CN118074124A

CN118074124A - Electric energy management method and device

Info

Publication number: CN118074124A
Application number: CN202410437222.3A
Authority: CN
Inventors: 黄山; 谭海锋
Original assignee: Guangzhou Rimsea Technology Co ltd
Current assignee: Guangzhou Rimsea Technology Co ltd
Priority date: 2024-04-12
Filing date: 2024-04-12
Publication date: 2024-05-24

Abstract

The application provides an electric energy management method and device, which are applied to a renewable energy system, wherein the method predicts the predicted electricity consumption and the predicted electricity price of a user in a target electricity consumption period; predicting a predicted power generation amount of the renewable energy system in the target power utilization period based on first influence factor data of a plurality of kinds of influence power generation amounts of the renewable energy system; and determining a target electric energy management strategy for enabling the predicted electric charge of the target electricity consumption period to accord with the preset electric charge condition based on the predicted electric energy generation amount, the predicted electric energy consumption amount and the predicted electric charge price of the target electricity consumption period, controlling the operation of the renewable energy source system and the power grid system in the target electricity consumption period based on the target electric energy management strategy, reasonably distributing the electric energy generated by the renewable energy source system and reasonably using the power grid electric energy, thereby reducing electric energy waste and reducing the total electric charge price of users.

Description

Electric energy management method and device

Technical Field

The application relates to the technical field of new energy, in particular to an electric energy management method and device.

Background

With the increasing demands for global energy crisis and environmental protection, there is an increasing need for efficient and sustainable energy utilization. Conventional energy management systems often cannot flexibly adapt to power price fluctuations and user actual demands, resulting in energy waste and cost rise, for example, renewable energy is used when the power price is low, and grid power is used when the power price is high, resulting in power cost rise.

Disclosure of Invention

Therefore, the application aims to provide an electric energy management method and device, which are used for reasonably distributing electric energy generated by a renewable energy system and reasonably using electric power of a power grid, so that electric energy waste is reduced, and the total electricity price of a user is reduced.

The embodiment of the application provides an electric energy management method which is applied to a renewable energy system, and comprises the following steps:

predicting predicted electricity consumption and predicted electricity price of a user in a target electricity consumption period;

Predicting a predicted power generation amount of the renewable energy system in the target power utilization period based on first influence factor data of a plurality of kinds of influence power generation amounts of the renewable energy system;

Determining a target electric energy management strategy for enabling the predicted electric charge of the target electric use period to accord with a preset electric charge condition based on the predicted electric energy generation amount, the predicted electric energy consumption amount and the predicted electric price of the target electric use period; the target electric energy management strategy comprises a first electric energy use strategy of the renewable energy system and a second electric energy use strategy of the power grid.

In some embodiments, in the power management method, the predicting the predicted power consumption of the user in the target power consumption period includes:

Acquiring actual power consumption and meteorological data of a user in a first historical power consumption period and meteorological data in a target power consumption period from a first target database based on a preconfigured first interface; wherein the first historical electricity usage period is determined based on a target electricity usage period;

Inputting the actual power consumption, the meteorological data and the meteorological data in the target power consumption period into a pre-trained power consumption prediction model; the electricity consumption prediction model is trained based on a first training set constructed by historical electricity consumption of a user and meteorological data corresponding to the historical electricity consumption;

And the electricity consumption prediction model processes the actual electricity consumption in the first historical electricity consumption period, the meteorological data and the meteorological data in the target electricity consumption period, and determines the predicted electricity consumption of the target electricity consumption period of the user.

In some embodiments, the power management method, the predicting the predicted power price of the user in the target power utilization period includes:

acquiring actual electricity prices in a second historical electricity utilization period from a second target database based on a second interface which is configured in advance; wherein the second historical electricity usage period is determined based on a target electricity usage period;

Converting the actual electricity rates in the second historical electricity use period into standardized electricity rate features based on the maximum actual electricity rates, the minimum actual electricity rates and the standard electricity rates in the second historical electricity use period;

Inputting the standardized electricity price characteristics in the second historical electricity consumption period into a pre-trained electricity price prediction model; the electricity price prediction model is trained based on a second training set constructed by historical electricity price;

and the electricity price prediction model processes the standardized electricity price characteristics in the second historical electricity use period and determines the predicted electricity price of the target electricity use period.

In some embodiments, in the electric energy management method, the predicting the predicted electric energy generation amount of the renewable energy system in the target electric energy utilization period is based on first influence factor data that affects the electric energy generation amount of the renewable energy system; comprising the following steps:

acquiring first influence factor data of various kinds of influence on the power generation capacity of a renewable energy system in a target power utilization period; wherein the first influence factor data includes: geographic location data, terrain feature data, meteorological data;

Inputting the data of the plurality of first influence factors into a pre-constructed power generation amount prediction model; the power generation amount prediction model is constructed based on historical first influence factor data and configuration information of the renewable energy system;

and the power generation amount prediction model processes the plurality of first influence factor data and configuration information of the renewable energy system, and predicts the predicted power generation amount of the renewable energy system in the target power utilization period.

