Processing method and system based on smart energy unit

Abstract

The embodiment of the invention provides a processing method and system based on a smart energy unit, and belongs to the technical field of smart energy. The method comprises the following steps: acquiring real-time electricity consumption data through an intelligent electric meter, acquiring real-time environment data through sensor equipment, and acquiring a real-time equipment state through remote monitoring equipment; inputting the real-time electricity consumption data, the real-time environment data and the real-time equipment state into an energy demand prediction model to obtain real-time predicted energy demand data; the real-time predicted energy demand data comprises a first predicted power generation amount of photovoltaic power generation equipment, a second predicted power generation amount of wind power generation equipment and a predicted energy demand; generating a real-time energy scheduling strategy according to the first predicted generating capacity, the second predicted generating capacity and the predicted energy demand; and executing energy scheduling processing according to the real-time energy distribution strategy so as to adjust the first power generation amount of the photovoltaic power generation equipment, the second power generation amount of the wind power generation equipment and the charging and discharging amount of the energy storage equipment. Therefore, energy utilization rate and power generation efficiency are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of smart energy technology, and in particular to a processing method and system based on a smart energy unit. Background Art

[0002] With the acceleration of industrialization and the development of social economy, industrial parks have become one of the important economic growth points. In modern industrial parks, the efficiency and flexibility of energy management systems are key factors in improving productivity and reducing operating costs.

[0003] Traditional energy management methods usually rely on manual operations and fixed scheduling strategies, resulting in a slow response to real-time changes in energy demand. This approach is not only unable to effectively cope with the energy demand fluctuations of different production lines and equipment in the park, but may also cause energy waste and additional operating costs.

[0004] In order to solve the above problems, smart energy units are applied. By applying smart energy units in industrial parks, industrial parks can be assisted to achieve more efficient, environmentally friendly and economical energy use. However, although the application of smart energy units is becoming more and more extensive, they still face many challenges in practical applications. For example, multiple types of energy, such as solar energy and wind energy, need to coexist and work together in a system. How to manage these energy sources well and make them work better has become an urgent problem to be solved. Summary of the invention

[0005] The present invention provides a processing method and system based on smart energy units to dynamically adjust the operation strategies of photovoltaic power generation, wind power generation and energy storage equipment, reduce energy waste and unnecessary cost expenditure. At the same time, it can ensure that the output of power generation equipment (photovoltaic and wind power) and energy storage equipment matches the demand, thereby maximizing the use of renewable energy (such as solar energy and wind energy) and reducing dependence on traditional energy.

[0006] In a first aspect, the present invention provides a processing method based on a smart energy unit, which is applied to the smart energy unit. The smart energy unit includes an energy storage device management module, a wind power generation device management module, a photovoltaic power generation device management module, a smart meter, a sensor device and a remote device. The method includes:

[0007] Obtain real-time electricity consumption data through smart meters, real-time environmental data through sensor devices, and real-time device status through remote monitoring devices;

[0008] Inputting real-time electricity consumption data, real-time environmental data, and real-time equipment status into an energy demand prediction model to obtain real-time predicted energy demand data; wherein the energy demand prediction model is a mathematical model for real-time prediction of energy demand obtained after training based on historical electricity consumption data, historical environmental data, and historical equipment status; the real-time predicted energy demand data includes a first predicted power generation of a photovoltaic power generation device, a second predicted power generation of a wind power generation device, and predicted energy demand;

[0009] generating a real-time energy dispatching strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand;

[0010] Energy scheduling processing is performed according to the real-time energy allocation strategy to adjust the first power generation of the photovoltaic power generation equipment, the second power generation of the wind power generation equipment, and the charge and discharge amount of the energy storage device.

[0011] In a possible design of the first aspect, the training process of the energy demand prediction model includes:

[0012] Obtain historical electricity consumption data, historical environmental data, and historical equipment status;

[0013] Determine a training data set for training an initial prediction model and a verification data set for verifying the performance of the energy demand prediction model based on historical electricity consumption data, historical environmental data, and historical equipment status;

[0014] The initial prediction model is trained according to the training data in the training data set to obtain the predicted power consumption data;

[0015] Determine the loss function value based on the historical electricity consumption data and the predicted electricity consumption data;

[0016] The parameters of the initial prediction model are adjusted according to the loss function value, and the process of training the initial prediction model according to the training data in the training data set is repeated until the convergence condition is reached to obtain the energy demand prediction model.

[0017] In a possible design of the first aspect, determining the loss function value according to the historical power consumption data and the predicted power consumption data includes:

[0018] According to the formula Calculate the loss function value M;

[0019] Where n represents the number of training data in the training data set, y i represents the historical electricity consumption data of the i-th training data, Represents the predicted electricity consumption data of the i-th training data.

