Energy scheduling management method and device, micro-grid system and energy management system

Abstract

The invention provides an energy scheduling management method and device, a micro-grid system and an energy management system. The method comprises the following steps: in response to received natural language type power consumption scene information, identifying a user intention; determining a target power utilization scene according to the user intention, at least one of the received equipment induction information and a preset scene case library; and performing scheduling management on at least one of power generation equipment, energy storage equipment and power utilization equipment connected with the energy scheduling management system according to the target power utilization scene. The intelligent level and the user satisfaction degree of energy dispatching management are improved, and meanwhile, the energy utilization efficiency is also improved.

Description

Technical Field

[0001] This application relates to the field of power system technology, specifically to an energy dispatch management method, device, microgrid system, and energy management system. Background Technology

[0002] In photovoltaic-storage-charging systems, related technologies typically formulate energy dispatch strategies based on forecasts of renewable energy generation such as wind and solar power, combined with electricity consumption forecasts, to improve the system's energy efficiency. For example, in residential photovoltaic-storage-charging systems, the charging and discharging periods of energy storage batteries can be planned in advance based on forecasts of photovoltaic power generation and household electricity consumption. This prioritizes the storage and utilization of surplus photovoltaic power, and releases electricity during peak electricity prices or periods of insufficient sunlight, thereby maximizing the self-consumption ratio and achieving a win-win situation for both economic and environmental benefits.

[0003] However, when users’ electricity consumption behavior changes, the original energy dispatch strategy, that is, the dispatch and management of power generation equipment, energy storage equipment and power consumption equipment, may be difficult to apply to the new electricity consumption behavior, which may easily cause users’ electricity consumption behavior to be unresponsive, resulting in problems such as reduced user satisfaction and decreased energy utilization efficiency. Summary of the Invention

[0004] This application aims to provide an energy dispatch management method, device, microgrid system, and energy management system, which will be described in the following aspects.

[0005] In a first aspect, an energy dispatch management method is provided, applied to an energy dispatch management system. The method includes: in response to receiving natural language-based electricity consumption scenario information, identifying user intent; determining a target electricity consumption scenario based on the user intent, at least one of the received device sensing information, and a preset scenario case library; and dispatching and managing at least one of the power generation equipment, energy storage equipment, and electricity consumption equipment connected to the energy dispatch management system based on the target electricity consumption scenario.

[0006] As one possible implementation, the device sensing information includes at least one of the following: the status information of the electrical equipment; the current environmental status information; the user status information in the current power consumption scenario; and the user behavior information in the current power consumption scenario.

[0007] As one possible implementation, the step of scheduling and managing at least one of the power generation equipment, energy storage equipment, and power consumption equipment connected to the energy dispatch management system according to the target electricity consumption scenario includes: determining target data corresponding to the target electricity consumption scenario based on the target electricity consumption scenario and the data type corresponding to the target electricity consumption scenario; determining the energy dispatch parameters based on the target data and a pre-established correspondence between the target data and energy dispatch parameters; and scheduling and managing at least one of the power generation equipment, energy storage equipment, and power consumption equipment connected to the energy dispatch management system according to the energy dispatch parameters; wherein the energy dispatch parameters are used to adjust the electricity consumption forecast results and / or dispatch targets of the energy dispatch management system.

[0008] As one possible implementation, the energy dispatch parameters include at least one of the following: load forecast adjustment parameters, used to adjust the load forecast results generated by the energy dispatch management system based on historical load data; dispatch target adjustment parameters, used to adjust the dispatch targets of the energy dispatch management system; wherein the dispatch targets include one or more of the following: economic targets, comfort targets, and environmental targets.

[0009] As one possible implementation, determining the target data corresponding to the target power consumption scenario based on the target power consumption scenario and the data type corresponding to the target power consumption scenario includes: obtaining part or all of the data in the target data from the user intent and / or the device sensing information based on the target power consumption scenario and the data type corresponding to the target power consumption scenario; and / or, in response to the user intent and the device sensing information not containing at least part of the data in the target data, outputting prompt information related to the at least part of the data, and determining the at least part of the data based on the response of the prompt information.

[0010] As one possible implementation, the step of scheduling and managing at least one of the power generation equipment, energy storage equipment, and electrical consumption equipment connected to the energy scheduling management system according to the energy scheduling parameters includes: determining an energy scheduling strategy based on the energy scheduling parameters and electricity consumption forecast results, wherein the electricity consumption forecast results include load forecast results; and scheduling and managing at least one of the power generation equipment, energy storage equipment, and electrical consumption equipment connected to the energy scheduling management system according to the energy scheduling strategy.

[0011] As one possible implementation, determining the energy dispatch strategy based on the energy dispatch parameters and electricity consumption forecast results includes: adjusting the load forecast results and / or adjusting the dispatch objectives of the energy dispatch management system based on the energy dispatch parameters.

[0012] As one possible implementation, the correspondence between the data type corresponding to the target electricity consumption scenario and the target electricity consumption scenario is pre-established in the preset scenario case library.

[0013] As one possible implementation, the method further includes: updating the preset scenario case library based on the actual electricity consumption data of the target electricity consumption scenario.

[0014] Secondly, an energy dispatch management device is provided, comprising: an intent recognition module for receiving natural language-based electricity consumption scenario information and recognizing user intent; a scenario determination module for determining a target electricity consumption scenario based on the user intent, received device sensing information, and a preset scenario case library; and a dispatch execution module for dispatching and managing at least one of the power generation equipment, energy storage equipment, and electricity consumption equipment connected to the energy dispatch management device according to the target electricity consumption scenario.