In some embodiments, in the power management method, a target power management policy that makes the predicted power rate of the target power use period conform to a preset power rate condition is determined based on the predicted power generation amount, the predicted power consumption amount, and the predicted power rate of the target power use period; comprising the following steps:

Determining the predicted power generation amount, the difference condition of the predicted power consumption and the subinterval in the target power consumption period; wherein, different subintervals correspond to different predicted electricity prices;

determining a first electric energy use strategy of a renewable energy system and a second electric energy use strategy of a power grid of each subinterval based on the difference condition and the predicted electricity price of the subinterval; when the electric power of the power grid is needed to be used, the lower the power supply price of the subinterval is, the more the electric power of the power grid is used.

In some embodiments, the power management method determines a second power usage policy of the power grid of each subinterval based on the difference condition and the predicted power rates of the subintervals, including:

Constructing an objective function and a plurality of different triggering conditions based on a plurality of variables of each subinterval, wherein the different triggering conditions correspond to different constraint conditions; the variables comprise predicted electricity price, predicted electricity consumption and predicted electricity generation amount, energy storage cost, energy storage charge amount, energy storage discharge cost and energy storage discharge amount;

and determining a first electric energy use strategy, a second electric energy use strategy of the power grid and an energy storage strategy of the storage battery based on the objective function and a target constraint condition corresponding to a target trigger condition met by at least part of the variables.

In some embodiments, in the power management method, when the target triggering condition is that the predicted power generation amount is smaller than the predicted power consumption amount, and a difference between the predicted power generation amount and the predicted power consumption amount is greater than a preset threshold, the method further includes:

and controlling at least one electric equipment with the priority meeting the preset priority condition to enter a low-power consumption mode or stop operation based on the priority of the preset multiple electric equipment.

In some embodiments, the method for managing electric energy further includes:

When the target triggering condition is that the predicted power generation amount is larger than the predicted power consumption amount, selling the electric energy stored in the renewable energy system when the actual power price in the target time period is larger than a preset power price threshold value; the preset electricity price threshold is determined based on a predicted electricity price.

In some embodiments, the method for managing electric energy further includes: after determining the target power management policy that enables the predicted power rate of the target power use period to meet the preset power rate condition, the method further includes:

determining the real-time power generation amount of the renewable energy system in the process of controlling the renewable energy system to execute the first power use strategy;

And adjusting the target electric energy management strategy based on the real-time generated energy of the renewable energy system.

In some embodiments, there is also provided an electrical energy management device for use in a renewable energy system, the device comprising:

the first prediction module is used for predicting the predicted electricity consumption and the predicted electricity price of the user in the target electricity consumption period;

The second prediction module is used for predicting the predicted power generation amount of the renewable energy system in the target power utilization period based on first influence factor data of various power generation amounts of the renewable energy system;

The determining module is used for determining a target electric energy management strategy for enabling the predicted electric charge of the target electric use period to accord with a preset electric charge condition based on the predicted electric energy generation amount, the predicted electric energy consumption amount and the predicted electric price of the target electric use period; the target electric energy management strategy comprises a first electric energy use strategy of the renewable energy system and a second electric energy use strategy of the power grid.

The embodiment of the application provides an electric energy management method and device, which are applied to a renewable energy system, wherein the method predicts the predicted electricity consumption and the predicted electricity price of a user in a target electricity consumption period; predicting a predicted power generation amount of the renewable energy system in the target power utilization period based on first influence factor data of a plurality of kinds of influence power generation amounts of the renewable energy system; and determining a target electric energy management strategy for enabling the predicted electric charge of the target electricity consumption period to accord with the preset electric charge condition based on the predicted electric energy generation amount, the predicted electric energy consumption amount and the predicted electric charge price of the target electricity consumption period, controlling the operation of the renewable energy source system and the power grid system in the target electricity consumption period based on the target electric energy management strategy, reasonably distributing electric energy generated by the renewable energy source system and reasonably using the power grid electric energy, thereby reducing electric energy waste, reducing total electric charge price of a user and improving the income of the user for using the renewable energy source system.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method of power management according to an embodiment of the present application;

FIG. 2 is a flow chart of a method for predicting predicted power consumption of a user in a target power consumption period according to an embodiment of the application;

FIG. 3 is a flowchart of a method for predicting a predicted electricity price of a user in a target electricity utilization period according to an embodiment of the present application;

FIG. 4 is a flowchart of a method for predicting predicted power generation of a renewable energy system during the target power usage period according to an embodiment of the present application;

Fig. 5 is a flowchart of a method for determining a target power management policy for enabling a predicted power rate of a target power use period to meet a preset power rate condition according to an embodiment of the present application;

Fig. 6 is a schematic structural diagram of a power management device according to an embodiment of the present application;

fig. 7 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.

In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.

It should be noted that the term "comprising" will be used in embodiments of the application to indicate the presence of the features stated hereafter, but not to exclude the addition of other features.

Based on the above, in the embodiment of the application, an electric energy management method is provided, which is applied to a renewable energy system, and the method predicts the predicted electricity consumption and the predicted electricity price of a user in a target electricity consumption period; predicting a predicted power generation amount of the renewable energy system in the target power utilization period based on first influence factor data of a plurality of kinds of influence power generation amounts of the renewable energy system; and determining a target electric energy management strategy for enabling the predicted electric charge of the target electricity consumption period to accord with the preset electric charge condition based on the predicted electric energy generation amount, the predicted electric energy consumption amount and the predicted electric charge price of the target electricity consumption period, controlling the operation of the renewable energy source system and the power grid system in the target electricity consumption period based on the target electric energy management strategy, reasonably distributing electric energy generated by the renewable energy source system and reasonably using the power grid electric energy, thereby reducing electric energy waste, reducing total electric charge price of a user and improving the income of the user for using the renewable energy source system.