[0020] In a possible design of the first aspect, determining a training data set for training an initial prediction model and a verification data set for verifying the performance of an energy demand prediction model based on historical electricity consumption data, historical environmental data, and historical equipment status includes:

[0021] Extracting power consumption characteristics corresponding to historical power consumption data, environmental characteristics corresponding to historical environmental data, and status characteristics corresponding to historical equipment status respectively;

[0022] According to the preset sequence length, the power consumption characteristics, environmental characteristics and state characteristics are used to obtain training sequence data;

[0023] According to the set proportion, the training sequence data is divided into a training data set and a verification data set; wherein the number of training data in the training data set accounts for 80% of the training sequence data, and the number of verification data in the verification data set accounts for 20% of the training sequence data.

[0024] In a possible design of the first aspect, generating a real-time energy dispatch strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand includes:

[0025] When it is determined that the sum of the first predicted power generation and the second predicted power generation is less than the predicted energy demand, determining a discharge amount of the energy storage device;

[0026] According to the determined discharge amount of the energy storage device, the first power generation amount and power generation period of the photovoltaic power generation device, the second power generation amount and power generation period of the wind power generation device, and the discharge amount and discharge period of the energy storage device are determined respectively.

[0027] In a possible design of the first aspect, generating a real-time energy dispatch strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand includes:

[0028] When it is determined that the sum of the first predicted power generation and the second predicted power generation is greater than or equal to the predicted energy demand, the first power generation and power generation period of the photovoltaic power generation equipment are determined, and the second power generation and power generation period of the wind power generation equipment are determined.

[0029] In a possible design of the first aspect, the method further includes:

[0030] Based on the first predicted power generation, the second predicted power generation and the predicted energy demand, a suggestion for using electrical equipment is sent to the user.

[0031] In a second aspect, the present invention provides a processing system based on a smart energy unit, which is applied to the smart energy unit. The smart energy unit includes an energy storage device management module, a wind power generation device management module, a photovoltaic power generation device management module, a smart meter, a sensor device and a remote device. The system includes:

[0032] Real-time data acquisition module, used to obtain real-time power consumption data through smart meters, real-time environmental data through sensor devices, and real-time device status through remote monitoring devices;

[0033] A prediction module is used to input real-time power consumption data, real-time environmental data, and real-time equipment status into an energy demand prediction model to obtain real-time predicted energy demand data; wherein the energy demand prediction model is a mathematical model for real-time prediction of energy demand obtained after training based on historical power consumption data, historical environmental data, and historical equipment status; the real-time predicted energy demand data includes a first predicted power generation of a photovoltaic power generation device, a second predicted power generation of a wind power generation device, and predicted energy demand;

[0034] A strategy generation module, used for generating a real-time energy dispatch strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand;

[0035] The adjustment module is used to perform energy scheduling processing according to the real-time energy allocation strategy to adjust the first power generation of the photovoltaic power generation equipment, the second power generation of the wind power generation equipment and the charge and discharge amount of the energy storage device.

[0036] In a possible design of the first aspect, the strategy generation module is specifically used to:

[0037] When it is determined that the sum of the first predicted power generation and the second predicted power generation is less than the predicted energy demand, determining a discharge amount of the energy storage device;

[0038] According to the determined discharge amount of the energy storage device, respectively determine the first power generation amount and power generation period of the photovoltaic power generation device, the second power generation amount and power generation period of the wind power generation device, and the discharge amount and discharge period of the energy storage device; or,

[0039] When it is determined that the sum of the first predicted power generation and the second predicted power generation is greater than or equal to the predicted energy demand, the first power generation and power generation period of the photovoltaic power generation equipment are determined, and the second power generation and power generation period of the wind power generation equipment are determined.

[0040] In a possible design of the first aspect, the system further includes:

[0041] The power usage suggestion module is used to send power equipment usage suggestions to the user according to the first predicted power generation, the second predicted power generation and the predicted energy demand.

[0042] In a third aspect, the present invention provides an electronic device, comprising:

[0043] processor; and,

[0044] A memory for storing executable instructions of the processor;

[0045] Wherein, the processor is configured to perform any method in the first aspect by executing executable instructions.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement any one of the methods in the first aspect.

[0047] The processing method and system based on the smart energy unit provided by the present invention can dynamically adjust the operation strategy of photovoltaic power generation, wind power generation and energy storage equipment by acquiring power consumption data, environmental data and equipment status in real time, and combining the energy demand prediction model obtained by training based on historical data for prediction. This real-time optimization makes energy use more efficient and can reduce energy waste and unnecessary cost expenditure. In addition, the energy demand prediction model can provide accurate energy demand predictions to ensure that the output and demand of power generation equipment (photovoltaic and wind power) and energy storage equipment match, thereby maximizing the use of renewable energy (such as solar energy and wind energy) and reducing dependence on traditional energy. Real-time energy scheduling strategies can quickly respond to changes in electricity demand and changes in environmental conditions. In addition, the working status of photovoltaic power generation, wind power generation and energy storage equipment can be automatically adjusted according to the predicted energy demand, making the entire energy system more flexible and adaptable. Accurate energy scheduling can ensure that each energy device (including photovoltaic, wind power generation and energy storage equipment) operates in the optimal state. This not only improves the operating efficiency of the equipment, but also extends the service life of the equipment. Through scientific prediction and optimized scheduling, the system can effectively reduce overproduction and waste of energy, thereby reducing overall energy consumption and improving the economy and environmental protection of energy use. It realizes intelligent monitoring and management of energy systems, uses advanced sensor equipment and remote equipment to obtain and analyze data in real time, makes energy management more intelligent and automated, and reduces the need for manual intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present invention and, together with the description, serve to explain the principles of the embodiments of the present invention.

