Multi-terminal linkage energy scheduling method and apparatus

Abstract

The present application relates to a multi-terminal linkage energy scheduling method and apparatus. The method comprises: acquiring multi-terminal data, wherein the multi-terminal data comprises power supply side data, power grid side data, load side data, and energy storage side data; on the basis of the acquired multi-terminal data, predicting multi-terminal electricity amount related information within a future preset time period by means of a prediction algorithm, wherein the multi-terminal electricity amount related information comprises photovoltaic power generation related information, power grid power generation related information, power consumption information of a load side device, and electricity charging and discharging related information of an energy storage device; on the basis of an energy efficiency target, acquiring energy regulation information by means of the multi-terminal electricity amount related information; and controlling the energy storage device and / or the load side device on the basis of the energy regulation information. According to the solution of the present application, by means of a multi-party linkage mechanism, a scheduling plan formed on the basis of a preset scheduling target is more suitable for actual requirements and more accurate, and the energy storage device and the load side device can be automatically controlled on the basis of the scheduling plan.

Description

Multi-terminal linkage energy scheduling method and device Technical Field

[0001] The present application relates to the field of electrical information technology, and in particular to a multi-terminal linkage energy scheduling method and device. Background Art

[0002] As carbon neutrality becomes a global priority, various countries and regions are introducing policies to encourage photovoltaics. Global distributed solar photovoltaic capacity is projected to reach 530 GW by 2024. Solar photovoltaics are also becoming the most cost-effective alternative to alternative power generation. After experiencing four phases of growth: start-up, development, decline, and recovery, my country's photovoltaic industry has now entered a period of steady growth. Many households are installing photovoltaic panels on their roofs and inverters, energy storage batteries, charging stations, and other equipment to optimize their energy mix and reduce energy consumption. At the same time, the ability to optimize household equipment to achieve energy conservation and emission reduction is gaining increasing attention.

[0003] Existing technologies include integrated home energy intelligent optimization and management systems based on model predictive control. These systems analyze the structural characteristics of a home energy local area network (LAN) and the operating characteristics of each device to develop an economical and optimal energy management solution. For example, LMPC methods can be used to perform online rolling optimization based on the energy consumption demands of loads within the LAN at different times, real-time energy prices, and the status of distributed generation and energy storage devices, achieving optimal energy allocation, economical system operation, and safe operation.

[0004] Existing technologies also include photovoltaic building energy planning solutions for home users. These solutions establish prediction models for photovoltaic power generation, power supply, and load demand, aiming to minimize investment and operating costs over the life of the building energy system project. These solutions then plan the capacity of energy storage devices connected to the building energy system. This technology is used to plan the capacity of energy storage devices by establishing photovoltaic power generation models, power supply models, load demand models, and minimizing investment and operating costs.

[0005] Summary of the Invention

[0006] The inventors found that common household integrated energy management systems do not have sufficient accuracy in predicting data collected from multiple terminals; moreover, common household integrated energy management systems do not fully consider the linkage of the multiple devices that constitute the system and lack coordination.

[0007] According to a first aspect of the present application, a multi-terminal linkage energy scheduling method is provided, characterized by comprising:

[0008] Acquiring multi-terminal data, wherein the multi-terminal data includes power supply side data, grid side data, load side data, and energy storage side data;

[0009] Based on the acquired multi-terminal data, a prediction algorithm is used to predict multi-terminal power information within a preset time period in the future. The multi-terminal power information includes photovoltaic power generation information, grid power generation information, load-side equipment power consumption information, and energy storage equipment charge and discharge information.

[0010] According to the energy efficiency target, obtaining energy control information through the multi-terminal power information; and

[0011] The energy storage device and / or the load-side device are controlled according to the energy regulation information.

[0012] According to a second aspect of the present application, a multi-terminal linked energy dispatching device is provided, characterized in that it includes:

[0013] A data acquisition unit, configured to acquire multi-terminal data, wherein the multi-terminal data includes power supply side data, grid side data, load side data, and energy storage side data;

[0014] A data prediction unit is configured to predict, based on the acquired multi-terminal data, multi-terminal power information within a preset future time period using a prediction algorithm, the multi-terminal power information including photovoltaic power generation information, grid power generation information, load-side equipment power consumption information, and energy storage equipment charge and discharge information;

[0015] a regulation information acquisition unit, configured to acquire energy regulation information through the multi-terminal power information according to an energy efficiency target; and

[0016] A device control unit is used to control the energy storage device and / or the load-side device according to the energy regulation information.

[0017] According to a third aspect of the present application, an electronic device is provided, including:

[0018] processor; and

[0019] The memory stores computer instructions, and when the computer instructions are executed by the processor, the processor is caused to perform the method described in the first aspect.