Referring to fig. 1, fig. 1 shows a flowchart of a method for managing electric energy in an embodiment of the present application, where the method is applied to a renewable energy system, and the method includes steps S101 to S103:

s101, predicting predicted electricity consumption and predicted electricity price of a user in a target electricity consumption period;

s102, predicting predicted power generation amount of the renewable energy system in the target power utilization period based on first influence factor data of various power generation amounts of the renewable energy system;

S103, determining a target electric energy management strategy for enabling the predicted electric charge of the target electric use period to meet preset electric charge conditions based on the predicted electric energy generation amount, the predicted electric energy consumption amount and the predicted electric price of the target electric use period; the target electric energy management strategy comprises a first electric energy use strategy of the renewable energy system and a second electric energy use strategy of the power grid.

The renewable energy system comprises a solar power generation system, a wind power generation system, a hydroelectric power generation system and the like, wherein the solar power generation system and the wind power generation system are common in a group such as home power generation or a company.

Taking a solar power generation system as an example, the renewable energy system includes: the solar panel, the inverter, the processor and the storage battery; the solar panel converts solar energy into direct current; the inverter converts direct current generated by the solar panel into alternating current so as to supply power to electric equipment. In addition, the inverter can intelligently distribute power according to the energy demand of the electric equipment and the charging state of the storage battery under the control of the processor, so that the power supply of the electric equipment or the power distribution and the function switching of the storage battery are realized. The storage battery is used as an energy storage unit of the system, provides power support when the solar energy is insufficient or the power consumption demand is high, and can be charged from the inverter under the control of the processor when the solar energy is sufficient; when the solar energy is insufficient or the electric equipment needs more power, the storage battery can supply power to the electric equipment through the inverter.

The processor in the embodiment of the application not only sends out a control instruction to adjust the working mode of the inverter by collecting the real-time data of the solar panel, the inverter and the storage battery, but also executes the steps of the electric energy management method in the embodiment of the application to generate the target electric energy management strategy and control the running states of the inverter and the storage battery as well as the running states of the electric equipment.

In the embodiment of the application, the processor is also connected with power grid control equipment for controlling power supply of a power grid and load control equipment for controlling electric equipment. That is, in addition to interacting with the inverters and batteries of the solar power generation system, the processor is now connected to grid control devices and load control devices, enabling more comprehensive and fine control of the overall energy utilization and distribution process.

In the step S101, the predicted power consumption amount and the predicted power price of the user in the target power consumption period are predicted.

The predicted electricity consumption and the predicted electricity price of the target electricity consumption period can be determined through one calculation, can be determined through multiple calculations, for example, the predicted electricity consumption and the predicted electricity price between 18 points and 20 points can be directly predicted for the period between 18 points and 20 points, and can also be predicted multiple times, for example, the predicted electricity consumption and the predicted electricity price in the two periods between 18 points and 19 points and between 19 points and 20 points respectively.

That is, the predicted electricity consumption amount and the predicted electricity price of the target electricity consumption period may each be one or more values.

Specifically, referring to fig. 2, the predicted electricity consumption of the predicted user in the target electricity consumption period includes the following steps S201-S203:

s201, acquiring actual power consumption and meteorological data of a user in a first historical power consumption period and meteorological data in a target power consumption period from a first target database based on a preconfigured first interface; wherein the first historical electricity usage period is determined based on a target electricity usage period;

S202, inputting actual power consumption, meteorological data and meteorological data in a target power consumption period into a pre-trained power consumption prediction model; the electricity consumption prediction model is trained based on a first training set constructed by historical electricity consumption of a user and meteorological data corresponding to the historical electricity consumption;

S203, the electricity consumption prediction model processes the actual electricity consumption, the meteorological data and the meteorological data in the target electricity consumption period in the first historical electricity consumption period, and the predicted electricity consumption of the target electricity consumption period of the user is determined.

The actual power usage during the first historical power usage period is a sequence of actual power usage, e.g., [0.10, 0.09, 0.2, 0.08, 0.15, ] (units: kWh), each value in the sequence representing power usage during a predetermined period of time, e.g., 1 hour, 0.5 hours, etc.

The first target database comprises a database for recording the electricity consumption and a weather forecast database of a meteorological mechanism.

The first interface, by way of example, may employ Tibber API interfaces.

The weather has great influence on the electricity consumption, and the rise and the fall of the air temperature can lead to the change of the electricity consumption, and when the air temperature rises, for example, families, people need to use refrigeration equipment such as an air conditioner to adjust the indoor temperature, so that the electricity consumption is increased. Conversely, when the air temperature is reduced, a heating device is required to keep the room warm, and the electricity consumption is increased. Thus, summer and winter are typically peak periods of electricity usage, while spring and autumn are relatively low. For industrial production and commercial activities, in hot weather, the plant may need to increase the operating time of the ventilation and cooling equipment, thereby increasing the power consumption.

Based thereon, the meteorological data comprises: temperature data, humidity data, rainfall data, wind speed data, etc.

Therefore, in the embodiment of the application, when the predicted electricity consumption of the target electricity consumption period is predicted, the historical actual electricity consumption sequence, the weather data and the weather data in the target electricity consumption period need to be acquired, so that weather factors are considered during prediction, and more accurate predicted electricity consumption is obtained.