[0015] Thirdly, a microgrid system is provided, comprising: a power generation device for providing electrical energy to the microgrid system; an energy storage device connected to the power generation device for storing or releasing electrical energy; an electrical consumption device connected to the power generation device and the energy storage device for consuming electrical energy; and a control device communicatively connected to the power generation device, the energy storage device, and the electrical consumption device for executing the energy dispatch management method as described in any implementation of the first aspect.

[0016] Fourthly, an energy management system is provided, comprising: a memory for storing program instructions; and a processor for executing the program instructions to perform the method as described in any implementation of the first aspect.

[0017] This application determines the user's electricity consumption scenario by matching relevant information reflecting the user's electricity consumption behavior, including user intent determined by the user's natural language and operational data received from IoT devices, with a pre-set scenario case library. For example, a family dinner scenario. Based on the determined electricity consumption scenario, the application schedules and manages the power consumption equipment, energy storage equipment, and power generation equipment of the photovoltaic-energy storage-charging system. For example, for a family dinner scenario, the charging and discharging periods of the energy storage battery can be planned in advance to suit the user's electricity consumption behavior, thereby improving user satisfaction and energy utilization efficiency. Attached Figure Description

[0018] Figure 1 The diagram shown is a schematic of the structure of a photovoltaic energy storage and charging system.

[0019] Figure 2 As shown Figure 1 The diagram shows the structure of the energy management system in the photovoltaic energy storage and charging system.

[0020] Figure 3 The diagram shown is a flowchart of the energy dispatch management method provided in an embodiment of this application.

[0021] Figure 4 The diagram shown is a schematic flowchart of an energy dispatch management method provided in an embodiment of this application.

[0022] Figure 5 The diagram shown is a flowchart of an energy dispatch management method provided in another embodiment of this application.

[0023] Figure 6 The diagram shown is a flowchart of an energy dispatch management method provided in another embodiment of this application.

[0024] Figure 7 The diagram shown is a structural schematic of the energy dispatch management device provided in an embodiment of this application.

[0025] Figure 8 The diagram shown is a structural schematic of a microgrid system provided in an embodiment of this application.

[0026] Figure 9 The diagram shown is a structural schematic of the energy management system provided in an embodiment of this application. Detailed Implementation

[0027] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0028] A photovoltaic-storage-charging system (also known as a photovoltaic-storage-charging station) is a typical microgrid system. Its core task is to achieve energy balance and optimal economic efficiency in the closed loop of "power generation-energy storage-electricity consumption". Photovoltaic-storage-charging systems can include residential photovoltaic-storage-charging systems suitable for home users to improve self-consumption rates and save on electricity bills; industrial and commercial photovoltaic-storage-charging systems suitable for factories, shopping malls, office buildings, etc., to reduce electricity costs, increase the proportion of green electricity, and reduce carbon emissions; or integrated energy solutions that highly integrate photovoltaic power generation, energy storage systems, charging equipment, and energy management within standard containers or prefabricated cabins.

[0029] Figure 1 A schematic diagram of a photovoltaic energy storage and charging system is shown. Figure 1 As shown, the photovoltaic-energy storage-charging system 100 includes a power generation module 110, an energy storage module 120, a power conversion module 130, a power consumption module 140, and an energy management module 150. Figure 1 As shown, the residential photovoltaic-storage-charging system 100 can maintain millisecond-level response between grid-connected, off-grid, and grid-connected / off-grid switching states through its electricity meter 160 and public grid interface 170.

[0030] like Figure 1 As shown, the power generation module 110 may include one or more new energy power generation devices, which can be used to convert renewable energy into electrical energy as the energy source for the photovoltaic-storage-charging system 100. The new energy power generation devices may be photovoltaic power generation devices, wind power generation devices, etc.

[0031] The energy storage module 120 can be used to store surplus electrical energy generated by the power generation module 110 and release it when needed. The energy storage module 120 can employ various energy storage technologies, such as electrochemical batteries that store energy through internal chemical reactions, supercapacitors that achieve extremely fast charging and discharging speeds and extremely long cycle lives by relying on the principle of physical electrostatic adsorption, flywheel energy storage technology that converts electrical energy into kinetic energy through an accelerating rotor, and compressed air energy storage that compresses air and stores it in underground caverns, which can be released to generate electricity during peak electricity demand periods.

[0032] The power conversion module 130 can realize the conversion of electrical energy form and control of energy flow between different types of power generation modules 110 and power consumption modules 140. Taking photovoltaic power generation as an example, the power conversion module 130 includes DC-DC boosting on the photovoltaic side, bidirectional DC-AC inversion of the battery in the energy storage module 120, and grid synchronization function; that is, the power conversion module 130 can both invert photovoltaic DC power into AC power for use by the power consumption module 140, and rectify grid AC power into DC power to charge the battery.

[0033] The power module 140 typically includes: an emergency load 141 (i.e., a backup load), such as a refrigerator or security system, which is independently powered by the energy storage module 120 (the battery) when off-grid; a grid-connected load 142, such as everyday household appliances that are directly connected to the grid; and a charging pile 143, which is used to provide green or low-cost electricity for electric vehicles (EVs).

[0034] The energy management module 150, or energy management system (EMS), is the "brain" of the residential photovoltaic-storage-charging system 100. It can be a standalone smart hardware device, embedded in the integrated photovoltaic-storage inverter, or run in the cloud. The EMS can collect real-time data on photovoltaic power generation, battery state of charge (SOC), various load power, and grid electricity price, and store it locally. Then, it runs intelligent control algorithms to send charging and discharging power and time period instructions to the inverter (in the power conversion module 130), the battery management system (BMS) (in the energy storage module 120), and the charging pile, thereby maximizing photovoltaic self-consumption, minimizing household electricity expenses, and seamless switching during grid outages.