[0020] According to a fourth aspect of the present application, a non-transitory computer storage medium is provided, storing a computer program, which, when executed by multiple processors, enables the processors to execute the method described in the first aspect.

[0021] According to the linked energy scheduling method and device provided in this application, by using information such as the household's power supply side, load side, storage side, and grid side models, an optimal control model is calculated according to the preset scheduling objectives to form a scheduling plan. The scheduling plan is then used to regulate the charging and discharging of energy storage devices and the power consumption of load-side devices. Through a multi-party linkage mechanism, the solution of this application forms a scheduling plan that is more in line with actual needs and more accurate according to the preset scheduling objectives, and can automatically control energy storage devices and load-side devices according to the scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without exceeding the scope of protection required by this application.

[0023] FIG1 is a schematic diagram of an energy dispatching system based on source-grid-load-storage linkage according to an embodiment of the present application.

[0024] FIG2 is a flow chart of a multi-terminal linkage energy scheduling method according to the first embodiment of the present application.

[0025] FIG3 is a flow chart of a multi-terminal linkage energy scheduling method according to a second embodiment of the present application.

[0026] FIG4 is a schematic diagram of a multi-terminal linkage energy scheduling device according to the first embodiment of the present application.

[0027] FIG5 is a schematic diagram of a multi-terminal linkage energy scheduling device according to a second embodiment of the present application.

[0028] FIG6 is a structural diagram of an electronic device provided by this application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0030] This application provides an energy efficiency target optimization and scheduling system based on source-grid-load-storage linkage. This system focuses on regulating the charging and discharging of energy storage batteries and load power consumption. It considers factors such as the power generation of various distributed photovoltaic power generation devices in household energy systems, the charging / discharging of electric vehicles, charging piles, and energy storage systems, as well as the power consumption of smart loads, to build an optimal control system based on energy efficiency goals. As shown in Figure 1, the system mainly consists of a power supply module, a grid module, a load module, an energy storage module, an intelligent algorithm module, and a control module.

[0031] According to some embodiments, the power supply side module may include a data acquisition module and a prediction module. The power supply may be in various forms. In the case where the power supply is photovoltaic, the power supply side includes photovoltaic modules, inverters and other equipment. The data acquisition module collects real-time data and historical data on photovoltaic power generation as well as meteorological weather, temperature, irradiance, etc., and organizes, stores and analyzes the data. After filtering abnormal information (for example, filtering noise, false data, interference data, etc.), the data is transmitted to the prediction module, and the prediction module will output power generation information for a period of time in the future. Before the power supply side module is put into use or during the process of being put into use, the prediction module compares and verifies the real data with the predicted data, corrects the deviation, and makes the data predicted by the prediction module more and more accurate. At the same time, the prediction module also transmits data to the intelligent algorithm module.

[0032] According to some embodiments, the grid side includes smart meters, CTs, and other equipment. The grid-side module may include a data acquisition module and a prediction model. The data acquisition module collects data such as the amount of electricity purchased and sold to the grid, the frequency and number of power outages, and the prices at which electricity is purchased and sold from the grid, and organizes, stores, and analyzes the data. After filtering out abnormal information, the data is transmitted to the prediction module, which outputs data such as the number of power outages, the duration of power outages, and the amount of electricity purchased and sold for a certain period of time. Before or during the commissioning of the grid-side module, the prediction module compares and verifies actual data with predicted data, corrects any deviations, and ensures that the predicted data is increasingly accurate. Simultaneously, the prediction module also transmits data to the intelligent algorithm module.

[0033] According to some embodiments, the load side can be divided into off-grid or on-grid loads (such as washing machines, air conditioners, water heaters, etc.) and back-up loads (such as emergency exit lighting, refrigerators, etc.), which can be further divided into dispatchable loads (such as washing machines, dishwashers, water heaters), cuttable loads (such as air conditioners, televisions) and critical loads (such as lighting equipment, refrigerators). The load side module may include a data acquisition module and a prediction model. Among them, the data acquisition module can collect data such as the load power consumption on the on-grid side (conventional) and the load power consumption on the back-up side (emergency), the user's power usage habits, and organize, store and analyze the data. After filtering the abnormal information, the data is passed to the prediction module, and the prediction module will output data such as load power consumption that conforms to the user's rules for a period of time in the future. The prediction module compares and verifies the real data with the predicted data, corrects the deviation, and makes the data predicted by the prediction module more and more accurate. At the same time, the prediction module also transmits data to the intelligent algorithm model;

[0034] According to some embodiments, the energy storage side may include energy storage batteries, electric vehicles (EVs) with charging stations, and other equipment. The energy storage side module may include a data acquisition module and a prediction model. According to some embodiments, the equipment in the energy storage side module includes both conventional energy storage batteries and modern electric vehicles with bidirectional charging stations. Electric vehicles have the dual properties of energy storage and load, and their energy storage properties can be used as large "power banks." The data acquisition module collects data such as battery charge and discharge power, battery capacity, SOC (State of Charge), and SOH (State of Health), and organizes, stores, and analyzes the data. After filtering out abnormal information, the data is transmitted to the prediction module, which outputs information such as how long it will take to fully charge and the remaining power. The prediction module compares and verifies actual data with predicted data, correcting for any discrepancies and ensuring increasingly accurate predictions. The prediction module in the energy storage side module transmits this data to the intelligent algorithm module. Simultaneously, the energy storage module also receives the energy scheduling plan from the control module to control the charging and discharging of the equipment.