The first historical electricity consumption period is determined based on a target electricity consumption period, and in some embodiments, the time period length corresponding to the single electricity consumption in the sequence of the first historical electricity consumption period is determined based on the target electricity consumption period, for example, the target electricity consumption period is 1 hour, and then the time period length corresponding to the single electricity consumption is also 1 hour; or the first historical electricity usage period selection is determined based on the target electricity usage period, e.g., an adjacent first historical electricity usage period prior to the target electricity usage period may be selected; a first historical electricity usage period similar in characteristic to the target electricity usage period may be selected; the features are similar, including: the time points are similar (for example, 18-19 points of the power consumption of 18-19 points of the Saturday are predicted, 18-19 points of a plurality of histories are selected as the first historic power consumption time period, and 38 degrees of the air temperature are predicted, and a plurality of 38-degree air temperature time periods are selected as the first historic power consumption time period).

The first historical electricity usage period is determined based on a preset characteristic of a target electricity usage period; the preset characteristics comprise one of time characteristics, regional characteristics and meteorological characteristics. The first historical electricity utilization period has the same preset characteristics as the target electricity utilization period, so that the predicted electricity utilization amount is more accurate.

The electricity consumption prediction model is trained based on a first training set constructed by historical electricity consumption of a user and meteorological data corresponding to the historical electricity consumption; illustratively, the electricity consumption prediction model adopts a random forest model.

The random forest model, illustratively, assumes 100 decision trees in the random forest, each trained on a different subset of data of the first training set. In the training process, decision tree construction and integration of a prediction beam are included: the decision tree construction is to construct a decision path of each tree on the randomly selected feature subset; the integrated prediction: the prediction results of all trees are combined through average values to obtain final prediction. The predicted electricity price of the predicted user in the target electricity utilization period comprises the following steps:

Inputting the actual power consumption in the second historical power consumption period into a pre-trained electricity price prediction model; the electricity price prediction model is trained based on a second training set constructed by historical electricity price;

And the electricity price prediction model processes the actual electricity consumption in the second historical electricity consumption period and determines the predicted electricity price of the target electricity consumption period.

Referring to fig. 3, fig. 3 is a flowchart illustrating a method for predicting a predicted electricity price of a user in a target electricity consumption period according to an embodiment of the present application; as shown in fig. 3, the predicted electricity prices of the predicted users in the target electricity utilization period include the following steps S301 to S304:

S301, acquiring an actual electricity price in a second historical electricity utilization period from a second target database based on a second interface which is configured in advance; wherein the second historical electricity usage period is determined based on a target electricity usage period;

S302, converting the actual electricity price in the second historical electricity use period into a standardized electricity price characteristic based on the maximum actual electricity price, the minimum actual electricity price difference value and the actual electricity price and the standard electricity price difference value in the second historical electricity use period;

S303, inputting the standardized electricity price characteristics in the second historical electricity consumption period into a pre-trained electricity price prediction model; the electricity price prediction model is trained based on a second training set constructed by historical electricity price;

s304, the electricity price prediction model processes the standardized electricity price characteristics in the second historical electricity consumption period, and the predicted electricity price of the target electricity consumption period is determined.

Here, the second interface may also use Tibber API interfaces.

The second target database is a database storing actual electricity prices.

The actual electricity prices in the second historical electricity usage period are actual electricity price sequences, [0.10, 0.11, 0.10, 0.12, 0.15, ] (units: $/kWh), and the time intervals of the sequences are hours, i.e. the actual electricity prices are recorded once per hour.

The actual electricity rates in the second historical electricity use period are converted into standardized electricity rate features based on the differences of the maximum actual electricity rates, the minimum actual electricity rates, and the differences of the actual electricity rates and the standard electricity rates in the second historical electricity use period, in other words, the actual electricity rate sequence is subjected to standardized processing, and the electricity rate data is converted to between 0 and 1.

Specifically, the difference between the actual electricity price and the standard electricity price, and the ratio between the difference between the maximum actual electricity price and the minimum actual electricity price in the second historical electricity use period are determined as the standardized electricity price characteristics of the actual electricity price. Specifically, the following formula (1):

normalized_price = (price - min_price) / (max_price - min_price) ，……(1)；

Wherein, normalized_price characterizes a normalized electricity price feature; the price represents the actual electricity price; min_price represents a standard electricity price; max_price characterizes the maximum actual electricity price in the second historical electricity usage period; min_price characterizes the minimum actual electricity price over the second historical electricity usage period.

In some embodiments, the samples in the second training set are constructed based on a sliding window method. For example, the electricity prices for the next hour are predicted using data for the past 24 hours, so that the input samples are: [0.10, 0.11, 0.10, ], 24 hours electricity price); the output samples were: [0.13] is the electricity price at 25 hours.

The second historical electricity utilization period is determined based on a target electricity utilization period, and in particular, the second historical electricity utilization period is determined based on preset characteristics of the target electricity utilization period; the preset features comprise one of time features, regional features and weather features. The second historical electricity utilization period has the same preset characteristics as the target electricity utilization period, so that electricity price prediction is more accurate.

For example, if the target electricity consumption period is 1 hour, the period length corresponding to the actual electricity price in the second historical electricity consumption period is also 1 hour; and if the target electricity utilization period is a certain period of Saturday, the actual electricity prices in the second historical electricity utilization period are all the electricity prices of other Saturday in the certain period of Saturday.

The electricity price prediction model may employ an LSTM model.