[0035] Figure 2 A schematic diagram of the structure of an EMS 150 is shown. (For example...) Figure 2 As shown, the EMS 150 may include an optical power prediction module 151, a load prediction module 152, and a scheduling decision module 153.

[0036] The photovoltaic power prediction module 151 can predict the photovoltaic power generation of the power generation module 110 based on historical photovoltaic data and numerical weather forecasts (meteorological parameters); the load prediction module 152 can predict the load data of the power consumption module 140 based on the historical load data collected and stored by the EMS 150; the scheduling decision module 153 can generate battery charging and discharging instructions, photovoltaic power generation limitation instructions, and charging pile charging instructions based on the photovoltaic power generation predicted by the photovoltaic power prediction module 151, the load data predicted by the load prediction module 152, and combined with electricity price information, charging pile equipment status, etc., thereby optimizing the system's energy utilization efficiency.

[0037] To further enhance the energy dispatch capabilities of photovoltaic-storage-charging systems, the industry currently incorporates charging piles and electric vehicle batteries into a unified dispatch strategy optimization when specifying intelligent dispatch strategies, thereby expanding the capacity boundaries and adjustment dimensions of photovoltaic-storage-charging systems. However, the energy management system (EMS) of photovoltaic-storage-charging systems still faces the following challenges.

[0038] First, the perception of electricity consumption information is too limited in scope. Current EMS systems primarily rely on structured data such as photovoltaic power, load forecasting, time-of-use pricing, and charging pile status, but lack the ability to perceive in real-time key variables affecting household energy consumption, such as household size, member activities, travel plans, ambient temperature, humidity, and weather. Furthermore, they lack the ability to perceive in real-time key variables affecting industrial and commercial energy consumption, such as workshop production plans, equipment maintenance and downtime plans, shift schedules, meeting and event arrangements, and logistics and supply chain information. This lack of data means that optimization models can only operate under limited information conditions, making it difficult to accurately capture users' actual electricity needs, thus affecting the accuracy of dispatching decisions.

[0039] Secondly, EMS lacks timely response to ad-hoc tasks, primarily due to its inability to effectively parse users' natural language input. For example, when users provide crucial information such as "guests are visiting tonight, requiring increased electricity" or "the whole family will be away for the next three days," or when companies provide crucial information through their internal systems such as "equipment maintenance this Friday, production will be shut down all day" or "temporarily increase production by 50% for three days," EMS cannot convert these into executable constraints or optimization parameters. This prevents dynamic adjustments to load forecasting and dispatching strategies, potentially leading to the waste of renewable energy or additional electricity purchase costs, as well as an inability to provide better service to users, resulting in low user satisfaction and poor energy efficiency.

[0040] To address the aforementioned problems, this application proposes an energy dispatch and management method, device, microgrid system, and energy management system. The following describes... Figures 3 to 9 The working principles of the energy dispatch management method, device, microgrid system, and energy management system proposed in this application are illustrated with examples. It should be understood that... Figures 3 to 9 The examples provided are merely to help those skilled in the art understand the embodiments of this application, and are not intended to limit the embodiments of this application to... Figures 3 to 9 The specific structure is as follows. Based on the examples given, those skilled in the art will obviously be able to make various equivalent modifications or changes, and such modifications and changes also fall within the scope of the embodiments of this application.

[0041] The energy dispatch management method proposed in this application includes, for example: Figure 3 As shown, step S310: In response to the received natural language-based electricity usage scenario information, identify the user's intent.

[0042] Among them, natural language-based electricity usage scenario information refers to electricity usage scenario information contained in natural language. This information can be expressed by household users directly in everyday spoken language or written form, reflecting their needs, intentions, or temporary changes. It is easy to understand that although this type of information is usually fragmented and unstructured, it best reflects the actual electricity usage scenario.

[0043] In some embodiments, natural language information may include natural language dialogue input by the user. As an example, a user mentioning in the dialogue, "We have guests tonight, so the living room air conditioner needs to be turned on half an hour earlier," includes power consumption information in four dimensions: time, space, equipment, and family activities. As another example, a user mentioning in the dialogue, "An elderly person suddenly falls ill, so let's reserve the energy storage power for the bedroom air conditioner first," reflects the priority adjustment in an emergency medical power consumption scenario.

[0044] In other embodiments, natural language information may also include weather forecasts presented in natural language forms such as spoken language or text. For example, descriptions like "Thunderstorms tomorrow afternoon, temperature drops sharply by 8 degrees Celsius" or "Sunny for the next three days, UV radiation is extremely strong" often carry emotional connotations or offer practical tips. Compared to numerical meteorological data (such as numerical weather forecasts), these are more intuitive and easier for users to directly incorporate into their home energy management decisions. For instance, "scorching sun" might prompt a user to raise the air conditioning temperature in advance. For instance, hearing "strong winds and temperature drop" might temporarily switch the nighttime heating to continuous operation.

[0045] It should be understood that, in the embodiments of this application, natural language information may include one or more of the following: user-input natural language dialogue and weather forecasts presented in natural language form; this embodiment of the application is not limited to these. It should also be understood that the types of natural language information in this application are not limited to these; natural language information may also be other types of information.

[0046] like Figure 3 As shown, in step S320, the target power consumption scenario is determined based on at least one of the determined user intent and the received device sensing information and a preset scenario case library.

[0047] In some embodiments, the device sensing information may include one or more of the following: the status information of the electrical device, the current environmental status information, the user status information in the current power consumption scenario, and the user behavior information in the current power consumption scenario.

[0048] As one method, device sensing information is obtained through third-party intelligent systems, IoT devices, smart homes, and other electricity-related information.

