A household energy storage scheduling optimization method and system

Abstract

The application provides a household energy storage scheduling optimization method and system, which comprises the following steps: obtaining daily electricity price information, daily weather information, user household historical power consumption data and energy storage device state respectively; predicting daily photovoltaic power generation power through a photovoltaic power prediction model based on the daily weather information; predicting daily household power consumption power through a household load prediction model based on the user household historical power consumption data; constructing a target optimization function based on the daily photovoltaic power generation power, the household power consumption power, the electricity price information and the energy storage device state information, and calculating the optimal charging power and the optimal discharging power of the energy storage battery in each time period of the day through a solver; comparing the actually detected battery charging and discharging power with the planned optimal charging and discharging power, and re-optimizing the charging and discharging power of the remaining time period of the day when the power error exceeds a threshold value. Through the scheme, the adaptability and reliability of photovoltaic energy storage scheduling can be improved.

Description

Technical Field

[0001] This invention belongs to the field of energy dispatching technology, and in particular relates to a method and system for optimizing household energy storage dispatching. Background Technology

[0002] With the rapid popularization of distributed photovoltaic (PV) and residential energy storage systems in residential settings, user-side energy management has become a key factor affecting energy costs and efficiency. Residential energy storage devices achieve peak shaving and valley filling, boosting PV self-consumption, and arbitrage through battery charging and discharging. However, due to the randomness of residential electricity load, the uncertainty of PV power generation, and the dynamic changes in time-of-use pricing, achieving more refined, low-cost, and high-yield energy dispatch in residential scenarios has become a pressing issue for the industry.

[0003] Currently, there are two main approaches to residential energy storage technology: one is a self-consumption control strategy, where photovoltaic (PV) power generated is stored in storage devices when the load exceeds capacity, and released to meet the demand when the load is low; the other is to predict PV power generation and load conditions based on historical power generation and discharge data, and then plan the charging and discharging power accordingly. While both approaches can improve the utilization value of PV power generation to some extent, their reliability in dispatching PV power generation is relatively low because they do not consider the impact of weather changes and the actual condition of the storage devices. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and system for optimizing home energy storage scheduling, which is used to solve the problem of low reliability of current photovoltaic power generation scheduling.

[0005] In a first aspect of the present invention, a method for optimizing home energy storage scheduling is provided, comprising: The system acquires daily electricity price information, daily weather information, historical electricity consumption data of users' households, and the status of energy storage devices. Based on the weather information of the day, the photovoltaic power generation power of the day is predicted by a photovoltaic power prediction model, which is trained based on historical photovoltaic power generation data and historical weather information. Based on users’ historical household electricity consumption data, the household load prediction model is used to predict the household’s daily electricity consumption. Based on the daily photovoltaic power generation, daily household electricity consumption, daily electricity price information, and energy storage device status information, an objective optimization function is constructed, and the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day are calculated by a solver. The actual measured battery charging power and discharging power are compared with the planned optimal charging power and optimal discharging power. If the difference between the charging power and the discharging power exceeds the preset threshold, the charging and discharging power for the remaining time period of the day will be dynamically optimized again.

[0006] In a second aspect of the present invention, a home energy storage scheduling optimization system is provided, comprising: The data acquisition module is used to acquire the daily electricity price information, the daily weather information, the user's historical electricity consumption data, and the status of energy storage devices, respectively. The first prediction module is used to predict the photovoltaic power generation power of the day based on the weather information of the day through a photovoltaic power prediction model. The photovoltaic power prediction model is trained based on historical photovoltaic power generation data and historical weather information. The second prediction module is used to predict the daily household electricity consumption based on the user's historical household electricity consumption data and through a household load prediction model. The optimal scheduling solution module is used to construct an objective optimization function based on the daily photovoltaic power generation, daily household electricity consumption, daily electricity price information, and energy storage device status information, and to calculate the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day through the solver; The scheduling optimization module compares the actual detected battery charging power and discharging power with the planned optimal charging power and optimal discharging power respectively. When the difference between the charging power and the discharging power exceeds the preset threshold, the charging and discharging power for the remaining time period of the day is dynamically optimized again.

[0007] In a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect of the present invention.

[0008] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present invention.