[0049] Figure 1 It is a structural diagram of the smart energy unit;

[0050] Figure 2 A flowchart of a processing method based on a smart energy unit provided by an embodiment of the present invention is shown;

[0051] Figure 3 A schematic diagram of the structure of a processing system based on a smart energy unit provided in an embodiment of the present invention is shown;

[0052] Figure 4 A schematic diagram showing the structure of another processing system based on a smart energy unit provided in an embodiment of the present invention is shown;

[0053] Figure 5 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present invention.

[0054] The above drawings have shown specific embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the embodiments of the present invention in any way, but to illustrate the concepts of the embodiments of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0055] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present invention as detailed in the appended claims.

[0056] First, the terms involved in the embodiments of the present invention are explained:

[0057] Smart energy unit: usually refers to one or a group of devices, systems or technologies that can achieve automated and intelligent management in smart grids, distributed energy systems or microgrids. These units may include but are not limited to solar photovoltaic panels, wind turbines, energy storage devices (such as batteries), smart meters, energy management systems, etc.

[0058] In modern industrial parks, the efficiency and flexibility of energy management systems are key factors in improving productivity and reducing operating costs. Traditional energy management methods usually rely on manual operations and fixed scheduling strategies, resulting in slow response to real-time changes in energy demand. This approach not only cannot effectively cope with the energy demand fluctuations of different production lines and equipment in the park, but may also cause energy waste and additional operating costs.

[0059] Traditional energy management methods usually rely on manual operations and fixed scheduling strategies, resulting in a slow response to real-time changes in energy demand. This approach is not only unable to effectively cope with the energy demand fluctuations of different production lines and equipment in the park, but may also cause energy waste and additional operating costs.

[0060] Specifically, the problems with traditional energy management methods mainly include:

[0061] Mismatch between energy supply and demand: Due to the lack of effective forecasting methods, it is difficult to accurately predict energy demand, resulting in energy supply surplus or shortage from time to time.

[0062] Low equipment utilization: Energy equipment is not operating efficiently, especially during periods of low load, when equipment is often operating inefficiently.

[0063] Lack of intelligent scheduling: Traditional energy management systems rely on manual intervention for scheduling and cannot automatically adjust according to real-time conditions, reducing the flexibility of the system.

[0064] The phenomenon of data silos is serious: the lack of an effective data exchange mechanism between different energy systems leads to a serious phenomenon of information silos, making it difficult to achieve overall optimization of energy management.

[0065] In order to solve the above problems, smart energy units are applied. By applying smart energy units in industrial parks, industrial parks can be assisted to achieve more efficient, environmentally friendly and economical energy use. However, although the application of smart energy units is becoming more and more extensive, they still face many challenges in practical applications. For example, multiple types of energy, such as solar energy and wind energy, need to coexist and work together in a system. How to manage these energy sources well and make them work better has become an urgent problem to be solved.

[0066] Therefore, in order to solve the above problems, it is necessary to propose an improved processing system based on smart energy units to dynamically adjust the operation strategies of photovoltaic power generation, wind power generation and energy storage equipment, reduce energy waste and unnecessary cost expenditure. At the same time, it can ensure that the output of power generation equipment (photovoltaic and wind power) and energy storage equipment matches the demand, thereby maximizing the use of renewable energy (such as solar and wind energy) and reducing dependence on traditional energy.

[0067] The embodiments of the present invention are intended to solve the problems existing in the above-mentioned prior art. Specifically, the concepts of the embodiments of the present invention are developed around the following core points:

[0068] Real-time data collection: Various types of data are collected in real time through smart meters, sensor devices and remote devices.

[0069] Data processing and analysis: Through the pre-trained energy demand prediction model, the real-time energy demand is predicted based on the collected real-time data to obtain real-time predicted energy demand data.

[0070] Intelligent scheduling: Generate real-time energy scheduling strategies based on the predicted real-time energy demand data.

[0071] Dynamic adjustment: According to the real-time energy dispatch strategy, the power generation equipment (wind power and photovoltaic) and energy storage equipment are dispatched.

[0072] Interaction with users: Based on real-time forecasts of energy demand, recommendations on the use of electrical equipment are sent to users.