The LSTM model comprises an input layer, one or more LSTM layers and a full connection layer, wherein the LSTM layers comprise a certain number of LSTM units. Illustratively, the LSTM model has one LSTM layer with 50 LSTM cells.

The input layer receives time series data, and in the embodiment of the present application, receives an actual electricity price sequence in the second historical electricity use period, for example, receives a normalized electricity price characteristic of an actual electricity price of 24 time steps.

Correspondingly, the one or more LSTM layers process normalized power rate characteristics of the actual power rates for the 24 time steps.

And the full connection layer receives the processing results of one or more LSTM layers and outputs the predicted electricity price of the next time step.

The loss function of the electricity price prediction model is Mean Square Error (MSE), specifically, please refer to formula (2):

MSE = Σ(actual - predicted)² / n ，…… （2）；

Wherein actual characterizes the actual electricity price in the sample; the predicted characterization electricity price prediction model predicts a predicted electricity price based on an electricity price sequence in the sample; actual-predicted characterizes the difference between the predicted electricity price and the actual voltage of the electricity price prediction model; n guarantees the number of samples, MSE characterizes the mean square error.

The Mean Square Error (MSE) is adopted as a loss function, so that the difference between the predicted electricity price and the actual electricity price of the sensitive perceived electricity price prediction model can accurately reflect the model prediction precision; as the error decreases, the gradient of MSE also decreases, facilitating convergence of the model.

The process of training the electricity price prediction model based on the second training set is as follows: in each iteration, the gradient of the loss function with respect to the current parameter (e.g., weight) is first calculated; then updating the first and second moment estimates of the gradient (i.e., the average of the gradient and the average of the square); based on these first and second moment estimates of the updated gradients, a learning rate is adjusted for each parameter of the electricity price prediction model, and the parameters are updated using this adjusted learning rate.

It should be noted that, after the electricity consumption prediction model processes the actual electricity consumption, the weather data and the weather data in the target electricity consumption period in the first historical electricity consumption period and determines the predicted electricity consumption of the target electricity consumption period of the user, the first training set is updated based on the actual electricity consumption, the weather data and the weather data in the target electricity consumption period in the first historical electricity consumption period and the predicted electricity consumption and the actual electricity consumption in the target electricity consumption period, so that the electricity consumption prediction model is updated in full or in increment based on the updated first training set.

And similarly, the electricity price prediction model processes the standardized electricity price characteristics in the second historical electricity consumption period, and updates the second training set based on the standardized electricity price characteristics in the second historical electricity consumption period, the predicted electricity price in the target electricity consumption period and the actual electricity price after determining the predicted electricity price in the target electricity consumption period, so as to perform full-scale update or incremental update on the electricity price prediction model based on the updated second training set.

In the step S102, the predicted power generation amount of the renewable energy system in the target power use period is predicted based on a plurality of first influence factor data that influence the power generation amount of the renewable energy system.

In the embodiment of the application, please refer to fig. 4, fig. 4 shows a flowchart of a method for predicting the predicted power generation amount of the renewable energy system in the target power utilization period according to the embodiment of the application; the method comprises the steps of predicting predicted power generation capacity of a renewable energy system in the target power utilization period based on first influence factor data of various kinds of power generation capacity influencing the renewable energy system; comprising the following steps S401-S403:

S401, acquiring first influence factor data of various kinds of influence on the power generation capacity of a renewable energy system in a target power utilization period; wherein the first influence factor data includes: geographic location data, terrain feature data, meteorological data;

S402, inputting the plurality of first influence factor data into a pre-constructed power generation amount prediction model; the power generation amount prediction model is constructed based on historical first influence factor data and configuration information of the renewable energy system;

S403, the generated energy prediction model processes the plurality of first influence factor data and configuration information of the renewable energy system, and predicts predicted generated energy of the renewable energy system in the target electricity utilization period.

Different geographic positions and topographical features can influence the availability and distribution of renewable energy sources such as solar energy, wind energy and the like, thereby influencing the generated energy of a renewable energy source system; for example, under the same meteorological data, areas with high altitude and little cloud have higher solar radiation intensity; shadows created by surrounding buildings, trees, or other obstructions may reduce the light received by the photovoltaic panel.

The configuration information of the renewable energy system may affect the power generation of the renewable energy system. For example, in a solar power generation system, the quality and type of a solar panel, and the conversion efficiency of an inverter directly affect the power generation performance of the entire solar power generation system.

In the embodiment of the application, the predicted power generation amount of the renewable energy system in the target power utilization period is predicted more accurately based on a plurality of first influence factor data and the configuration information of the renewable energy system.

In the step S103, a target power management policy for making the predicted power rate of the target power use period conform to a preset power rate condition is determined based on the predicted power generation amount, the predicted power consumption amount, and the predicted power rate of the target power use period; the target electric energy management strategy comprises a first electric energy use strategy of the renewable energy system and a second electric energy use strategy of the power grid.