[0035] According to some embodiments, the intelligent algorithm module uses the data information provided by the prediction modules in each module to build an AI model with the goals of prioritizing electricity sales, ensuring electricity use, or minimizing electricity costs, etc., and derives an optimal control plan through neural networks, deep learning and other algorithms, and transmits it to the control module.

[0036] According to some embodiments, the control module generates the optimal real-time scheduling instructions for the equipment at the current moment based on the control plan information calculated by the intelligent algorithm module, and sends the control instructions to each equipment unit in the home energy structure through electronic information communication technology to achieve the optimal solution for home energy.

[0037] In the system shown in Figure 1, measuring instruments are installed on the power supply, grid, load, and energy storage sides to collect and digitally store data. Serial communication ports, including but not limited to RS422, RS232, and RS485, enable automatic data collection, storage, analysis, and analysis. Data transmission is accomplished through USB, large and small quad-core interfaces, or built-in Bluetooth / WiFi / Zigbee modules.

[0038] Based on the above system, according to one aspect of the present application, a method for coordinated energy scheduling is provided. FIG2 is a flow chart of a multi-terminal coordinated energy scheduling method according to a first embodiment of the present application. As shown in FIG2 , the method includes the following steps.

[0039] Step S201, acquiring multi-terminal data, wherein the multi-terminal data includes power supply side data, grid side data, load side data, and energy storage side data;

[0040] Step S202: Based on the acquired multi-terminal data, a prediction algorithm is used to predict multi-terminal power-related information within a preset time period in the future. The multi-terminal power-related information includes photovoltaic power generation-related information, grid power generation-related information, power consumption information of load-side equipment, and charge-discharge information of energy storage equipment.

[0041] As shown in Figure 1, the power supply side, grid side, load side, and energy storage side each have a corresponding data acquisition module and prediction module. The power supply module, grid side module, load side module, energy storage side module, intelligent algorithm module, and control module in Figure 1 send and receive data at set intervals (e.g., 5 minutes). The power supply module, grid side module, load side module, and energy storage side module each predict relevant data for the current time interval before the next time interval. For example, if the time interval is 5 minutes, at 0 minutes, the data corresponding to the 5-minute interval is predicted, at 5 minutes, the data corresponding to the 10-minute interval is predicted, and so on.

[0042] For photovoltaic power sources, the data acquisition model collects both real-time and historical data on photovoltaic power generation, weather, temperature, and irradiance, and organizes, stores, and analyzes this data. After filtering out any anomalies, the data is passed to the prediction module, which outputs information about photovoltaic power generation over the next period of time.

[0043] The following aspects should be considered when developing a prediction algorithm for power generation information. Photovoltaic power generation is significantly affected by weather conditions and varies with sunlight. Higher irradiance values ​​result in higher power generation. The power generation output from the prediction model is calculated based on the difference between the predicted and actual data.

[0044] On the grid side, the data acquisition module collects grid-side data, including the amount of power purchased and sold to the grid, the frequency and number of power outages, and the prices at which electricity is purchased and sold to the grid. This data is then organized, stored, and analyzed. After filtering out abnormal information, the data is passed to the prediction module, which outputs grid-related information, including the number of power outages, their duration, and the amount of power purchased and sold.

[0045] For example, the grid can obtain the local time-of-use electricity price, Price1(grid, t), based on the location information provided by the user when creating a power station. Assuming that abnormal power outages occur repeatedly due to the same reason, for ease of calculation, this price is converted into an additional electricity price during the outage period, with a multiplier of β. In this way, the additional fee during the outage period is B*Price1(grid, t).

[0046] The optimized electricity price Price(grid, t)=(1+β)*Price1(grid, t).

[0047] On the load side, the data acquisition module collects load-side data, including on-grid and backup load power consumption, as well as user electricity usage habits. The module then organizes, stores, and analyzes this data, filtering out any anomalies before transmitting it to the prediction module. The prediction module outputs load-side device power consumption information, including load power consumption consistent with user patterns over a period of time.