[0049] Among them, the device sensing information from the third-party intelligent system can be data directly or indirectly related to electricity consumption that is pushed in real time by an external mature intelligent platform (i.e., the third-party intelligent system) through its own sensors, terminals or cloud services.

[0050] Because third-party smart systems are usually deeply integrated with mature smart home and Internet of Things technologies, and connect to various sensing terminals such as human body sensors, temperature and humidity sensors, radio frequency identification (RFID) devices, and intelligent connected vehicles, they can provide richer and more comprehensive device sensing information.

[0051] This application does not limit the types of third-party intelligent systems. In some embodiments, the third-party intelligent system can be a smart home system. For example, it can connect to devices such as lights and air conditioners via short-range wireless protocols to provide real-time feedback on the status of people indoors and the operating parameters of the devices.

[0052] In some other embodiments, the third-party intelligent system can also be a vehicle-to-everything (V2X) system. For example, it can rely on the vehicle's built-in communication module to upload data such as battery level, driving location, and estimated arrival time to the cloud, thereby supporting remote appliance control and charging reservation.

[0053] In addition, IoT devices can be used to acquire device sensing information. For example, IoT devices are metering devices such as smart meters and sockets, which can record electricity consumption data with accuracy at the second or millisecond level; for example, IoT devices for the environment are temperature, humidity and human infrared sensors to capture the state of the environment and the presence of people; for example, IoT devices are mobile transportation devices such as charging pile controllers and vehicle terminals to provide real-time feedback on battery status and charging needs.

[0054] By using the electricity-related information reflected in the received device sensing information based on user intent, as mentioned above, we can expand the user's perception of electricity information dimensions, thereby more accurately capturing the user's actual electricity demand and laying the foundation for formulating more accurate energy dispatch strategies.

[0055] In this application embodiment, the preset scenario case library may also be called the electricity scenario collection, electricity scenario library, etc., which pre-stores multiple electricity scenarios. Each electricity scenario can be used to systematically describe the user behavior pattern in the corresponding activity scenario.

[0056] For example, the household electricity consumption scenario of "family gathering" represents the behavioral patterns corresponding to families gathering at home, including an increase in the number of family members and the increase in household electrical appliances. For example, the household electricity consumption scenario of "going on vacation" represents a decrease in the number of family members or even no one at home, resulting in a decrease in household electrical appliances.

[0057] In some embodiments, the pre-defined scenario case library can be constructed through the collection and analysis of historical actual electricity consumption data. As one approach, data sources may include total household load power data recorded by smart meters, start-stop times and operating power details of household appliances obtained from IoT device detection, family member activity habits recorded in user behavior logs, and standardized household electricity consumption cases provided by publicly available datasets.

[0058] In this embodiment, the preset scenario case library can be a user-specific scenario case library or a public scenario case library; this embodiment does not limit this. The user-specific scenario case library can be a highly personalized library gradually formed by storing, recording, and learning the historical electricity consumption behavior and preferences of individual users. For example, for a family that habitually charges its electric vehicle (EV) daily, the electricity demand for the EV (on the day of charging) is less than the electricity demand when the EV is habitually charged once a week.

[0059] The public scenario case library can be typical scenario templates that are pre-built by the system provider or trained with massive amounts of data. These templates are highly versatile and universal, and can provide reliable basic scenario recognition capabilities for new users or users who lack historical data.

[0060] This application does not limit the method used to store multiple electricity consumption scenarios in the preset scenario case library. In some embodiments, a knowledge graph can be used to store multiple electricity consumption scenarios. As a semantic network representation, knowledge graphs are well-suited for expressing complex relationships between scenarios, electrical equipment, personnel, and environmental parameters, thus intuitively describing the associations between various types of data in scenarios such as "family gatherings." In other embodiments, a database (e.g., a relational database or a time-series database) can be used to store multiple electricity consumption scenarios in the scenario case library to meet the frequent query needs of electricity consumption scenarios. In still other embodiments, a lightweight document-based storage method such as JSON can be used to improve flexibility.

[0061] As mentioned above, it can be seen that by combining user intent determined from natural language-based electricity usage scenario information with one or more types of device sensing information, relatively sufficient information about the user's electricity usage can be obtained. Based on the obtained electricity usage information and a pre-set scenario case library, the user's target electricity usage scenario can be determined. The target electricity usage scenario can be the user's electricity usage scenario at a future time, or it can be the user's current electricity usage scenario, which can be determined specifically through electricity usage information.

[0062] In other words, the target electricity scenario can be selected from the preset scenario case library that is closest to the user intent and device sensing information determined based on natural language-based electricity scenario information.

[0063] In some embodiments, the target electricity consumption scenario can be determined by using an agent in conjunction with LLM (Local Language Management). As one approach, when a user inputs a vague instruction (e.g., "There will be many people at home tonight"), LLM can transform it into a clear user intent ("family gathering" scenario) through natural language processing. At this point, the agent can then search for similar cases from a pre-defined scenario case library as the target electricity consumption scenario. For example, The user entered: "I need to charge my phone tonight"; A prompt can be constructed: The agent can provide: 1. Intelligent operation and maintenance service; 2. Battery level query service; 3. Customized scheduling scenario optimization service; If a user enters "I need to charge tonight", which service might they need? Please provide the information in the format {number: service}. LLM provides the answer: {3: Optimize services for custom scheduling scenarios} Once intent recognition is complete, the custom scheduling scenario optimization service Agent is invoked to identify the user's intent and subsequently determine the target electricity consumption scenario.