[0073] In summary, the concept of the embodiment of the present invention is to obtain power consumption data, environmental data and equipment status in real time, and to predict the energy demand prediction model obtained by training based on historical data, so as to realize dynamic adjustment of the operation strategy of photovoltaic power generation, wind power generation and energy storage equipment. This real-time optimization makes energy use more efficient and can reduce energy waste and unnecessary cost expenditure. In addition, the energy demand prediction model can provide accurate energy demand prediction to ensure that the output and demand of power generation equipment (photovoltaic and wind power) and energy storage equipment match, so as to maximize the use of renewable energy (such as solar energy and wind power) and reduce dependence on traditional energy. Real-time energy scheduling strategy can quickly respond to changes in electricity demand and changes in environmental conditions. In addition, the working state of photovoltaic power generation, wind power generation and energy storage equipment can be automatically adjusted according to the predicted energy demand, making the entire energy system more flexible and adaptable. Accurate energy scheduling can ensure that each energy device (including photovoltaic, wind power generation and energy storage equipment) operates in the optimal state. This not only improves the operating efficiency of the equipment, but also extends the service life of the equipment. Through scientific prediction and optimized scheduling, the system can effectively reduce the overproduction and waste of energy, thereby reducing overall energy consumption and improving the economy and environmental protection of energy use. It realizes intelligent monitoring and management of energy systems, uses advanced sensor equipment and remote devices to acquire and analyze data in real time, makes energy management more intelligent and automated, and reduces the need for human intervention.

[0074] The structure of the smart energy unit involved in the embodiment of the present invention is briefly described below. Figure 1 Figure 1 is a schematic diagram of the structure of the smart energy unit. Figure 1 As shown, the smart energy unit 100 may include a data acquisition module 110 , a data processing and analysis module 120 , an intelligent decision-making and scheduling module 130 , a user interaction module 140 and an execution module 150 .

[0075] The data acquisition module 110 may include a smart meter for measuring power consumption, a sensor device for monitoring environmental parameters (such as temperature, humidity, and light intensity), and a remote module for monitoring device status.

[0076] The data processing and analysis module 120 may include a machine learning unit and a data visualization tool. The machine learning unit is used to train the energy demand prediction model using historical data and output real-time predicted energy demand data based on the real-time data of the data acquisition module. The data visualization tool is used to display energy usage to managers through charts, dashboards, etc.

[0077] The intelligent decision-making and scheduling module 130 can dynamically generate real-time energy scheduling strategies based on real-time predicted energy demand data to achieve scheduling of power generation equipment (wind and photovoltaic) and energy storage equipment.

[0078] The user interaction module 140 includes a mobile application / web interface and a smart terminal. The mobile application / web interface is used to provide users with an interface for viewing energy usage and setting usage preference information. The smart terminal may include smart sockets, smart lighting equipment, smart thermostats, etc., so as to control the energy consumption of electrical equipment.

[0079] The execution module 150 may include an intelligent actuator and an energy storage device, wherein the intelligent actuator is used to execute the scheduling of power generation equipment (wind power and photovoltaic power) and energy storage equipment, such as controlling the working state of the equipment, etc. The energy storage device is used to store clean energy for emergency use.

[0080] The processing method and system based on the smart energy unit provided by the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0081] Figure 2 FIG. 1 is a flowchart of a processing method based on a smart energy unit provided by an embodiment of the present invention. Figure 2 As shown, the processing method based on the smart energy unit provided in the embodiment of the present invention is applied to Figure 1 The smart energy unit shown in the figure, in this embodiment, the smart energy unit also includes energy storage equipment, wind power generation equipment, photovoltaic power generation equipment, smart meters, sensor equipment and remote equipment. The method includes the following steps:

[0082] 2100. Obtain real-time electricity consumption data through smart meters, obtain real-time environmental data through sensor devices, and obtain real-time device status through remote monitoring devices.

[0083] 2200. Input the real-time electricity consumption data, the real-time environmental data, and the real-time equipment status into the energy demand prediction model to obtain the real-time predicted energy demand data.

[0084] 2300. Generate a real-time energy scheduling strategy based on the first predicted power generation, the second predicted power generation and the predicted energy demand.

[0085] 2400. Perform energy scheduling processing according to the real-time energy allocation strategy to adjust the first power generation of the photovoltaic power generation equipment, the second power generation of the wind power generation equipment, and the charge and discharge capacity of the energy storage device.

[0086] Among them, the sensor equipment may include temperature sensors, humidity sensors, light sensors, anemometers, etc. The real-time equipment status may include the status and performance of photovoltaic power generation equipment, wind power generation equipment, and energy storage equipment.

[0087] After obtaining real-time power consumption data, real-time environmental data, and real-time equipment status, the energy demand prediction model predicts the energy demand data based on the real-time power consumption data, real-time environmental data, and real-time equipment status to obtain real-time predicted energy demand data. The real-time predicted energy demand data includes the first predicted power generation of the photovoltaic power generation equipment, the second predicted power generation of the wind power generation equipment, and the predicted energy demand.

[0088] The energy demand prediction model is a mathematical model for real-time prediction of energy usage demand obtained through training based on historical electricity consumption data, historical environmental data, and historical equipment status.

[0089] Specifically, after obtaining historical power consumption data, historical environmental data, and historical equipment status, data cleaning and feature selection are first performed on the historical power consumption data, historical environmental data, and historical equipment status, respectively extracting power consumption features corresponding to the historical power consumption data, environmental features corresponding to the historical environmental data, and state features corresponding to the historical equipment status. Afterwards, feature scaling is performed on the power consumption features, environmental features, and state features so that the feature bases have zero mean and unit variance.

