real-time operation data.

3. The method according to claim 2, characterized in that The predicted power generation, power load, and energy storage demand in the future time period include: Use historical data analysis and machine learning algorithms to predict future power generation and load; According to the prediction result and the current energy storage state, a charging and discharging plan of the energy storage unit is determined.

4. The method according to claim 3, characterized in that The step of adjusting the working states of the power generation unit, the power consumption unit and the energy storage unit of the source-grid-load-storage system based on the prediction result includes: Establish a multi-objective optimization model; Solving the multi-objective optimization model using a mixed integer linear programming method to obtain the optimal working state of each unit; The multi-objective optimization model includes at least three objective functions: cost minimization, carbon emission minimization, and power supply and demand balance maximization. The calculation formulas corresponding to the three objective functions are defined as follows: ； in, represents the minimum total operating cost, Indicates The cost factor of a unit, Indicates The power of each unit, Indicates The fixed cost of a unit, is the total number of units in the system, represents the minimum emission, Indicates The emission factor for each unit, Indicates the maximum power supply. Indicates the maximum power demand, The balance between electricity supply and demand is maximized. Indicates The power supply of each power supply unit, Indicates The power consumption of each power unit.

5. The method according to claim 1, characterized in that Also includes: After adjusting the working state, the actual operating effect of the source-grid-load-storage system is monitored and fed back to the control system for iterative optimization.

6. The method according to claim 1, characterized in that The adjusting the working states of the power generation unit, the power consumption unit and the energy storage unit of the source-grid-load-storage system also includes: Dynamically adjust the output power of the power generation unit according to weather forecast information and seasonal changes; Intelligently schedule the usage time of power units based on users' power usage habits and demand forecasts.

7. The method according to claim 1, characterized in that The adjusting the working states of the power generation unit, the power consumption unit and the energy storage unit of the source-grid-load-storage system also includes: Adjust the charging and discharging strategy of the energy storage unit to minimize the peak power of the grid; Among them, the calculation formula corresponding to minimizing the peak power of the power grid is defined as follows: ； in, represents the peak power of the power grid, Indicates A power supply unit at time The power supply Indicates The power consumption unit at time The power consumption, Indicates that the energy storage unit is at time The charge and discharge capacity changes, Indicates the maximum charge and discharge power of the energy storage unit.

Images