[0048] The load-side data acquisition module collects historical data on users' devices, including historical household appliance load and electric vehicle mileage. This data can be used to derive ideal scheduling and predict household load demand. Hourly power consumption information for household appliance loads can be obtained through smart meters, or by viewing electricity bills provided by the power grid company. Monthly power consumption can be broken down into daily units based on household electricity needs. Hourly power consumption within a single day can also be scheduled based on appliance characteristics and user preferences. Specific settings are as follows:

[0049] Based on household electricity consumption information and user electricity consumption habits, electrical loads are divided into dispatchable loads and non-dispatchable loads. The average daily photovoltaic hourly power generation of the month is selected, and the average daily photovoltaic power generation is subtracted from the non-dispatchable load power to obtain the hourly power surplus and shortage. The dispatchable load is then dispatched. At the same time, the non-dispatchable load and the dispatchable load after dispatch are collected to generate the forecast data for household load demand after dispatch for each time period.

[0050] Furthermore, electric vehicles are gradually becoming ubiquitous in households, serving the dual roles of energy storage and load. Electric vehicles are typically charged at night during off-peak hours to ensure the lowest electricity prices while maintaining the same level of usage the following day. Therefore, the charging load of electric vehicles is shifted to off-peak hours as a dispatchable load. Automakers have developed a comprehensive conversion relationship between mileage and charge capacity, allowing them to calculate the required charge capacity for electric vehicles.

[0051] On the energy storage side, the equipment in the energy storage module includes both conventional energy storage batteries and new electric vehicles combined with bidirectional charging stations. Electric vehicles have the dual properties of energy storage and load, and their energy storage properties allow them to function as large "power banks." The data acquisition module collects energy storage data, including battery charge and discharge power, battery capacity, SOC, SOH, and other data, and organizes, stores, and analyzes this data. After filtering out abnormal information, the data is transmitted to the prediction module, which outputs information related to the energy storage device's charge and discharge, including how long it will take to fully charge and how long the remaining power will last.

[0052] For example, the data acquisition module in the energy storage model can collect data such as the battery's charge and discharge power, rated capacity, SOH, and SOC. The remaining battery capacity, the expected hours to fully charge, and the remaining battery life can be calculated using the following formula:

[0053] Remaining battery capacity = rated capacity * SOH * SOC

[0054] Estimated hours to fully charge = rated capacity * SOH * (1-SOC) / charging power

[0055] Remaining power available hours = rated capacity * SOH * SOC / power consumption.

[0056] For the power supply, grid, load, and energy storage sides, each prediction model considers not only the multi-terminal data currently being collected in real time by the data acquisition module, but also historical multi-terminal data and the difference between the predicted data and the actual measured data for the previous time period. Furthermore, the difference between the predicted data and the actual measured data for the current time period is calculated and used to predict data for the next time period. This continuous iteration ensures more accurate predictions from the prediction module.

[0057] In this way, step S202 can specifically include: predicting the multi-terminal power-related information within a future preset time period through the prediction algorithm based on the multi-terminal data currently collected in real time, the multi-terminal data collected historically, and the deviation between the multi-terminal power-related information predicted last time and the multi-terminal power-related information currently obtained.

[0058] Step S203, obtaining energy control information through the multi-terminal power-related information according to the energy efficiency target; and

[0059] Step S204: Control the energy storage device and / or the load-side device according to the energy regulation information.

[0060] The intelligent algorithm module uses data provided by the prediction modules in each model to build an AI model with energy efficiency as the goal. Using neural networks, deep learning, and other algorithms, it develops an optimal control plan and transmits it to the control module. Energy efficiency goals include at least one of prioritizing electricity sales, ensuring electricity availability, and minimizing electricity costs.

[0061] According to some embodiments, if the energy efficiency goal is to prioritize electricity sales, all generated electricity is sold to the grid company and not used for household consumption or battery charging. This goal is generally applicable in areas where electricity purchase prices are low and electricity sales prices are high. If the energy efficiency goal is to guarantee electricity supply, during periods of abnormal utility power, the energy storage battery can support normal household loads. This goal is generally applicable in areas with frequent climate anomalies. If the energy efficiency goal is to minimize electricity costs, the conventional practice is to charge energy storage during valley prices and discharge energy storage during peak prices under time-of-use electricity prices to achieve peak-valley arbitrage. This goal is generally applicable in areas with time-of-use electricity prices.

[0062] For the control module, based on the control plan information calculated by the intelligent algorithm module, it generates the best real-time scheduling instructions for the equipment at the current moment, and sends control instructions to each equipment unit in the home energy structure through electronic information and communication technology to achieve the optimal solution for home energy.