[0090] Since it is necessary to capture the long-term dependency of time series data in this embodiment, after completing the feature scaling process, the power consumption features, environmental features and state features are combined to obtain training sequence data according to the preset sequence length. The preset sequence length is configured as the number of hours in a day, that is, the preset sequence length is 24. In some other implementations, the sequence length can also be configured according to actual usage requirements, which is not limited here.

[0091] Afterwards, the training sequence data is divided into a training data set and a verification data set according to the set ratio. In this embodiment, the number of training data in the training data set accounts for 80% of the training sequence data, and the number of verification data in the verification data set accounts for 20% of the training sequence data.

[0092] After obtaining the training data set and the validation data set, the initial prediction model is trained according to the training data set, and the performance of the energy demand prediction model is verified according to the validation data set.

[0093] Specifically, the initial prediction model is trained according to the training data in the training data set to obtain the predicted power consumption data. The loss function value is determined according to the historical power consumption data and the predicted power consumption data. The parameters of the initial prediction model are adjusted according to the loss function value, and the initial prediction model is repeatedly trained according to the training data in the training data set until the convergence condition is reached to obtain the energy demand prediction model. The convergence condition may be reaching a specified training cycle, or the loss function value may reach a set value.

[0094] Among them, the calculation formula of the loss function value can be: Calculate the loss function value M; where n represents the number of training data in the training data set, y i represents the historical electricity consumption data of the i-th training data, Represents the predicted electricity consumption data of the i-th training data. This loss function calculation method can well reflect the difference between historical electricity consumption data and predicted electricity consumption data, and help the model pay more attention to larger errors during the training process. In energy demand forecasting, large errors may lead to insufficient or excessive energy supply. Therefore, this is very important for energy demand forecasting.

[0095] When verifying the performance of the energy demand prediction model based on the verification data set, for each verification data in the verification data set, the verification data is input into the trained energy demand prediction model to obtain the predicted electricity consumption data, and the average square difference between the predicted electricity consumption data and the historical electricity consumption data in the verification data is calculated.

[0096] After obtaining the mean square difference corresponding to each validation data, the average of multiple mean square differences is calculated. If the average value is less than the set threshold, it means that the performance of the energy demand prediction model is good and has good generalization ability. If the average value is greater than or equal to the set threshold, it means that the performance of the energy demand prediction model is poor, and further adjustment of model parameters or modification of features used for training is required.

[0097] Next, a real-time energy dispatching strategy can be generated based on the energy demand prediction model. Specifically, it is first necessary to determine the relationship between the sum of the first predicted power generation and the second predicted power generation and the predicted energy demand, and then generate a real-time energy dispatching strategy based on the relationship between the sum of the first predicted power generation and the second predicted power generation and the predicted energy demand.

[0098] Among them, when it is determined that the sum of the first predicted power generation and the second predicted power generation is less than the predicted energy demand, it means that the predicted power generation cannot meet the predicted energy demand. At this time, the energy storage device needs to discharge to make up for the gap in energy demand. Then the difference between the predicted energy demand and the sum of the first predicted power generation and the second predicted power generation can be determined as the discharge amount of the energy storage device. Furthermore, according to the determined discharge amount of the energy storage device, the first power generation and power generation period of the photovoltaic power generation device, the second power generation and power generation period of the wind power generation device, and the discharge amount and discharge period of the energy storage device can be determined respectively.

[0099] When it is determined that the sum of the first predicted power generation and the second predicted power generation is greater than or equal to the predicted energy demand, it means that the predicted power generation is sufficient, and clean energy (light energy and wind energy) can be used preferentially, and then the first power generation and power generation period of the photovoltaic power generation equipment are determined, and the second power generation and power generation period of the wind power generation equipment are determined. In practical applications, if the power generation of clean energy far exceeds the predicted energy demand, it can be considered to store the excess power generation in energy storage equipment or sell it to the power grid.

[0100] For example, suppose it is predicted that the power generation of photovoltaic power generation equipment and wind power generation equipment is higher during the day and lower at night, and it is predicted that there will be a peak in energy demand at night. The generated real-time energy scheduling strategy can be divided into daytime charging and discharging plans and nighttime charging and discharging plans:

[0101] Among them, for the daytime charging and discharging plan, assuming that the first predicted power generation of the photovoltaic power generation equipment is 70KWh and the second predicted power generation of the wind power generation equipment is 80KWh, the sum of the first predicted power generation and the second predicted power generation is 150KWh, and the predicted energy demand during the day is 100KWh. It is determined that the photovoltaic power generation equipment and the wind power generation equipment will charge the energy storage equipment during the day (such as 9:00-17:00), and it is estimated that about 50KWh of electricity can be stored. At the same time, the first power generation of the photovoltaic power generation equipment is adjusted to 50KWh, and the second power generation of the wind power generation equipment is adjusted to 50KWh.