[0009] In this embodiment of the invention, the photovoltaic power generation power of the day is predicted by a photovoltaic power prediction model, and the household electricity consumption power of the day is predicted by a household load prediction model. Then, an objective optimization function is constructed to solve for the optimal charging power and the optimal discharging power. If there is an error in the actual charging and discharging power, the charging and discharging power for the remaining period is re-optimized. This not only improves the reliability of photovoltaic power generation scheduling, but also enhances the adaptability and accuracy of energy storage scheduling. At the same time, it maximizes the utilization value of photovoltaic power generation and maximizes user benefits. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating a method for optimizing home energy storage scheduling according to an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the principle of a home energy storage scheduling optimization method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a home energy storage scheduling optimization system provided in one embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0012] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0013] It should be understood that the terms "comprising" and other similar expressions in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units and is not limited to the listed steps or units. Furthermore, "first" and "second" are used to distinguish different objects and are not intended to describe a specific order.

[0014] Please see Figure 1 A flowchart illustrating a method for optimizing home energy storage scheduling provided in this embodiment of the invention includes: S101. Obtain the daily electricity price information, daily weather information, historical electricity consumption data of user households, and status of energy storage devices respectively; Daily electricity price information can include the purchase price and the selling price of electricity. It generally needs to be obtained one day in advance. It can be obtained from the power grid company through an online API, which will show the current electricity price for the equipment connected to the grid and the electricity price for the next whole day.

[0015] The weather information for the day can include weather type, such as sunny, cloudy, rainy, or partly cloudy, as well as solar irradiance range, cloud cover, precipitation probability, temperature range, humidity, etc. Weather information can be obtained from local site weather data through meteorological bureau interfaces or commercial weather APIs.

[0016] Historical electricity consumption data for a user's household can include power consumption, electricity usage behavior, load characteristics, etc., which can be obtained through power metering devices. The data can also be linked to current holidays, that is, relevant tags can be attached to the data.

[0017] The status of energy storage devices, also known as the status of home energy storage batteries, can include SOC (State of Charge), available battery capacity, and maximum charging and discharging power.

[0018] Among these methods, historical photovoltaic power generation data can also be obtained to train photovoltaic power prediction models. Historical photovoltaic power generation data can be obtained in two ways: one is by connecting to the photovoltaic power generation equipment through communication to directly obtain and store the power generation data of the photovoltaic equipment for the whole day; the other is by statistically analyzing the self-generated power data of the energy storage equipment and the sampling data of the grid port to calculate the corresponding photovoltaic power generation power / trend.

[0019] S102. Based on the weather information of the day, predict the photovoltaic power generation power of the day through a photovoltaic power prediction model. The photovoltaic power prediction model is trained based on historical photovoltaic power generation data and historical weather information. The weather information for the day can include the weather type and weather parameters, such as the weather type being cloudy, and the parameters being sunlight intensity, temperature range, cloud cover, etc. The weather parameters generally include weather factors closely related to photovoltaic power generation.

[0020] The photovoltaic power prediction model is a deep learning model used for time series forecasting, and can be models such as LSTM (Long Short-Term Memory Network) or TCN (Temporal Convolutional Network). The input of the photovoltaic power prediction model is the weather information of the day, and the output is the photovoltaic power generation of the day. Based on the output, a time-related curve of photovoltaic power generation can be generated.

[0021] S103. Based on the user's historical household electricity consumption data, predict the household electricity consumption for the day using a household load prediction model; Historical household electricity consumption data includes data such as historical household power consumption, electricity consumption behavior, and load status. Based on historical household electricity consumption data, household power consumption for the current day or the next day can be predicted in real time.

[0022] The household load prediction model is a deep learning model based on time series prediction. It can be composed of multiple models, each used to determine different electricity consumption types and predict the corresponding power consumption. For example, a classification model can be used to determine the user's electricity consumption type, while recurrent neural network models and Markov models can be combined to predict the power consumption of the corresponding types. The input of the household load prediction model is the user's historical household electricity consumption data over a period of time, and the output is the household power consumption for the current day. Based on the output, a time-related curve of household power consumption can be generated.

[0023] S104. Based on the photovoltaic power generation, household electricity consumption, electricity price information and energy storage device status information of the day, construct the objective optimization function, and calculate the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day through the solver. Based on the daily photovoltaic power generation, daily household electricity consumption, daily electricity price information, and energy storage device status information, a time-related objective optimization function is constructed to calculate the optimal charging power and optimal discharging power for different time periods of the 24 hours of the day.

[0024] The objective optimization function can be expressed as the sum of the difference between the predicted household electricity consumption and the predicted photovoltaic power generation in each time period, and the difference between the optimal charging power and the optimal discharging power of the energy storage battery, while minimizing the electricity price.