[0063] After obtaining energy regulation information based on the energy efficiency target, the energy storage device and / or the load-side device on the energy storage side can be controlled based on the energy regulation information. Among them, the control of the energy storage device mainly controls the charging and discharging of the energy storage device. For example, when the energy efficiency target is to ensure electricity consumption, the energy storage device is maintained at a predetermined power level, and when the power level of the energy storage device does not meet the requirement, it is charged; for another example, when the power provided by the front grid side and the power supply side does not meet the needs of the load device, the energy storage device is instructed to discharge. In addition, the control of the load-side device is mainly to reduce the power consumption of the load-side device.

[0064] Load-side devices can generally be divided into dispatchable and non-dispatchable loads, or on-grid and backup loads. Non-dispatchable loads are typically required for emergencies or cannot be arbitrarily powered off, such as emergency exit lighting and refrigerators. Dispatchable loads are typically non-emergency devices, such as televisions and washing machines. In some embodiments, load-side devices can be configured as dispatchable or non-dispatchable loads based on actual needs.

[0065] When the system's power supply is insufficient to meet the needs of load-side devices, it is necessary to reduce the power consumption of the load-side devices. According to some embodiments, reducing the power consumption of load-side devices generally involves dispatching power to dispatchable load devices while ensuring power consumption of non-dispatched load devices among the load-side devices. For example, if the current power supply is 20W, the power consumption of non-dispatched load devices is 10W, and the power consumption of non-dispatched load devices is 15W, then 10W of the 20W will be first allocated to the non-dispatched load devices, and the remaining 10W will be allocated to the non-dispatched load devices.

[0066] Thus, step S204 may specifically include:

[0067] In response to the energy control information indicating that the energy storage device is to be charged within the future preset time period, controlling the energy storage device to charge;

[0068] In response to the energy control information indicating that the energy storage device is to be discharged within the future preset time period, controlling the energy storage device to discharge; and

[0069] In response to the energy regulation information indicating that the power consumption of the load-side device should be reduced within the future preset time period, the power consumption of the load-side device is controlled to be reduced.

[0070] For the sake of convenience in explaining the solution of this application, the energy efficiency goal of this application is to minimize the cost of electricity. Electric vehicles are now gradually entering thousands of households, and they have a huge impact on the pressure on the power grid and the scheduling of household energy. In the energy management system of this application, electric vehicles (including charging piles) are taken into account. They can be used as both power loads and discharge power sources.

[0071] Under the goal of minimizing electricity costs, we first construct an objective function to achieve this goal, as shown in the following equation:

[0072] in:

[0073] Δt is the time interval between each period of the grid electricity price during the peak, flat and valley periods;

[0074] y represents the grid electricity price;

[0075] Price(grid, t) is the unit price of cost or benefit between the household and the grid in period t;

[0076] Home(grid, t) is the power exchanged between the home and the grid in period t;

[0077] Price(ev,t) is the unit price of the built-in battery power decay cost of the electric vehicle in period t;

[0078] Power(ev,t) is the charging and discharging power of the electric vehicle in period t;

[0079] Price(bat, t) is the unit price of the sum of the energy storage battery power decay cost and the battery pack maintenance cost in period t;

[0080] Power(bat, t) is the charging and discharging power of the energy storage battery in period t;

[0081] Data is acquired, predictions are made, and energy control information is obtained at fixed time intervals. The tth period refers to the current time interval.

[0082] In this embodiment, the multi-terminal power-related information includes the grid electricity price, the unit price of the cost or benefit between the home and the grid, the exchange power between the home and the grid, the unit price of the electric vehicle's built-in battery power decay cost, the electric vehicle's charge and discharge power, the unit price of the sum of the energy storage battery power decay cost and the battery pack maintenance cost, and the energy storage battery charge and discharge power. It will be understood by those skilled in the art that, depending on actual circumstances and needs, the multi-terminal power-related information may also include other information, which falls within the scope of this application.

[0083] In this embodiment, the objective function must satisfy the constraints of energy conservation of the system, charge and discharge power, and charge and discharge capacity of the battery and electric vehicle. That is, the objective function Min Cost satisfies the following constraints:

[0084] Energy conservation constraints

[0085] Power(pv,t)+Home(grid,t)=Power(load,t)+Power(ev,t)

[0086] Among them, Power(pv,t) is the photovoltaic power generation power in the tth period, and Power(load,t) is the power of all loads in the tth period.

[0087] Energy storage battery charging and discharging power constraints

[0088] -χ*P-bat≤Power(bat,t)≤χ*P-bat

[0089] Where P-bat is the unit battery pack capacity, and χ is the battery pack charge or discharge power limit ratio within the time period Δt.

[0090] Energy storage battery charge and discharge capacity constraints

[0091] Wherein, P-bat is the capacity of the unit battery pack; It is the minimum capacity ratio allowed for a unit battery pack. It is the maximum capacity ratio allowed for a unit battery pack.

[0092] Electric vehicle charging power constraints

[0093] Among them, P-ev is the unit electric vehicle battery pack capacity, It is the charging or discharging power limit ratio of the electric vehicle battery pack within the time period Δt.