In the embodiment of the present application, referring to fig. 5, fig. 5 shows a flowchart of a method for determining a target power management policy that enables a predicted power rate of a target power utilization period to meet a preset power rate condition according to the embodiment of the present application; specifically, determining a target electric energy management strategy for enabling the predicted electric charge of the target electric use period to meet a preset electric charge condition based on the predicted electric energy generation amount, the predicted electric energy consumption amount and the predicted electric price of the target electric use period; comprises the following steps S501-S502:

S501, determining the predicted power generation amount, the difference condition of the predicted power consumption and the subinterval in the target power consumption period; wherein, different subintervals correspond to different predicted electricity prices;

S502, determining a first electric energy use strategy of a renewable energy system and a second electric energy use strategy of a power grid of each subinterval based on the difference condition and the predicted electricity price of the subinterval; when the electric power of the power grid is needed to be used, the lower the power supply price of the subinterval is, the more the electric power of the power grid is used.

In some embodiments, after determining the first power usage policy of the renewable energy system and the second power usage policy of the power grid for each sub-interval based on the difference condition and the predicted power price of the sub-interval, the energy storage policy of the storage battery, the operation policy of the electric device, and the selling policy of the electric energy stored in the renewable energy system for each sub-interval are determined based on the difference condition and the predicted power price of the sub-interval.

That is, in the present application, based on the difference situation and the predicted electricity prices of the subintervals, a 5-dimensional strategy of a first electricity usage strategy of the renewable energy system, a second electricity usage strategy of the electricity grid, an energy storage strategy of the electricity grid for the storage battery, an operation strategy of the electric equipment, and a selling strategy of the electricity stored in the renewable energy system of each subinterval are determined.

Specifically, based on the difference condition and the predicted electricity prices of the subintervals, determining a first electricity usage policy of the renewable energy system and a second electricity usage policy of the power grid of each subinterval includes: constructing an objective function and a plurality of different triggering conditions based on various variables of each subinterval, wherein the different triggering conditions correspond to different constraint conditions, and the number of the constraint conditions corresponding to the triggering conditions is one or more; the variables comprise predicted electricity price, predicted electricity consumption and predicted electricity generation amount, energy storage cost, energy storage charge amount, energy storage discharge cost and energy storage discharge amount;

The power consumption strategy, namely the power consumption of each period; the energy storage strategy, namely the energy storage state of each time period, comprises the charge quantity and the discharge quantity of the storage battery.

The objective function, i.e. the objective to be optimized, in the embodiment of the present application is to minimize the cost of systematic electricity.

By way of example only, in embodiments of the present application, the objective function formula is the following formula (3):

，……（3）

Wherein, C _total represents the total cost of electricity, including the cost of electricity consumption and the cost of energy storage; p _i denotes the predicted electricity price for the i-th subinterval; x _i represents the predicted power consumption of the i-th subinterval; g _i denotes the predicted power generation amount of the i-th subinterval; e _i denotes an energy storage cost (including battery charge loss) of the i-th subinterval, y _i denotes an energy storage charge amount of the i-th subinterval, and F _i denotes an energy storage discharge cost (including battery discharge loss) of the i-th subinterval; z _i represents the energy storage/discharge amount of the i-th subinterval.

The triggering conditions include: when the electric quantity of the storage battery is lower than a preset electric quantity threshold value, the predicted electric quantity is larger than the predicted electric quantity, the renewable energy system stops generating electricity, and the like.

The storage battery may also be referred to as an electric storage device, or the like.

The constraints are used to ensure specific requirements of the system in terms of power usage and energy storage, for example: the power consumption needs must meet the demands of users, the charge and discharge efficiency of the storage battery, the charge and discharge rate limitation of the energy storage device of the storage battery, the capacity limitation of the storage battery and the limitation of the total load power.

The number of factors to be considered in a specific power utilization scene is large, the number of variables is also large, and the combination of the triggering condition and the constraint condition is large, so that the following examples are not listed one by one.

Exemplary, in the embodiment of the present application, the triggering condition is: q is less than or equal to 20 percent, and Gi is more than xi, and when the constraint condition is that: gi=xi+yi; wherein, Q represents the electric quantity of the storage battery; that is, when the electric quantity of the storage battery is lower than the preset electric quantity threshold value by 20% and the predicted electric quantity is larger than the predicted electric quantity, the sum of the stored energy charging quantity and the predicted electric quantity is the predicted electric quantity, that is, only the electric energy of the solar energy system is adopted to supply power to the electric equipment and simultaneously charge the storage battery.

Conversely, when the trigger condition is: q is less than or equal to 20 percent, and when Gi is less than xi, P _i is less than the constraint condition when the predicted electricity price threshold value is preset: gi+yi < xi; wherein, Q represents the electric quantity of the storage battery; when the electric quantity of the storage battery is lower than a preset electric quantity threshold value by 20%, and the predicted electric quantity is smaller than the predicted electric quantity, the sum of the stored energy charging quantity and the predicted electric quantity is smaller than the predicted electric quantity, namely, the electric energy of the solar energy system is only adopted to supply power to the electric equipment, and meanwhile, the electric energy of the power grid is also adopted to supply power to the electric equipment and charge the storage battery.

Illustratively, when the trigger condition is: q is more than or equal to 90%, P _i is smaller than a preset predicted electricity price threshold value, xi is more than Gi, and the constraint condition is that: xi-gi=mi; mi represents the power supply quantity of the power grid in the ith subinterval; i.e. when the battery of the ith subinterval is in a full state and the predicted electricity price of the ith subinterval is lower, the power grid is preferably used for supplying power instead of the battery.

In contrast, exemplary, when the trigger condition is: q is more than or equal to 90%, P _i is larger than a preset predicted electricity price threshold value, xi is more than Gi, and the constraint condition is that: xi-gi=ni; ni represents the power supply quantity of the storage battery in the ith subinterval; when the storage battery in the ith subinterval is in a full state, the predicted electricity price of the ith subinterval is higher, and the storage battery is used for supplying power instead of the power grid.