[0025] Optionally, the objective optimization function can be the minimization of daily electricity cost or the maximization of electricity revenue, and at least power constraints, SOC constraints, battery capacity constraints and energy conservation constraints can be set. Based on the objective optimization function and constraints, the solver is invoked to calculate the optimal charging power and discharging power for each time period of the day, and to generate the corresponding optimal scheduling instruction set.

[0026] In some embodiments, the objective optimization function is expressed as: ; The constraints are expressed as follows: ; in, L(t) Predict electricity consumption for users (excluding sudden loads). PV(t) For residential solar PV forecast input, These represent the charging and discharging power of the energy storage battery, respectively. Indicates electricity price, Indicates charging efficiency. This indicates the discharge efficiency.

[0027] After constructing the objective function and setting the corresponding constraints, a solver can be invoked to perform the solution. The solver can be a linear programming solver, a mixed-integer programming solver, or a heuristic approximate optimization algorithm, such as a genetic algorithm or particle swarm optimization. The solver automatically calculates the optimal charging and discharging power for each time period based on the objective function and constraints, forming a 24-hour optimal scheduling instruction set. This instruction set will guide the energy storage battery to perform reasonable energy scheduling under different electricity price periods and different load demands, achieving the lowest overall cost or maximum benefit.

[0028] S105. Compare the actual detected battery charging power and discharging power with the planned optimal charging power and optimal discharging power respectively. If the difference between the charging power and the discharging power exceeds the preset threshold, the charging and discharging power for the remaining time period of the day will be dynamically optimized again.

[0029] The actual charging and discharging power of the energy storage battery is detected in real time and compared with the planned optimal charging and discharging power. The total power flow of the household can be collected in real time through the power metering module at the inlet port and compared with the optimal charging and discharging schedule. When a significant difference is detected between the actual power and the planned power (such as sudden load start-up or sudden weather changes causing large changes in photovoltaic power), dynamic planning is triggered to re-optimize the charging and discharging power of the battery for the remaining time period, so as to maintain the original optimization target as much as possible.

[0030] This embodiment ensures that the energy storage battery operates stably in a dynamic environment and maintains the effectiveness and reliability of the scheduling target by means of real-time detection and automatic replanning.

[0031] In this embodiment, based on multidimensional data, accurate prediction of photovoltaic power generation and household electricity consumption can be achieved through time series prediction models, thereby improving the accuracy of scheduling strategies; optimal charging and discharging strategies can be formulated in advance based on electricity price information to maximize user benefits; dynamic scheduling optimization is achieved instead of relying on fixed scheduling rules, resulting in better adaptability; photovoltaic power generation can be effectively utilized, improving self-consumption rate and avoiding curtailment caused by unreasonable battery SOC, maximizing the utilization value of photovoltaic power generation, and comprehensively considering battery status to avoid frequent ineffective cycles. The scheduling strategy can incorporate a battery life model to make benefits and lifespan more balanced.

[0032] In one embodiment, the principle of the home energy storage scheduling optimization method is as follows: Figure 2As shown in the diagram, the photovoltaic power generation module mainly includes photovoltaic panels to provide electrical energy. The energy storage control module mainly includes energy storage batteries and a control system to control the charging and discharging of the energy storage batteries. The power metering module is used to count the actual electricity consumption of the household load, and the load module is used to represent the household electrical load. The arrows in the diagram indicate the direction of energy flow. Based on the actual electricity consumption counted by the power metering module, the charging and discharging power of the energy storage batteries in the energy storage control module can be dynamically adjusted.

[0033] The energy storage control module can control the energy storage battery to perform charging and discharging. Based on information such as the daily photovoltaic power generation forecast and the daily household power consumption forecast, it solves for the optimal charging power and optimal discharging power of the energy storage battery. Furthermore, based on the charging power error, it dynamically optimizes the charging and discharging power for the remaining time period.

[0034] In one embodiment, step S102 further includes: The actual output power of the photovoltaic system and the predicted photovoltaic power generation are obtained at a predetermined time granularity. When the difference between the actual output power and the predicted photovoltaic power generation exceeds a preset threshold, dynamic error correction is triggered.