[0094] Electric vehicle charging and discharging capacity constraints

[0095] Ψmin*P-ev≤∑Power(ev,t)≤Ψmax*P-ev

[0096] Among them, P-ev is the unit electric vehicle battery pack capacity, Ψmin is the minimum capacity ratio allowed for electric vehicles, and Ψmax is the maximum capacity ratio allowed for electric vehicles.

[0097] Under the premise of satisfying the above constraints, the values ​​of Home(grid, t), Power(ev, t), and Power(bat, t) are determined to minimize the objective function Min Cost. Among them, Home(grid, t)>0 and Home(grid, t)<0 respectively indicate the need to purchase electricity from the grid and the need to sell electricity to the grid; Power(ev, t)>0 and Power(ev, t)<0 respectively indicate charging and discharging electric vehicles; Power(bat, t)>0 and Power(bat, t)<0 respectively indicate charging and discharging energy storage batteries. After obtaining energy control information based on energy efficiency goals, energy storage devices and / or load-side devices can be controlled based on this energy control information. For example, in the above embodiment, Power(ev, t)>0 indicates that the electric vehicle is charged, and the corresponding energy control information is to charge the electric vehicle in the next time period; Power(ev, t)<0 indicates that the electric vehicle is discharged, and the corresponding energy control information is to instruct the electric vehicle to discharge in the next time period; Power(bat, t)>0 indicates that the energy storage battery is charged, and the corresponding energy control information is to instruct the energy storage battery to charge in the next time period; Power(bat, t)<0 indicates that the energy storage battery is discharged, and the corresponding energy control information is to discharge the energy storage battery in the next time period.

[0098] In this way, generating energy regulation information corresponding to the lowest electricity cost includes: determining the values ​​of multi-terminal power-related information corresponding to the case where the electricity cost is lowest; and generating energy regulation information according to the values ​​of multi-terminal power-related information.

[0099] This application takes into account the dual properties of electric vehicles (including charging piles) of energy storage and load, and constructs a new objective function corresponding to the energy efficiency goal of minimizing electricity costs. The energy regulation information obtained can be more adapted to the current structure of the household integrated energy management system and achieve better regulation accuracy and effect.

[0100] FIG3 is a flow chart of a multi-terminal linkage energy scheduling method according to a second embodiment of the present application. Compared with FIG2 , steps S301 to S304 of FIG3 are the same as steps S201 to S204 of FIG2 , except that FIG3 further includes the following steps.

[0101] Step S305, obtaining actual multi-terminal power information within the future preset time period;

[0102] Step S306, comparing the predicted multi-terminal power related information with the actual multi-terminal power related information to obtain a prediction deviation value; and

[0103] Step S307: Optimize the prediction algorithm according to the prediction deviation value.

[0104] For any of the power supply, grid, load, and energy storage modules, the predicted data for the current time period is based on currently collected data, historically collected data, and the deviation between the predicted data and the actual data for the previous time period. During the prediction process for the current time period, the deviation between the predicted data and the actual data for the previous time period is used to optimize the current prediction algorithm.

[0105] For example, if the prediction algorithm used is an algorithm based on a neural network model, during the prediction process, the deviation between the predicted data and the actual data is used as feedback data to continuously optimize and improve the neural network model. For example, the coefficients of the neural network model are adjusted so that the predicted data continues to approach the actual data.

[0106] Among them, the process of optimizing the prediction algorithm corresponding to the prediction model, on the one hand, can be before the data acquisition module collects data, historical data (including the collected historical data and the corresponding real data) can be input into the prediction model for training, by comparing and verifying the real data with the predicted data, correcting the deviation, so that the prediction data of the prediction algorithm is more and more accurate. When the prediction accuracy of the prediction model meets the requirements, the trained prediction model is used for actual data prediction. On the other hand, in the process of data acquisition module collecting data, by comparing and verifying the real data with the predicted data, correcting the deviation, so that the prediction data of the prediction algorithm is more and more accurate, that is, the prediction accuracy of the prediction module is continuously optimized in the actual data collection and prediction process. In addition, the above two methods can also be used in combination, that is, before the data acquisition module collects data, the prediction model is trained by inputting historical data into the prediction model, and the prediction accuracy of the prediction module is continuously optimized in the actual data collection and prediction process.

[0107] According to another aspect of the present application, a multi-terminal linkage energy scheduling device is provided. FIG4 is a schematic diagram of a linkage energy scheduling device according to a first embodiment of the present application. As shown in FIG4 , the linkage energy scheduling device includes a real-time acquisition unit 401, a data prediction unit 402, a plan acquisition unit 403, and a device control unit 404.