Converting the constructed objective function and constraint conditions into a linear programming model, and solving the constructed linear programming model by using a linear programming solver to obtain a first electric energy use strategy, a second electric energy use strategy of the power grid and an energy storage strategy of the storage battery; finally, checking whether the optimized result meets the constraint condition corresponding to the triggering condition, and whether the aim of minimizing the electricity cost is fulfilled.

It should be noted that, according to specific electricity usage scenarios and requirements, determining a first electric energy usage policy, a second electric energy usage policy of a power grid and an energy storage policy of a storage battery under various conditions, configuring corresponding trigger conditions and constraint conditions based on the first electric energy usage policy, the second electric energy usage policy of the power grid and the energy storage policy of the storage battery, and converting the trigger conditions and constraint conditions into mathematical formula expression; and converting the constructed objective function and constraint conditions into a linear programming model, solving the linear programming model, and reasonably determining a first electric energy use strategy, a second electric energy use strategy of the power grid and an energy storage strategy of the storage battery in the actual running process of the renewable energy system.

The triggering conditions and the constraint conditions corresponding to the first electric energy use strategy, the second electric energy use strategy of the power grid and the energy storage strategy of the storage battery under various conditions are converted into formula expression, and the construction and the solving of the linear programming model are established as the prior art, and are not repeated.

From multiple dimensions, the triggering conditions and constraint conditions under multiple conditions are considered, the use strategy of the electric energy of the renewable energy system and the electric energy of the power grid is comprehensively and finely regulated, renewable energy is fully utilized, the power grid electricity purchasing in high-price time period is reduced, and therefore the overall energy cost is reduced; the power supply and demand relation of power supply and power consumption can be balanced by carrying out cooperative optimization on the electric energy utilization strategy of the power grid and the energy storage strategy of the storage battery, so that the maximum utilization of the storage battery is realized, and the energy cost is further reduced; the energy consumption is reduced by controlling the operation of the electric equipment so as to balance the supply-demand relationship; by making a reasonable electric energy selling strategy, the electric energy stored in the renewable energy system can be sold to a power grid or other users in a period of higher electricity price, and additional economic benefits can be obtained while considering supply and demand relations and energy costs.

The lower the power supply price of the subinterval is, the more the electric energy of the power grid is used, that is, the renewable energy sources such as solar energy or wind energy are preferentially used, so that the dependence on the power grid is reduced; meanwhile, more power grid electric energy is used in the period of low electricity price, the power grid electric energy is reduced in the period of high electricity price, and renewable energy sources such as solar energy or wind energy are preferentially used, so that electricity consumption cost is reduced.

In some embodiments, determining a second power usage policy for the power grid for each subinterval based on the difference conditions and the predicted electricity prices for the subintervals comprises:

and when the target trigger condition is that the predicted power generation amount is smaller than the predicted power consumption amount, determining an energy storage strategy of the power grid in at least part of the subintervals for the storage battery based on the difference condition and the predicted power price of the subintervals.

That is, when it is determined that the predicted power generation amount is smaller than the predicted power consumption amount, the stored energy is stored when the power rate is low, and the stored energy is used when the power rate is high, so that even if the power generation amount of the renewable energy system cannot meet the demand when the power rate is high, the stored energy when the power rate is low can be utilized, and the power consumption cost can be reduced.

When the target triggering condition is that the predicted power generation amount is smaller than the predicted power consumption amount and the difference value between the predicted power generation amount and the predicted power consumption amount is larger than a preset threshold value, the method further comprises:

That is, when the predicted power generation amount and the predicted power consumption amount differ too much, the power of the non-critical device may be preferentially turned off or reduced. For example, the fresh air system is turned off, so that electric energy is saved, outdoor air quality is good, indoor personnel are fewer, or the indoor air quality requirement of a user is not particularly high, and the fresh air system can be turned off when electricity price is high.

Or according to the operation mode and the energy consumption characteristic of the equipment, selecting an efficient energy-saving operation mode. For example, for air conditioning equipment, an intelligent temperature control strategy can be adopted, and the equipment operation can be automatically adjusted according to the indoor temperature and humidity, so that excessive refrigeration or heating is avoided; or the target temperature is adjusted from 24 degrees to 26 degrees, thereby saving electric energy.

The electric energy management method provided by the embodiment of the application further comprises the following steps:

That is, if the predicted power generation amount is larger than the predicted power consumption amount, a suitable high power price opportunity may be selected to sell the surplus power amount; in the embodiment of the application, the preset electricity price threshold is determined by referring to the predicted electricity price, for example, the maximum 1 yuan of the reference predicted electricity price can be set to be sold when the real-time electricity price reaches 0.98, and the preset electricity price threshold fluctuates along with the fluctuation of the electricity price, so that the low price of selling the electric energy is avoided, the income is improved, and the overall energy use cost is reduced.

The electric energy management method provided by the embodiment of the application further comprises the following steps: after determining the target power management policy that enables the predicted power rate of the target power use period to meet the preset power rate condition, the method further includes:

Firstly, the predicted power generation amount has a certain error, and secondly, because the weather data in a target time period are referred to when the power generation amount is predicted, the weather data in the target time period are also predicted, and the actual weather data may not be the same, so that the actual power generation amount is wrong, for example, the power generation amount is more or less, the target power management strategy is adjusted based on the real-time power generation amount of the renewable energy system, the rationality of the target power management strategy is ensured, for example, the storage battery is ensured to store enough power at low price, and the full use of the power of the renewable energy system is ensured.