[0064] like Figure 3 As shown, in step S330, at least one of the power generation equipment, energy storage equipment, and power consumption equipment connected to the energy dispatch management system is dispatched and managed according to the target electricity consumption scenario. For example, when the electricity consumption corresponding to the target electricity consumption scenario is high, the power generation equipment can be controlled to generate more electricity, or the energy storage equipment can store more energy during off-peak hours. For example, when the electricity consumption corresponding to the target electricity consumption scenario is low, less power generation or energy storage can be implemented to improve energy utilization efficiency.

[0065] As can be seen, this application determines the user's electricity consumption scenario by matching relevant information that reflects the user's electricity consumption behavior, including user intent determined by the user's natural language and received operational data such as from IoT devices, with a preset scenario case library. For example, a family dinner scenario. Based on the determined electricity consumption scenario, the application schedules and manages the power consumption equipment, energy storage equipment, and power generation equipment of the photovoltaic-storage-charging system. For example, for a family dinner scenario, the charging and discharging periods of the energy storage battery can be planned in advance to suit the user's electricity consumption behavior, improve user satisfaction, and improve energy utilization efficiency.

[0066] In some embodiments, the preset scenario case library may also store data types corresponding to various electricity consumption scenarios, used to determine target data based on the determined target electricity consumption scenario. That is, in the preset scenario case library, for each electricity consumption scenario, the required data type is predefined to determine the target data. In other words, the correspondence between the determined target electricity consumption scenario and its corresponding data type is pre-established in the preset scenario case library. As an example, the data types corresponding to the "family gathering" scenario may include: "start time," "end time," "number of participants," "dining method," and "ambient temperature," etc. When analyzing electricity-related data obtained based on user intent, device sensing information, etc., and determining, for example, "there are 11 people at the dinner tonight," the corresponding data type is "number of participants," and the corresponding target data can be determined to be "11 people."

[0067] As can be seen, in this embodiment of the application, the target data of the target power consumption scenario can be determined based on the target power consumption scenario and the data type corresponding to the target power consumption scenario.

[0068] It should be understood that the data types corresponding to the electricity consumption scenarios (including target electricity consumption scenarios) can be preset and updated in real time according to the actual usage situation during the use of the preset scenario case library. This application embodiment does not limit this.

[0069] Once the target data corresponding to the target electricity consumption scenario is determined, the embodiments of this application can determine the energy dispatch parameters based on the target data and the pre-established correspondence between the target data and the energy dispatch parameters.

[0070] The pre-established correspondence between target data and energy scheduling parameters can be a predefined mapping rule in a preset scenario case library, which is a rule for converting target data into energy scheduling parameters.

[0071] In this embodiment of the application, the energy dispatch management system can dispatch and manage one or more of the electrical equipment, energy storage equipment, and power generation equipment connected to it according to energy dispatch parameters.

[0072] In some embodiments, energy dispatch parameters may include load forecasting adjustment parameters, which may also be referred to as load forecasting influence factors. These load forecasting adjustment parameters can be used to adjust the load forecasting results generated by the energy dispatching management system based on historical load data.

[0073] For example, firstly, when the target electricity consumption scenario is determined to be "family gathering," the required data types are determined by querying a preset scenario case library, including: start time, end time, number of people, dining method, and ambient temperature. Then, based on user input, "number of people: 11" is determined; "ambient temperature: 30°C" is obtained from the temperature and humidity sensor; and "start time: 18:00, end time: 21:00, dining method: outdoor barbecue" is determined from the user dialogue. Then, according to the mapping rules defined in the preset scenario case library, energy scheduling parameters are generated based on the above data (and historical load data). For example, the rule is: if the number of people for an outdoor barbecue is greater than 10, the load prediction adjustment parameter is determined to be: load increase of 20%.

[0074] It should be understood that in the above examples, the energy scheduling parameters can be determined as: a 20% increase in load, or further as: a 20% increase in load from 18:00 to 21:00. This application does not limit the specific implementation.

[0075] In some embodiments, energy dispatch parameters may also include dispatch target adjustment parameters, which may also be referred to as dispatch target weighting factors. These dispatch target adjustment parameters can be used to adjust the dispatch targets of the energy dispatch management system.

[0076] In this application embodiment, the scheduling objective can be an economic objective, that is, to meet the electricity demand of the target electricity consumption scenario with the lowest cost as the premise for corresponding scheduling management; the scheduling objective can also be a comfort objective, that is, to conduct corresponding scheduling management with the highest user comfort as the premise for corresponding scheduling management; the scheduling objective can also be an environmental objective, that is, to conduct corresponding scheduling management with the highest proportion of the electricity source of the electrical equipment corresponding to the electricity generated by new energy in the electricity required by the target electricity consumption scenario as the premise for corresponding scheduling management.

[0077] For example, when comfort is the scheduling goal, the corresponding scheduling management is as follows: when the ambient temperature exceeds 28 degrees Celsius, turn on the air conditioner half an hour in advance, or store hot water in advance.

[0078] It should be understood that, in the embodiments of this application, the purpose of setting the scheduling target is to meet the user's electricity demand. One approach is to determine the scheduling target by defining the objective of the scheduling algorithm used, where the design objective of the scheduling algorithm originates from the user's electricity demand.

[0079] For example, when users prioritize economic efficiency, their electricity demand is designed as an algorithmic objective of "minimizing operating costs" or "minimizing electricity expenses," thus determining the system's scheduling objective to prioritize the use of lower-cost energy sources while meeting basic constraints. When users prioritize power supply reliability, their demand is transformed into an algorithmic objective of "minimizing power outages" or "maximizing voltage stability," guiding the scheduling objective towards ensuring continuous power supply and power quality. When users focus on environmental benefits, "minimizing carbon emissions" or "maximizing renewable energy consumption" becomes the core algorithmic objective, directly shaping a green and low-carbon-oriented scheduling strategy. This mechanism ensures that the final energy scheduling accurately responds to and serves the user's electricity consumption intentions.