[0108] Among them, the data acquisition unit 401 is used to acquire multi-terminal data, and the multi-terminal data includes power supply side data, grid side data, load side data and energy storage side data; the data prediction unit 402 is used to predict multi-terminal power-related information within a future preset time period through a prediction algorithm based on the acquired multi-terminal data, and the multi-terminal power-related information includes photovoltaic power generation-related information, grid power generation-related information, power consumption information of load-side equipment and power charging and discharging information of energy storage equipment; the control information acquisition unit 403 is used to acquire energy control information through the multi-terminal power-related information according to energy efficiency goals; and the device control unit 404 is used to control the energy storage device and / or the load-side device according to the energy control information.

[0109] According to some embodiments, the control information acquisition unit 403 includes:

[0110] A construction subunit, configured to construct an objective function related to minimizing electricity cost based on the multi-terminal power related information;

[0111] a determination subunit, configured to determine the constraints that the objective function needs to satisfy; and

[0112] The generating subunit is used to generate energy regulation information corresponding to the lowest electricity cost under the constraint conditions.

[0113] Among them, the energy storage equipment includes energy storage batteries and electric vehicles, and the multi-terminal power-related information includes the power price of the power grid, the unit price of the cost or benefit between the household and the power grid, the exchange power between the household and the power grid, the unit price of the built-in battery power decay cost of the electric vehicle, the charging and discharging power of the electric vehicle, the unit price of the sum of the energy storage battery power decay cost and the battery pack maintenance cost, and the energy storage battery charging and discharging power; the constraint conditions include energy conservation constraint conditions, energy storage battery charging and discharging power constraint conditions, energy storage battery charging and discharging capacity constraint conditions, electric vehicle charging power constraint conditions and electric vehicle charging and discharging capacity constraint conditions.

[0114] Wherein, the generating subunit is further used for:

[0115] Determining the values ​​of the multi-terminal power-related information corresponding to the minimum electricity cost; and

[0116] The energy control information is generated according to the values ​​of the multi-terminal power related information.

[0117] The energy regulation information includes the charging or discharging of the electric vehicle and / or the charging or discharging of the energy storage battery. The device control unit 404 is further configured to:

[0118] Instructing the electric vehicle to perform charging or discharging within the future preset time period; and / or instructing the energy storage battery to perform charging or discharging within the future preset time period.

[0119] Figure 5 is a schematic diagram of a multi-terminal linkage energy scheduling device according to the second embodiment of the present application. As shown in Figure 5, the linkage energy scheduling device includes a data acquisition unit 501, a data prediction unit 502, a control information acquisition unit 503, a device control unit 504, a real data acquisition unit 505, a deviation calculation unit 506 and an algorithm optimization unit 507. Among them, units 501 to 504 are the same as units 401 to 404 in Figure 4 and are not repeated here. The real data acquisition unit 505 is used to obtain the actual multi-terminal power information within the future preset time period; the deviation calculation unit 506 is used to compare the predicted multi-terminal power information with the actual multi-terminal power information to obtain a prediction deviation value; the algorithm optimization unit 507 is used to optimize the prediction algorithm based on the prediction deviation value. According to the multi-terminal linkage energy scheduling method and device provided by the present application, by knowing the power supply side, load side, storage side and grid side models of the home, the optimal control model is calculated according to the preset scheduling target, a scheduling plan is formed, and the charging and discharging of the energy storage device and the power consumption of the load side device are regulated by the scheduling plan. The solution of this application uses a multi-party linkage mechanism to form a scheduling plan according to preset scheduling targets that is more in line with actual needs and more accurate, and can automatically control energy storage equipment and load-side equipment according to the scheduling plan.

[0120] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical connection or other forms.

[0123] Referring to FIG6 , FIG6 provides an electronic device including a processor and a memory. The memory stores computer instructions, which, when executed by the processor, enable the processor to execute the computer instructions to implement the method and detailed solutions shown in FIG2 and FIG3 .

[0124] It should be understood that the above-described device embodiments are merely illustrative, and the devices disclosed herein may also be implemented in other ways. For example, the division of units / modules described in the above-described embodiments is merely a logical functional division, and actual implementations may employ alternative divisions. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0125] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present invention may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0126] If the integrated unit / module is implemented in hardware, the hardware may be a digital circuit, an analog circuit, or the like. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, and the like. Unless otherwise specified, the processor or chip may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the on-chip cache, off-chip memory, and storage may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), and the like.

[0127] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for enabling a computer electronic device (which can be a personal computer, a server or a network electronic device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned memory includes: various media that can store program codes, such as a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0128] An embodiment of the present application further provides a non-transitory computer storage medium storing a computer program. When the computer program is executed by multiple processors, the processors execute the method and detailed solutions shown in Figures 2 and 3.