[0102] For the night charging and discharging plan, assuming that the first predicted power generation of the photovoltaic power generation equipment is 10KWH and the second predicted power generation of the wind power generation equipment is 40KWH, the sum of the first predicted power generation and the second predicted power generation is 50KWh, and the predicted energy demand at night is 150KWH, then it is determined that the energy storage device discharges 100KWh to supplement the energy gap caused by insufficient power generation of the photovoltaic power generation equipment and the wind power generation equipment.

[0103] Therefore, by dynamically adjusting the operating strategies of photovoltaic power generation, wind power generation and energy storage equipment, energy waste and unnecessary cost expenditure can be reduced. At the same time, it can ensure that the output of power generation equipment (photovoltaic and wind power) and energy storage equipment matches the demand, maximize the use of clean energy and reduce dependence on traditional energy.

[0104] Furthermore, based on the above embodiment, the method of this embodiment can also send suggestions for the use of electrical equipment to the user based on the first predicted power generation, the second predicted power generation and the predicted energy demand. For example, energy-saving and emission-reduction suggestions can be sent to the user through an application, such as using high-power electrical appliances during periods when the power generation of clean energy is sufficient. For another example, when the power generation of clean energy is insufficient, adjust the lighting brightness, lower the air-conditioning temperature, turn off non-essential equipment, etc. This is to encourage users to take energy-saving measures on their own initiative to achieve energy conservation and emission reduction.

[0105] In summary, the technical solution provided in this embodiment can dynamically adjust the operation strategy of photovoltaic power generation, wind power generation and energy storage equipment by acquiring power consumption data, environmental data and equipment status in real time, and combining the energy demand prediction model obtained by training based on historical data for prediction. This real-time optimization makes energy use more efficient and can reduce energy waste and unnecessary cost expenditure. In addition, the energy demand prediction model can provide accurate energy demand predictions to ensure that the output and demand of power generation equipment (photovoltaic and wind power) and energy storage equipment match, thereby maximizing the use of renewable energy (such as solar energy and wind power) and reducing dependence on traditional energy. Real-time energy scheduling strategies can quickly respond to changes in electricity demand and changes in environmental conditions. In addition, the working status of photovoltaic power generation, wind power generation and energy storage equipment can be automatically adjusted according to the predicted energy demand, making the entire energy system more flexible and adaptable. Accurate energy scheduling can ensure that each energy device (including photovoltaic, wind power generation and energy storage equipment) operates in the optimal state. This not only improves the operating efficiency of the equipment, but also extends the service life of the equipment. Through scientific prediction and optimized scheduling, the system can effectively reduce the overproduction and waste of energy, thereby reducing overall energy consumption and improving the economy and environmental protection of energy use. It realizes intelligent monitoring and management of energy systems, uses advanced sensor equipment and remote devices to acquire and analyze data in real time, makes energy management more intelligent and automated, and reduces the need for human intervention.

[0106] Figure 3 The schematic diagram of the structure of a processing system 300 based on a smart energy unit provided by an embodiment of the present invention is shown. This embodiment is applied to a smart energy unit, and the smart energy unit includes energy storage equipment, wind power generation equipment, photovoltaic power generation equipment, smart meters, sensor equipment and remote equipment. Figure 3 As shown, the processing system 300 based on the smart energy unit of this embodiment may include:

[0107] The real-time data acquisition module 310 is used to obtain real-time power consumption data through smart meters, obtain real-time environmental data through sensor devices, and obtain real-time device status through remote monitoring devices.

[0108] The prediction module 320 is used to input the real-time electricity consumption data, real-time environmental data, and real-time equipment status into the energy demand prediction model to obtain real-time predicted energy demand data; wherein the energy demand prediction model is a mathematical model for real-time prediction of energy usage demand obtained after training based on historical electricity consumption data, historical environmental data, and historical equipment status; the real-time predicted energy demand data includes the first predicted power generation of the photovoltaic power generation equipment, the second predicted power generation of the wind power generation equipment, and the predicted energy demand.

[0109] The strategy generation module 330 is used to generate a real-time energy scheduling strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand.

[0110] The adjustment module 340 is used to perform energy scheduling processing according to the real-time energy allocation strategy to adjust the first power generation of the photovoltaic power generation equipment, the second power generation of the wind power generation equipment and the charge and discharge amount of the energy storage device.

[0111] Among them, when training the energy demand prediction model, the prediction module 320 obtains historical power consumption data, historical environmental data, and historical equipment status, performs data cleaning and feature selection on the historical power consumption data, historical environmental data, and historical equipment status, and extracts the power consumption features corresponding to the historical power consumption data, the environmental features corresponding to the historical environmental data, and the state features corresponding to the historical equipment status. Afterwards, the power consumption features, environmental features, and state features are feature scaled so that the feature bases have zero mean and unit variance.

[0112] Afterwards, the prediction module 320 obtains training sequence data based on the power consumption characteristics, environmental characteristics and state characteristics according to the preset sequence length. The training sequence data is divided into a training data set and a verification data set according to the set proportion. In this embodiment, the number of training data in the training data set accounts for 80% of the training sequence data, and the number of verification data in the verification data set accounts for 20% of the training sequence data.