[0080] It is easy to understand that in the embodiments of this application, the energy scheduling parameters can include both load prediction adjustment parameters and scheduling target adjustment parameters for scheduling management.

[0081] For example, when the load forecast adjustment parameter is "the load needs to be increased by 30% from 19:00 to 21:00", and the scheduling target adjustment parameter is "comfort priority", the energy scheduling strategy of the energy scheduling management system may include "commanding the energy storage battery to start charging at 5kW power at 4 pm, and commanding the EV charging to be delayed until midnight".

[0082] In some embodiments, to improve reliability and accuracy, after determining the target power consumption scenario based on user intent and / or device sensing information, it is further verified whether this information completely includes the target data corresponding to all data types for that target scenario. If some key data is found to be missing, a follow-up inquiry process can be automatically triggered, that is, outputting prompt information related to the missing data, such as proactively sending an inquiry message to the user regarding the missing data. After the user responds to the prompt information, the missing data can be supplemented by analyzing the response information until all target data corresponding to the target power consumption scenario is complete.

[0083] For example, when a user mentions "a family gathering tonight," the system first identifies the target electricity consumption scenario as "family gathering" and queries the preset scenario case library. This scenario typically requires data types such as "start time," "end time," "number of participants," and "dining method." However, the user's initial statement only mentions the intention to have a gathering without providing any specific information. Therefore, the system detects that the target data for this scenario is missing. Consequently, the energy dispatch management system will sequentially ask follow-up questions: "What time does the gathering start?", "How many people are expected to attend?", and "Is it indoor dining or an outdoor barbecue?"

[0084] Based on the specific content of the user's reply, the missing target data can be analyzed and identified, thus providing complete information input for the subsequent accurate generation of energy scheduling parameters.

[0085] For example, users responded one by one with "Starting at 6 pm", "About 10 people", and "Planning to have a barbecue in the yard". Based on these responses, the missing target data can be accurately determined as: start time (6:00 pm), number of people (10), and dining method (outdoor barbecue), thereby completing the target data and providing a basis for subsequent precise adjustments and scheduling.

[0086] To further improve the reliability of responding to users' electricity demands, during the user inquiry process, it can be first determined whether the user's input is relevant to energy dispatch. If the user's input is unrelated to energy dispatch, the response should be terminated directly. Only when the user's input is relevant to energy dispatch can subsequent related responses be initiated.

[0087] In this embodiment of the application, when scheduling and managing at least one of the power generation equipment, energy storage equipment, and power consumption equipment connected to the energy dispatch management system, an energy dispatch strategy can be determined based on energy dispatch parameters and power consumption forecast results, wherein the power consumption forecast results may include load forecast results.

[0088] In one approach, load forecasting results may include load forecasting results generated based on system operating data. This system operating data may be physical operating data that directly reflects or directly affects household electricity consumption.

[0089] For example, system operation data may include photovoltaic power generation related data, household load related data, and energy equipment related data. Photovoltaic power generation related data may include, for example, historical photovoltaic data stored in the EMS. Household load related data may include household load power, such as the power of electrical appliances like lighting, air conditioning, and kitchen appliances, load curves, and may also include special load characteristics, such as the power of electric vehicle charging piles and the charging and discharging power of energy storage PCS; energy equipment related data may include energy storage systems (e.g., Figure 1 The device status of the energy storage module 120 (in the system) can include, for example, the real-time SOC of the energy storage battery, the charging and discharging power of the energy storage battery, and the upper and lower limits of SOC. It can also include the device status of the EV, such as the real-time SOC of the EV, the charging and discharging power of the EV, and the SOC management threshold. Furthermore, it can include the photovoltaic system (e.g., Figure 1 The device status of the power generation module 110 in the system includes real-time discharge power, curtailed power, and inverter capacity limits. In addition, electricity-related information may also include some grid interaction data, such as the exchange power between the household and the main grid, i.e., the grid connection point power, and grid constraints (such as time-of-use pricing).

[0090] It should be understood that, in the embodiments of this disclosure, determining the energy dispatch strategy based on energy dispatch parameters and electricity consumption forecast results may include: adjusting the energy dispatch strategy generated based on the electricity consumption forecast results according to the energy dispatch parameters, and adjusting the electricity consumption forecast results according to the energy dispatch parameters, and then generating the corresponding energy dispatch strategy based on the adjusted electricity consumption forecast results.

[0091] One possible implementation of the scheme is to adjust the electricity consumption forecast results based on energy dispatch parameters and then generate an energy dispatch strategy based on the adjusted electricity consumption forecast results. This can be achieved by using energy dispatch parameters (e.g., load forecast adjustment parameters) to adjust the load forecast results in the electricity consumption forecast results, and / or using energy dispatch parameters (e.g., dispatch target adjustment parameters) to adjust the dispatch target of the energy dispatch management system.

[0092] In some embodiments, to further improve the reliability of the preset scenario case library, it can be updated. As one approach, after the user activity corresponding to the target electricity consumption scenario is completed, i.e., after the electricity consumption scenario ends, the data corresponding to the electricity consumption scenario in the preset scenario case library can be optimized by comparing the initial prediction (e.g., determining a 50% increase in expected electricity load based on target data and the correspondence between target data and load prediction influencing factors) with the actual electricity consumption data (e.g., after the target household electricity consumption scenario ends, the actual load only increases by 20%). For example, the values ​​of the load prediction adjustment parameters under the "outdoor barbecue" scenario can be automatically corrected, or new constraints can be added.