[0129] The embodiments of the present application are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only intended to help understand the method and core ideas of the present application. At the same time, changes or modifications made by those skilled in the art based on the ideas of the present application, the specific implementation methods, and the scope of application of the present application, all fall within the scope of protection of the present application. In summary, the contents of this specification should not be construed as limiting the present application.

Claims

1. A multi-terminal linkage energy dispatching method, characterized in that: include: Acquire multi-terminal data, wherein the multi-terminal data includes power supply side data, grid side data, load side data and energy storage side data; Based on the acquired multi-terminal data, a prediction algorithm is used to predict multi-terminal power information within a preset time period in the future, wherein the multi-terminal power information includes photovoltaic power generation information, power grid power generation information, power consumption information of load-side equipment, and power charging and discharging information of energy storage equipment; According to the energy efficiency target, energy regulation information is obtained through the multi-terminal power information; as well as The energy storage device and / or the load-side device are controlled according to the energy regulation information.

2. The method according to claim 1, characterized in that Also includes: Obtaining actual multi-terminal power related information within the future preset time period; Comparing the predicted multi-terminal power information with the actual multi-terminal power information to obtain a predicted deviation value; as well as The prediction algorithm is optimized according to the prediction deviation value.

3. The method according to claim 1, characterized in that The acquired multi-terminal data includes the multi-terminal data currently acquired in real time, the multi-terminal data acquired historically, and the deviation between the multi-terminal power related information predicted last time and the multi-terminal power related information currently acquired; The method predicts the multi-terminal power information within a preset time period in the future according to the acquired multi-terminal data by using a prediction algorithm, including: The multi-terminal power-related information within a preset time period in the future is predicted through the prediction algorithm based on the multi-terminal data currently collected in real time, the multi-terminal data collected historically, and the deviation between the multi-terminal power-related information predicted last time and the multi-terminal power-related information currently acquired.

4. The method according to any one of claims 1 to 3, characterized in that The controlling the energy storage device and / or the load-side device according to the energy regulation information includes: In response to the energy regulation information indicating that the energy storage device is to be charged within the future preset time period, controlling the energy storage device to be charged; In response to the energy regulation information indicating that the energy storage device is to be discharged within the future preset time period, controlling the energy storage device to discharge; and In response to the energy regulation information indicating that the power consumption of the load-side device should be reduced within the future preset time period, the power consumption of the load-side device is controlled to be reduced.

5. The method according to any one of claims 1 to 3, characterized in that: The energy efficiency target includes minimizing the electricity cost, and the energy regulation information is obtained through the multi-terminal electricity related information according to the energy efficiency target, including: Constructing an objective function related to the lowest electricity cost based on the multi-terminal power information; Determining constraints that the objective function needs to satisfy; and Under the constraints, energy control information corresponding to the lowest electricity cost is generated.

6. The method according to claim 5, characterized in that in, The energy storage device includes an energy storage battery and an electric vehicle, and the multi-terminal power-related information includes the power price of the power grid, the unit price of the cost or benefit between the household and the power grid, the exchange power between the household and the power grid, the unit price of the built-in battery power decay cost of the electric vehicle, the charging and discharging power of the electric vehicle, the unit price of the sum of the energy storage battery power decay cost and the battery pack maintenance cost, and the energy storage battery charging and discharging power; the constraint conditions include energy conservation constraint conditions, energy storage battery charging and discharging power constraint conditions, energy storage battery charging and discharging capacity constraint conditions, electric vehicle charging power constraint conditions, and electric vehicle charging and discharging capacity constraint conditions.

7. The method according to claim 6, characterized in that Under the constraints, the energy control information corresponding to the minimum electricity cost is generated, including: Determine the value of the multi-terminal power related information corresponding to the minimum power cost; and Generate the energy control information according to the values ​​of the multi-terminal power related information; Wherein, the energy regulation information includes charging or discharging of electric vehicles and / or charging or discharging of energy storage batteries, and the controlling of the energy storage device and / or the load-side device according to the energy regulation information includes: instructing the electric vehicle to perform charging or discharging within the future preset time period; and / or The energy storage battery is instructed to perform charging or discharging within the future preset time period.

8. A multi-terminal linkage energy dispatching device, characterized in that: include: A data acquisition unit, used to acquire multi-end data, wherein the multi-end data includes power supply side data, grid side data, load side data and energy storage side data; A data prediction unit, configured to predict, based on the acquired multi-terminal data, multi-terminal power-related information within a preset time period in the future by a prediction algorithm, wherein the multi-terminal power-related information includes photovoltaic power generation-related information, power grid power generation-related information, power consumption information of load-side equipment, and power charging and discharging information of energy storage equipment; A control information acquisition unit, configured to acquire energy control information through the multi-terminal power related information according to an energy efficiency target; as well as A device control unit is used to control the energy storage device and / or the load-side device according to the energy regulation information.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images