[0113] After obtaining the training data set and the validation data set, the initial prediction model is trained according to the training data set, and the performance of the energy demand prediction model is verified according to the validation data set.

[0114] Specifically, the initial prediction model is trained according to the training data in the training data set to obtain the predicted power consumption data. The loss function value is determined according to the historical power consumption data and the predicted power consumption data. The parameters of the initial prediction model are adjusted according to the loss function value, and the initial prediction model is repeatedly trained according to the training data in the training data set until the convergence condition is reached to obtain the energy demand prediction model. The convergence condition may be reaching a specified training cycle, or the loss function value may reach a set value.

[0115] Among them, the calculation formula of the loss function value can be: Calculate the loss function value M; where n represents the number of training data in the training data set, y i represents the historical electricity consumption data of the i-th training data, Represents the predicted electricity consumption data of the i-th training data. This loss function calculation method can well reflect the difference between historical electricity consumption data and predicted electricity consumption data, and help the model pay more attention to larger errors during the training process. In energy demand forecasting, large errors may lead to insufficient or excessive energy supply. Therefore, this is very important for energy demand forecasting.

[0116] In a possible implementation, the strategy generation module 330 is specifically used to: when it is determined that the sum of the first predicted power generation and the second predicted power generation is less than the predicted energy demand, it means that the predicted power generation cannot meet the predicted energy demand, and the energy storage device needs to discharge to make up for the gap in energy demand. Then the difference between the predicted energy demand and the sum of the first predicted power generation and the second predicted power generation can be determined as the discharge amount of the energy storage device. Furthermore, according to the determined discharge amount of the energy storage device, the first power generation and power generation period of the photovoltaic power generation device, the second power generation and power generation period of the wind power generation device, and the discharge amount and discharge period of the energy storage device can be determined respectively.

[0117] In a possible implementation, the strategy generation module 330 is specifically used to: when it is determined that the sum of the first predicted power generation and the second predicted power generation is greater than or equal to the predicted energy demand, it means that the predicted power generation is sufficient, and clean energy (light energy and wind energy) can be used preferentially, and then the first power generation and power generation period of the photovoltaic power generation equipment are determined, and the second power generation and power generation period of the wind power generation equipment are determined. In practical applications, if the power generation of clean energy far exceeds the predicted energy demand, it can be considered to store the excess power generation in the energy storage device or sell it to the power grid.

[0118] The processing system 300 based on the smart energy unit of this embodiment can be used to implement the technical solution of the above method embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0119] Further, Figure 4 FIG. 3 is a schematic diagram showing a structure of another processing system 300 based on a smart energy unit provided by an embodiment of the present invention. Figure 4 As shown, the processing system 300 based on the smart energy unit of this embodiment may also include: an electricity usage suggestion module 350, which is used to send electricity equipment usage suggestions to the user based on the first predicted power generation, the second predicted power generation and the predicted energy demand.

[0120] The processing system 300 based on the smart energy unit of this embodiment can be used to implement the technical solution of the above method embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0121] Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present invention. Figure 5 As shown, an electronic device 500 provided in this embodiment includes: a processor 501 and a memory 502; wherein:

[0122] The memory 502 is used to store computer programs, and the memory may also be a flash memory.

[0123] The processor 501 is used to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the above method embodiment.

[0124] Optionally, the memory 502 may be independent or integrated with the processor 501 .

[0125] When the memory 502 is a device independent of the processor 501, the electronic device 500 may further include:

[0126] The bus 503 is used to connect the memory 502 and the processor 501 .

[0127] This embodiment also provides a computer-readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the above-mentioned various embodiments.

[0128] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device implements the methods provided in the above various embodiments.

[0129] Those skilled in the art will readily appreciate other implementations of the embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The embodiments of the present invention are intended to cover any variations, uses, or adaptations of the embodiments of the present invention that follow the general principles of the embodiments of the present invention and include common knowledge or customary technical means in the art that are not disclosed in the embodiments of the present invention. The specification and embodiments are to be regarded as exemplary only, and the true scope and spirit of the embodiments of the present invention are indicated by the claims.

[0130] It should be understood that the embodiments of the present invention are not limited to the precise structures described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the embodiments of the present invention is limited only by the appended claims.

Claims

1. A processing method based on a smart energy unit, applied to a smart energy unit, wherein the smart energy unit includes an energy storage device management module, a wind power generation device management module, a photovoltaic power generation device management module, a smart meter, a sensor device and a remote device, characterized in that: The method comprises: Acquire real-time electricity consumption data through the smart meter, acquire real-time environmental data through the sensor device, and acquire real-time device status through the remote monitoring device; Inputting the real-time power consumption data, the real-time environmental data, and the real-time device status into an energy demand prediction model to obtain real-time predicted energy demand data; wherein the energy demand prediction model is a mathematical model for real-time prediction of energy usage demand obtained after training based on historical power consumption data, historical environmental data, and historical device status; the real-time predicted energy demand data includes a first predicted power generation of the photovoltaic power generation equipment, a second predicted power generation of the wind power generation equipment, and predicted energy demand; generating a real-time energy dispatch strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand; Energy scheduling processing is performed according to the real-time energy allocation strategy to adjust the first power generation of the photovoltaic power generation equipment, the second power generation of the wind power generation equipment and the charge and discharge amount of the energy storage device.