[0093] The updates to the above-mentioned preset scenario case library make the electricity usage scenario data in the scenario library more closely match users' real habits. As a result, when encountering the same or similar scenarios again in the future, more accurate energy scheduling parameters and energy scheduling strategies can be generated based on more accurate historical data.

[0094] Similarly, it is conceivable that constraints on energy equipment-related data can be added, deleted, modified, and queried to optimize the energy dispatching decisions of the EMS.

[0095] For example, when the power consumption scenario is "emergency backup", the energy dispatch parameters may include the constraint of "lower limit of energy storage SOC". In this case, its parameter can be modified from the usual 20% (in order to extend battery life) to 50% (in order to ensure that the home storage has emergency power), thereby dynamically changing the system's operating rules and prioritizing safety over economy.

[0096] For example, when the user scenario is "traveling," constraints related to human comfort, such as air conditioning and lighting, become irrelevant. In this case, these constraints and their corresponding variables can be deleted to improve optimization efficiency.

[0097] To facilitate understanding, the following will be combined with... Figures 4 to 6 This application provides a detailed description of the energy dispatch and management method proposed. It should be understood that... Figures 4 to 6 These are merely illustrative examples and do not constitute a limitation on the embodiments of this application.

[0098] like Figure 4 As shown, when a user inputs corpus, the first-layer intent recognition module first makes a preliminary judgment on the input content to identify whether it belongs to an instruction that needs to be modified in EMS. For example, by constructing a prompt to ask the LLM user the service type corresponding to the statement, if it is identified as an intent such as "custom scheduling scenario optimization service", then it enters the second-layer intent recognition module; otherwise, the process terminates.

[0099] The second-layer intent recognition module can match the input corpus with the electricity usage scenarios in the preset scenario case library to determine the most suitable target electricity usage scenario.

[0100] Subsequently, the necessary data types for the target electricity consumption scenario are extracted from the preset scenario case library, and it is determined whether the current user input already contains the target data corresponding to all data types; if there are any missing data, follow-up questions can be initiated (for example, providing default options such as "outdoor barbecue / indoor feast" for the user to choose from) until the user completes all the target data.

[0101] Finally, by calling LLM again to parse the user corpus, the complete target data is combined with the pre-established relationship between the target data and energy dispatch parameters, and transformed into energy dispatch parameters (such as load forecasting adjustment parameters), which are then transmitted to EMS, thereby completing the dispatch management of any one of the power generation equipment, energy storage equipment, and power consumption equipment.

[0102] like Figure 5 As shown, in a family gathering scenario, it can be deeply integrated with third-party systems such as smart home and smart vehicle networking systems. Through cameras, human body sensors, etc., it can detect an increase in the number of family members and transmit information such as the number of family members to EMS. EMS performs scene recognition according to the following steps.

[0103] Step 510: Interact with users through methods such as app push notifications.

[0104] Step 520: The LLM asks the user if they are planning a family gathering. After receiving an affirmative answer, follow up with the start and end times, number of attendees, etc.

[0105] Step 530: Combine indoor ambient temperature, weather forecast, and other data to search the scenario case library. Based on the search results, it is determined that cooking in the evening requires increased electricity load, and due to the high ambient temperature, air conditioning needs to be turned on for cooling. Adjust the parameters according to the load forecast and increase the load forecast value for the family gathering period.

[0106] Step 540: The EMS load forecasting module (time series forecasting large model) adjusts the forecasting results and generates new load forecasting results.

[0107] Step 550: The EMS scheduling decision module, based on the new load forecast results and information such as electricity prices, fully charges the energy storage batteries to prepare for demand during the evening when electricity prices are high. Simultaneously, it postpones the charging time for electric vehicles to the early morning of the following day.

[0108] Step 560: After completing the event, ask the user about the scheduling effect, and add the prediction and scheduling results to the event case library based on the user feedback.

[0109] like Figure 6 As shown, in scenarios where users are away from home, they proactively communicate with EMS via apps or other means to inform them of their upcoming long-distance vacation. EMS then identifies the electricity usage scenario. Step 610: Users interact with the energy management system through methods such as APP dialogue to inform it of their vacation plans.

[0110] Step 620: LLM asks for details about the vacation plan, such as when to leave, whether to drive, and whether the refrigerator at home can be turned off.

[0111] Step 630: The LLM combines indoor ambient temperature, weather forecast, and other data to query the scenario case library. Based on the query results, it sends a command to the EMS scheduling decision module to fully charge the electric vehicle (because the user needs to travel by electric vehicle), adjusts the backup power SOC (because the weather is unstable in the future and there is a risk of power outage, the refrigerator at home needs backup power), and sends a command to the EMS load forecast module to lower the future load forecast result (no one will be home during the vacation and there is no demand for electricity).

[0112] Step 640: The EMS scheduling decision module generates a new scheduling plan to ensure safe and economical electricity use for users during their vacation.

[0113] Step 650: After the scenario ends, combine user feedback information to generate a new electricity usage scenario and add it to the scenario case library.

[0114] The above text combined Figures 1 to 6 The method embodiments of this application are described in detail below, in conjunction with... Figures 7 to 9The present application provides a detailed description of the apparatus embodiments. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be found in the foregoing method embodiments.

[0115] This application also provides an energy dispatching and management device. For example... Figure 7 As shown, the energy dispatch management device 700 may include: an intent recognition module 710, used to receive natural language-based electricity consumption scenario information and recognize user intent; a scenario determination module 720, used to determine the target electricity consumption scenario based on the user intent, the received device sensing information and a preset scenario case library; and a dispatch execution module 730, used to perform dispatch management on at least one of the power generation equipment, energy storage equipment and electricity consumption equipment connected to the energy dispatch management device according to the target electricity consumption scenario.