[0035] In actual operation, the instantaneous power generation of photovoltaic arrays is often affected by factors such as sudden weather changes, shading, or hot spots on the modules, which may cause deviations between real-time power generation and predicted power generation. To ensure the accuracy of energy planning and scheduling in actual operation, this embodiment introduces a real-time photovoltaic power correction mechanism. The current photovoltaic input power is continuously acquired at a preset prediction time granularity (e.g., 5 minutes or 10 minutes) and compared with the predicted power. When the deviation exceeds a threshold (e.g., exceeding ±10% of the predicted value or exceeding a set absolute power difference), the system determines that a prediction error has occurred and dynamic correction is required.

[0036] Optionally, the step of triggering dynamic error correction when the difference between the actual photovoltaic output power and the predicted photovoltaic power generation exceeds a preset value includes: Obtain current weather information, determine whether the change value of weather parameters exceeds the threshold within a set unit time, and if the change value of weather parameters exceeds the threshold, trigger a reassessment of weather factors and scale or correct the photovoltaic power generation forecast curve for the day. The correction process requires initial deviation identification and cause inference. Based on current weather monitoring information, such as light sensor readings, rapid changes in cloud cover, and changes in rainfall patterns, it can be determined whether the decrease or increase in power is caused by sudden weather factors. If the weather changes rapidly, a weather factor reassessment mechanism is triggered, which reassesses the current weather factors to determine if they match the input weather information and scales or corrects the overall forecast curve.

[0037] Optionally, the actual output power of the photovoltaic system during the current preset time period is obtained, and a correction curve for a future period is generated based on the trend of the actual output power of the photovoltaic system and the original slope of the photovoltaic power generation prediction curve. The correction curve is then used as the photovoltaic power generation prediction curve.

[0038] Scaling or correcting the overall forecast curve can perform short-cycle compensation of the forecast curve. By using the actual output change trend of photovoltaic power generation over the past few minutes and combining it with the original slope of the forecast curve, a short-term corrected forecast curve for a small period of time in the future can be regenerated (this time period can be set according to whether the weather factors have returned to normal or it can be set to a fixed length). This curve replaces the original photovoltaic power generation forecast curve.

[0039] In this embodiment, by employing short-term forecast compensation, the adaptability and accuracy of the scheduling plan can be maintained when the weather changes suddenly, avoiding problems such as over-discharge of energy storage equipment and failure to charge in time caused by forecast deviations.

[0040] In one embodiment, step S103 includes: Feature extraction is performed on historical electricity consumption data of users' households, and cluster statistics are performed on the changing trends, duration and peak periods of historical household electricity power curves to classify household electricity load types. If the household electricity load is a long-term stable load or a periodic load, then the household electricity load curve for each period can be predicted by using a statistical regression model or a machine learning prediction model, combined with the current seasonal label, user behavior pattern label and holiday label. If the household electricity load is a random burst load type, a probabilistic burst load model is constructed based on the start frequency, average duration and peak power of historical burst loads to predict the household electricity load curve and calculate the burst power reserve of household electricity.

[0041] By extracting features from the collected long-term household historical electricity consumption data and performing cluster statistics on features such as the changing trend, duration, and peak periods of the power curve, household loads can be classified into stable long-term load types, periodic load types, and random sudden load types.

[0042] Among them, stable long-term load types include continuously operating devices such as refrigerators and routers, which have small power fluctuations and are highly predictable; periodic load types include devices with time regularity and periodic fluctuations such as air conditioners and electric water heaters, whose operating modes are affected by factors such as temperature, season, and user habits; and random burst load types include short-term high-power devices such as microwave ovens and hair dryers, whose operation is random and difficult to predict accurately by directly relying on traditional time series models.

[0043] For the classified long-term stable load type and periodic load type, statistical regression model or machine learning prediction model can be used, combined with seasonal factors, user behavior patterns and work / holiday labels, to generate household electricity load prediction curves for each time period of the next day.

[0044] To improve prediction accuracy, the system can also incorporate external features, such as outdoor temperature, humidity, and local holiday patterns, to correct prediction biases for periodic loads.

[0045] For random burst loads, an independent modeling approach is used instead of directly incorporating them into the overall prediction curve. Based on the characteristics of historical burst loads, such as start frequency, average duration, and peak power, a probabilistic burst load model is constructed, and its potential cumulative power demand is calculated. This cumulative power is not directly added to the next day's load curve, but is provided to the energy storage battery management module in the form of "burst power reserve" to reserve a certain proportion of energy storage space or instantaneous charge and discharge capacity in advance.