2. The method according to claim 1, characterized in that The training process of the energy demand prediction model includes: Acquire the historical power consumption data, the historical environment data and the historical device status; Determining a training data set for training an initial prediction model and a verification data set for verifying the performance of the energy demand prediction model according to the historical power consumption data, the historical environmental data, and the historical equipment status; The initial prediction model is trained according to the training data in the training data set to obtain predicted power consumption data; Determining a loss function value according to the historical power consumption data and the predicted power consumption data; The parameters of the initial prediction model are adjusted according to the loss function value, and the process of training the initial prediction model according to the training data in the training data set is repeated until a convergence condition is reached to obtain the energy demand prediction model.

3. The method according to claim 2, characterized in that The determining of the loss function value according to the historical power consumption data and the predicted power consumption data includes: According to the formula Calculate the loss function value M; Where n represents the number of training data in the training data set, y i represents the historical electricity consumption data of the i-th training data, Represents the predicted electricity consumption data of the i-th training data.

4. The method according to claim 2, characterized in that: The step of determining a training data set for training an initial prediction model and a verification data set for verifying the performance of the energy demand prediction model according to the historical power consumption data, the historical environmental data, and the historical device status includes: Respectively extracting power consumption characteristics corresponding to the historical power consumption data, environmental characteristics corresponding to the historical environmental data, and state characteristics corresponding to the historical device state; According to a preset sequence length, the power consumption characteristics, the environmental characteristics and the state characteristics are used to obtain training sequence data; According to the set proportion, the training sequence data is divided into the training data set and the verification data set; wherein the amount of training data in the training data set accounts for 80% of the training sequence data, and the amount of verification data in the verification data set accounts for 20% of the training sequence data.

5. The method according to claim 1, characterized in that The generating a real-time energy dispatching strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand includes: When it is determined that the sum of the first predicted power generation and the second predicted power generation is less than the predicted energy demand, determining the discharge amount of the energy storage device; According to the determined discharge amount of the energy storage device, the first power generation amount and power generation period of the photovoltaic power generation device, the second power generation amount and power generation period of the wind power generation device, and the discharge amount and discharge period of the energy storage device are determined respectively.

6. The method according to claim 1, characterized in that The generating a real-time energy dispatching strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand includes: When it is determined that the sum of the first predicted power generation and the second predicted power generation is greater than or equal to the predicted energy demand, the first power generation and power generation period of the photovoltaic power generation equipment are determined, and the second power generation and power generation period of the wind power generation equipment are determined.

7. The method according to claim 1, characterized in that The method further comprises: Based on the first predicted power generation, the second predicted power generation and the predicted energy demand, a recommendation on the use of electrical equipment is sent to the user.

8. A processing system based on a smart energy unit, applied to a smart energy unit, wherein the smart energy unit includes an energy storage device management module, a wind power generation device management module, a photovoltaic power generation device management module, a smart meter, a sensor device and a remote device, characterized in that: The system comprises: A real-time data acquisition module, used to obtain real-time power consumption data through the smart meter, obtain real-time environmental data through the sensor device, and obtain real-time device status through the remote monitoring device; A prediction module, used for inputting the real-time power consumption data, the real-time environmental data, and the real-time device status into an energy demand prediction model to obtain real-time predicted energy demand data; wherein the energy demand prediction model is a mathematical model for real-time prediction of energy use demand obtained after training based on historical power consumption data, historical environmental data, and historical device status; the real-time predicted energy demand data includes a first predicted power generation of the photovoltaic power generation equipment, a second predicted power generation of the wind power generation equipment, and predicted energy demand; A strategy generation module, configured to generate a real-time energy scheduling strategy according to the first predicted power generation, the second predicted power generation and the predicted energy demand; The adjustment module is used to perform energy scheduling processing according to the real-time energy allocation strategy to adjust the first power generation of the photovoltaic power generation equipment, the second power generation of the wind power generation equipment and the charge and discharge amount of the energy storage device.

9. The system according to claim 8, characterized in that The strategy generation module is specifically used for: When it is determined that the sum of the first predicted power generation and the second predicted power generation is less than the predicted energy demand, determining the discharge amount of the energy storage device; According to the determined discharge amount of the energy storage device, respectively determine the first power generation amount and power generation period of the photovoltaic power generation device, the second power generation amount and power generation period of the wind power generation device, and the discharge amount and discharge period of the energy storage device; or, When it is determined that the sum of the first predicted power generation and the second predicted power generation is greater than or equal to the predicted energy demand, the first power generation and power generation period of the photovoltaic power generation equipment are determined, and the second power generation and power generation period of the wind power generation equipment are determined.

10. The system according to claim 8, characterized in that The system further comprises: The electricity usage suggestion module is used to send electricity equipment usage suggestions to the user according to the first predicted power generation, the second predicted power generation and the predicted energy demand.

Images