[0116] This application also provides a microgrid system. For example... Figure 8 As shown, the microgrid system 800 may include a power generation device 810 for providing electrical energy to the microgrid system 800; an energy storage device 820 connected to the power generation device 810 for storing or releasing electrical energy; an electrical consumption device 830 connected to the power generation device 810 and the energy storage device 820 for consuming electrical energy; and a control device 840 communicatively connected to the power generation device 810, the energy storage device 820, and the electrical consumption device 830 for executing any of the energy dispatch management methods mentioned above.

[0117] This application also provides an EMS, such as Figure 9 As shown, the EMS 900 includes: a memory 910 for storing program instructions; and a processor 920 for executing the program instructions to perform any of the energy dispatch management methods mentioned above.

[0118] It should be understood that in the embodiments of this application, the processor 920 may be a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0119] The memory 910 may include read-only memory and random access memory, and provides instructions and data to the processor 920. A portion of the memory 910 may also include non-volatile random access memory. For example, the memory 910 may also store device type information.

[0120] In implementation, each step of the above method can be completed by the integrated logic circuitry of the hardware in the processor 920 or by instructions in software form. The method for requesting uplink transmission resources disclosed in the embodiments of this application can be directly implemented by the hardware processor, or by a combination of hardware and software modules in the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 910, and the processor 920 reads the information in memory 910 and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are not provided here.

[0121] It should be understood that in the embodiments of this application, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0122] It should be understood that in the embodiments of this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0123] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0124] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes 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 this application.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0126] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0127] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0128] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0129] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An energy scheduling management method applied to an energy scheduling management system, characterized in that, The method comprises: in response to receiving natural language power consumption scenario information, identifying a user intention; determining a target power consumption scenario according to the user intention, at least one of received device sensing information, and a preset scenario case library; managing at least one of power generation equipment, energy storage equipment, and power consumption equipment connected to the energy scheduling and management system according to the target power consumption scenario.

2. The method of claim 1, wherein, The device sensing information includes at least one of: state information of the power consumption equipment; current environmental state information; user state information in the current power consumption scenario; user behavior information in the current power consumption scenario.

3. The method according to claim 1 or 2, characterized in that, The management of at least one of the power generation equipment, the energy storage equipment, and the power consumption equipment connected to the energy scheduling and management system according to the target power consumption scenario comprises: determining target data corresponding to the target power consumption scenario according to the target power consumption scenario and a data type corresponding to the target power consumption scenario; determining an energy scheduling parameter according to the target data and a preset corresponding relationship between the target data and the energy scheduling parameter; managing at least one of the power generation equipment, the energy storage equipment, and the power consumption equipment connected to the energy scheduling and management system according to the energy scheduling parameter; The energy scheduling parameter is used to adjust a power consumption prediction result and / or a scheduling target of the energy scheduling and management system.

4. The method of claim 3, wherein, The energy scheduling parameter includes at least one of: a load prediction adjustment parameter used to adjust a load prediction result generated by the energy scheduling and management system according to historical load data; a scheduling target adjustment parameter used to adjust a scheduling target of the energy scheduling and management system; wherein the scheduling target includes one or more of the following: an economic target, a comfort target, and an environmental protection target.

5. The method of claim 3, wherein, The determination of the target data corresponding to the target power consumption scenario according to the target power consumption scenario and the data type corresponding to the target power consumption scenario comprises: acquiring part or all of the target data from the user intention and / or the device sensing information according to the target power consumption scenario and the data type corresponding to the target power consumption scenario; and / or in response to the user intention and the device sensing information not containing at least part of the target data, outputting prompt information related to the at least part of the data, and determining the at least part of the data according to a response to the prompt information.

6. The method of claim 3, wherein, The management of at least one of the power generation equipment, the energy storage equipment, and the power consumption equipment connected to the energy scheduling and management system according to the energy scheduling parameter comprises: determining an energy scheduling strategy according to the energy scheduling parameter and a power consumption prediction result, the power consumption prediction result including a load prediction result; managing at least one of the power generation equipment, the energy storage equipment, and the power consumption equipment connected to the energy scheduling and management system according to the energy scheduling strategy.

7. The method of claim 6, wherein, The determination of the energy scheduling strategy according to the energy scheduling parameter and the power consumption prediction result comprises: adjusting the load prediction result and / or adjusting a scheduling target of the energy scheduling and management system according to the energy scheduling parameter.

8. The method of claim 3, wherein, The correspondence between the data type corresponding to the target power consumption scenario and the target power consumption scenario is pre-established in the preset scenario case library.

9. The method of any one of claims 1 or 2, wherein, The method further includes: According to the actual power consumption data of the target power consumption scenario, updating the preset scenario case library.

10. An energy dispatch management apparatus, characterized by comprising: Comprise: An intention recognition module, configured to receive natural language power consumption scenario information and recognize user intention; A scenario determination module, configured to determine a target power consumption scenario according to the user intention, received device sensing information and a preset scenario case library; A scheduling execution module, configured to schedule and manage at least one of a power generation device, an energy storage device and a power consumption device connected to the energy scheduling and management apparatus according to the target power consumption scenario.

11. A microgrid system, characterized by, Comprise: A power generation device, configured to provide electric energy to the micro-grid system; An energy storage device, connected to the power generation device, configured to store or release electric energy; A power consumption device, connected to the power generation device and the energy storage device, configured to consume electric energy; A control apparatus, in communication connection with the power generation device, the energy storage device and the power consumption device, configured to execute the energy scheduling and management method according to any one of claims 1 to 10.

12. An energy management system, characterized by Comprise: A memory, configured to store program instructions; A processor, configured to execute the program instructions to execute the method according to any one of claims 1 to 10.

Images