[0046] By predicting random burst loads, energy storage devices can cope with the instantaneous power surges caused by random burst loads, avoiding excessive output of energy storage devices or affecting the overall scheduling strategy due to excessive burst loads.

[0047] In one embodiment, a preset proportion of available energy is reserved in the energy storage battery. When it is detected that the user's actual daily electricity consumption increases by more than a predetermined threshold or the actual daily photovoltaic power generation is lower than a predetermined threshold, the reserved energy in the energy storage battery is used for compensation.

[0048] To enhance adaptability in unforeseen circumstances, a portion of the battery's available energy can be reserved during the initial planning phase. This reserve provides short-term compensation during sudden load spikes or photovoltaic (PV) drops, preventing power shortages from exceeding battery load limits. The reserved energy can be set to a fixed value (fixed percentage), specifically based on the maximum power deviation actually observed in the battery. When a deviation in the household's instantaneous power is detected, the reserved energy is used to adjust the battery's discharge power, allowing the energy storage system to maximize the absorption of PV power while meeting the household's load demands, thus mitigating the impact of prediction errors.

[0049] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0050] Figure 3 This is a schematic diagram of a home energy storage scheduling optimization system provided in an embodiment of the present invention. The system includes: Data acquisition module 310 is used to acquire daily electricity price information, daily weather information, historical electricity consumption data of user households, and status of energy storage devices, respectively; The first prediction module 320 is used to predict the photovoltaic power generation power of the day based on the weather information of the day through a photovoltaic power prediction model. The photovoltaic power prediction model is trained based on historical photovoltaic power generation data and historical weather information. The second prediction module 330 is used to predict the daily household electricity consumption based on the user's historical household electricity consumption data and through a household load prediction model. The optimal scheduling solution module 340 is used to construct an objective optimization function based on the photovoltaic power generation, household electricity consumption, electricity price information and energy storage device status information of the day, and calculate the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day through the solver; Optionally, the objective optimization function can be the minimization of daily electricity cost or the maximization of electricity revenue, and at least power constraints, SOC constraints, battery capacity constraints and energy conservation constraints can be set. Based on the objective optimization function and constraints, the solver is invoked to calculate the optimal charging power and discharging power for each time period of the day, and to generate the corresponding optimal scheduling instruction set.

[0051] The scheduling optimization module 350 is used to compare the actual detected battery charging power and discharging power with the planned optimal charging power and optimal discharging power respectively. When the difference between the charging power or discharging power exceeds the preset threshold, the charging and discharging power for the remaining time period of the day will be dynamically optimized again.

[0052] In one embodiment, the first prediction module 320 further includes: The error judgment unit is used to obtain the current actual photovoltaic output power and the predicted photovoltaic power generation power at a predetermined time granularity. When the difference between the actual photovoltaic output power and the predicted photovoltaic power generation power exceeds a preset threshold, dynamic error correction is triggered.

[0053] Optionally, the dynamic correction unit further includes: The weather assessment unit is used to obtain current weather information and determine whether the change value of weather parameters exceeds the threshold within a set unit of time. If the change value of weather parameters exceeds the threshold, the weather factor is reassessed, and the photovoltaic power generation forecast curve for the day is scaled or corrected. Preferably, the weather assessment unit further includes: The dynamic correction unit is used to obtain the actual output power of the photovoltaic power generation during the current preset time period, generate a correction curve for a future period based on the trend of the actual output power of the photovoltaic power generation and the original slope of the photovoltaic power generation prediction curve, and use the correction curve as the photovoltaic power generation prediction curve.

[0054] In one embodiment, the second prediction module 330 includes: The load segmentation unit is used to extract features from users' historical electricity consumption data, perform cluster statistics on the changing trends, durations and peak periods of historical electricity power curves, and classify household electricity load types. The first electricity consumption prediction unit is used to predict the household electricity consumption curve for each period by using a statistical regression model or machine learning prediction model, combined with the current seasonal label, user behavior pattern label and holiday label, if the household electricity load is a long-term stable load type or a periodic load type. The second electricity consumption prediction unit is used to predict the household electricity consumption curve by constructing a probabilistic burst load model based on the start frequency, average duration and power peak of historical burst loads if the household electricity load is a random burst load type, and to calculate the burst power reserve of household electricity consumption.

[0055] In one embodiment, the scheduling optimization module 350 further includes: The reserved scheduling unit is used to compensate for the user's actual daily electricity consumption increase exceeding a predetermined threshold or the actual daily photovoltaic power generation being lower than a predetermined threshold after setting a preset proportion of available energy to reserve in the energy storage battery.

[0056] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0057] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device is used for battery scheduling optimization. Figure 4 As shown, the electronic device 40 of this embodiment includes: a memory 410, a processor 420, and a system bus 430. The memory 410 includes an executable program 4101 stored thereon. As those skilled in the art will understand, Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0058] The following is combined with Figure 4 A detailed introduction to each component of the electronic device: The memory 410 can be used to store software programs and modules. The processor 420 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 410. The memory 410 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cached data), etc. In addition, the memory 410 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0059] The memory 410 contains an executable program 4101 for energy scheduling methods. This executable program 4101 can be divided into one or more modules / units, which are stored in the memory 410 and executed by the processor 420 to implement energy storage battery charging and discharging scheduling, etc. Each module / unit can be a series of computer program instruction segments capable of performing a specific function, describing the execution process of the executable program 4101 in the electronic device 40. For example, the executable program 4101 can be divided into functional modules such as a data acquisition module, a first prediction module, a second prediction module, an optimal scheduling solution module, and a scheduling optimization module.

[0060] The processor 420 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 410, and by calling data stored in the memory 410, it performs various functions and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 420 may include one or more processing units; preferably, the processor 420 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, application programs, etc., and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 420.

[0061] The system bus 430 is used to connect various functional components inside the computer, transmitting data, address, and control information. Its type can be, for example, a PCI bus, an ISA bus, or a CAN bus. Instructions from the processor 420 are transmitted to the memory 410 via the bus, and the memory 410 sends data back to the processor 420. The system bus 430 is responsible for data and instruction exchange between the processor 420 and the memory 410. Of course, the system bus 430 can also connect to other devices, such as network interfaces and display devices.

[0062] In this embodiment of the invention, the executable program executed by the processor 420 included in the electronic device includes: The system acquires daily electricity price information, daily weather information, historical electricity consumption data of users' households, and the status of energy storage devices, respectively. Based on the weather information of the day, the photovoltaic power generation power of the day is predicted by a photovoltaic power prediction model, which is trained based on historical photovoltaic power generation data and historical weather information. Based on users’ historical household electricity consumption data, the household load prediction model is used to predict the household’s daily electricity consumption. Based on the daily photovoltaic power generation, daily household electricity consumption, daily electricity price information, and energy storage device status information, an objective optimization function is constructed, and the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day are calculated by a solver. The actual measured battery charging power and discharging power are compared with the planned optimal charging power and optimal discharging power. If the difference between the charging power and the discharging power exceeds the preset threshold, the charging and discharging power for the remaining time period of the day will be dynamically optimized again.

[0063] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0064] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0065] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions 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 invention.

Claims

1. A method for optimizing the scheduling of residential energy storage, characterized in that, include: The system acquires daily electricity price information, daily weather information, historical electricity consumption data of users' households, and the status of energy storage devices. Based on the weather information of the day, the photovoltaic power generation power of the day is predicted by a photovoltaic power prediction model, which is trained based on historical photovoltaic power generation data and historical weather information. The method of predicting the photovoltaic power generation capacity of the day based on the weather information of the day through the photovoltaic power prediction model also includes: The actual output power of the photovoltaic system and the predicted photovoltaic power generation are obtained at a predetermined time granularity. When the difference between the actual output power of the photovoltaic system and the predicted photovoltaic power generation exceeds a preset threshold, dynamic error correction is triggered. The step of triggering dynamic error correction when the difference between the actual photovoltaic output power and the predicted photovoltaic power generation exceeds a preset value further includes: Obtain current weather information, determine whether the change value of weather parameters exceeds the threshold within a set unit time, and if the change value of weather parameters exceeds the threshold, trigger a reassessment of weather factors and scale or correct the photovoltaic power generation forecast curve for the day. Based on users’ historical household electricity consumption data, the household load prediction model is used to predict the household’s daily electricity consumption. The method of predicting daily household power consumption based on historical household electricity consumption data using a household load prediction model includes: Feature extraction is performed on historical electricity consumption data of users' households, and cluster statistics are performed on the changing trends, duration and peak periods of historical household electricity power curves to classify household electricity load types. If the household electricity load is a long-term stable load or a periodic load, then the household electricity load curve for each period can be predicted by using a statistical regression model or a machine learning prediction model, combined with the current seasonal label, user behavior pattern label and holiday label. If the household electricity load is a random burst load type, a probabilistic burst load model is constructed based on the start frequency, average duration and peak power of historical burst loads to predict the household electricity load curve and calculate the burst power reserve of household electricity. Based on the daily photovoltaic power generation, daily household electricity consumption, daily electricity price information, and energy storage device status information, an objective optimization function is constructed, and the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day are calculated by a solver. The actual measured battery charging power and discharging power are compared with the planned optimal charging power and optimal discharging power. If the difference between the charging power and the discharging power exceeds the preset threshold, the charging and discharging power for the remaining time period of the day will be dynamically optimized again.

2. The method according to claim 1, characterized in that, The scaling or correction of the daily photovoltaic power generation forecast curve includes: The actual output power of the photovoltaic system during the current preset time period is obtained. Based on the trend of the actual output power of the photovoltaic system and the original slope of the photovoltaic power generation prediction curve, a correction curve for a future period is generated, and the correction curve is used as the photovoltaic power generation prediction curve.

3. The method according to claim 1, characterized in that, The construction of the objective optimization function and the calculation of the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day using a solver include: The objective optimization function is to minimize the daily electricity price cost or maximize the electricity price revenue, and at least power constraints, SOC constraints, battery capacity constraints, and energy conservation constraints are set. Based on the objective optimization function and constraints, the solver is invoked to calculate the optimal charging power and discharging power for each time period of the day, and to generate the corresponding optimal scheduling instruction set.

4. The method according to claim 1, characterized in that, The step of dynamically optimizing the charging and discharging power for the remaining time period of the day when the difference between charging power and discharging power exceeds a preset threshold also includes: The system sets a preset percentage of available energy to be reserved in the energy storage battery. When it detects that the user's actual daily electricity consumption increases by more than a predetermined threshold or the actual daily photovoltaic power generation is lower than a predetermined threshold, the system will use the reserved energy in the energy storage battery to compensate for the excess.

5. A home energy storage scheduling and optimization system, characterized in that, include: The data acquisition module is used to acquire the daily electricity price information, the daily weather information, the user's historical electricity consumption data, and the status of energy storage devices, respectively. The first prediction module is used to predict the photovoltaic power generation power of the day based on the weather information of the day through a photovoltaic power prediction model. The photovoltaic power prediction model is trained based on historical photovoltaic power generation data and historical weather information. The first prediction module further includes: The error judgment unit is used to obtain the current actual photovoltaic output power and the predicted photovoltaic power generation power at a predetermined time granularity. When the difference between the actual photovoltaic output power and the predicted photovoltaic power generation power exceeds a preset threshold, dynamic error correction is triggered. The weather assessment unit is used to obtain current weather information and determine whether the change value of weather parameters exceeds the threshold within a set unit of time. If the change value of weather parameters exceeds the threshold, the weather factor is reassessed, and the photovoltaic power generation forecast curve for the day is scaled or corrected. The second prediction module is used to predict the daily household electricity consumption based on the user's historical household electricity consumption data and through a household load prediction model. The second prediction module includes: The load segmentation unit is used to extract features from users' historical electricity consumption data, perform cluster statistics on the changing trends, durations and peak periods of historical electricity power curves, and classify household electricity load types. The first electricity consumption prediction unit is used to predict the household electricity consumption curve for each period by using a statistical regression model or machine learning prediction model, combined with the current seasonal label, user behavior pattern label and holiday label, if the household electricity load is a long-term stable load type or a periodic load type. The second electricity consumption prediction unit is used to predict the household electricity consumption curve by constructing a probabilistic burst load model based on the start frequency, average duration and power peak of historical burst loads if the household electricity load is a random burst load type, and to calculate the burst power reserve of household electricity. The optimal scheduling solution module is used to construct an objective optimization function based on the daily photovoltaic power generation, daily household electricity consumption, daily electricity price information, and energy storage device status information, and to calculate the optimal charging power and optimal discharging power of the energy storage battery for each time period of the day through the solver; The scheduling optimization module compares the actual detected battery charging power and discharging power with the planned optimal charging power and optimal discharging power respectively. When the difference between the charging power and the discharging power exceeds the preset threshold, the charging and discharging power for the remaining time period of the day is dynamically optimized again.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a home energy storage scheduling optimization method as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed, it implements the steps of a home energy storage scheduling optimization method as described in any one of claims 1 to 4.

Images