Based on the same inventive concept, the embodiment of the present application further provides an electric energy management device corresponding to the electric energy management method, and since the principle of solving the problem by the device in the embodiment of the present application is similar to that of the electric energy management method in the embodiment of the present application, the implementation of the device may refer to the implementation of the method, and the repetition is omitted.

Referring to fig. 6, fig. 6 is a schematic structural diagram of an electric energy management device according to an embodiment of the application; as shown in fig. 6, the electric energy management device is applied to a renewable energy system, and the device comprises:

a first prediction module 601, configured to predict a predicted power consumption and a predicted power price of a user in a target power consumption period;

A second prediction module 602, configured to predict a predicted power generation amount of the renewable energy system in the target power utilization period based on a plurality of first influence factor data that affect the power generation amount of the renewable energy system;

A determining module 603, configured to determine a target power management policy that enables the predicted power rate of the target power consumption period to conform to a preset power rate condition, based on the predicted power generation amount, the predicted power consumption amount, and the predicted power price of the target power consumption period; the target electric energy management strategy comprises a first electric energy use strategy of the renewable energy system and a second electric energy use strategy of the power grid.

In some embodiments, in the power management apparatus, the first prediction module is specifically configured to, when predicting a predicted power consumption of the user in the target power consumption period:

In some embodiments, in the power management apparatus, the first prediction module is specifically configured to, when predicting a predicted electricity price of the user in the target electricity usage period:

In some embodiments, in the electric energy management apparatus, the second prediction module predicts the predicted electric energy generation amount of the renewable energy system in the target electricity utilization period based on the first influence factor data that affects the electric energy generation amount of the renewable energy system, and specifically is configured to:

In some embodiments, in the power management apparatus, the determining module is specifically configured to, when determining, based on the predicted power generation amount, the predicted power consumption amount, and the predicted power price in the target power consumption period, a target power management policy that makes the predicted power rate in the target power consumption period meet a preset power rate condition:

In some embodiments, in the power management apparatus, the determining module is specifically configured to, when determining the second power usage policy of the power grid in each subinterval based on the difference condition and the predicted power rates of the subintervals:

In some embodiments, the power management device further includes a control module, configured to, when the target trigger condition is that the predicted power generation amount is smaller than the predicted power consumption amount, and a difference between the predicted power generation amount and the predicted power consumption amount is greater than a preset threshold, sell the power stored in the renewable energy system when the actual power price in the target time period is greater than the preset power price threshold, and control at least one power consumption device with a priority meeting a preset priority condition to enter a low power consumption mode or stop running based on priorities of the preconfigured multiple power consumption devices.

In some embodiments, the electric energy management device further includes a selling module, configured to sell electric energy stored in the renewable energy system when the actual electricity price in the target time period is greater than a preset electricity price threshold when the target trigger condition is that the predicted electricity generation amount is greater than the predicted electricity consumption amount; the preset electricity price threshold is determined based on a predicted electricity price.

In some embodiments, the power management device further includes an adjustment module, configured to determine, after determining a target power management policy that makes the predicted power rate of the target power utilization period meet the preset power rate condition, a real-time power generation amount of the renewable energy system in a process of controlling the renewable energy system to execute the first power utilization policy;

Based on the same inventive concept, the embodiment of the present application further provides an electronic device corresponding to the electric energy management method, and since the principle of solving the problem of the electronic device in the embodiment of the present application is similar to that of the electric energy management method in the embodiment of the present application, implementation of the electronic device may refer to implementation of the method, and repeated descriptions are omitted.

Referring to fig. 7, fig. 7 shows a schematic structural diagram of an electronic device according to an embodiment of the application, where the electronic device 700 includes: a processor 702, a memory 701 and a bus, said memory 701 storing machine readable instructions executable by said processor 702, said processor 702 and said memory 701 communicating via the bus when the electronic device 700 is running, said machine readable instructions when executed by said processor 702 performing the steps of said power management method.

Based on the same inventive concept, the embodiment of the present application further provides a computer readable storage medium corresponding to the electric energy management method, and since the principle of solving the problem by using the computer readable storage medium in the embodiment of the present application is similar to that of the electric energy management method in the embodiment of the present application, the implementation of the computer readable storage medium can refer to the implementation of the method, and the repetition is omitted.

A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the power management method.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the method embodiments, and are not repeated in the present disclosure. In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, and for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a platform server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. A method of power management for use in a renewable energy system, the method comprising:

2. The power management method according to claim 1, wherein predicting the predicted power consumption of the user in the target power consumption period includes:

3. The power management method according to claim 1, wherein predicting the predicted power rate of the user at the target power usage period includes:

4. The power management method according to claim 1, wherein the predicted power generation amount of the renewable energy system in the target power use period is predicted based on first influence factor data that affects power generation amounts of the renewable energy system; comprising the following steps:

5. The power management method according to claim 1, wherein a target power management policy that causes the predicted power rate of the target power use period to conform to a preset power rate condition is determined based on the predicted power generation amount, the predicted power consumption amount, and the predicted power rate of the target power use period; comprising the following steps:

6. The power management method of claim 5, wherein determining a first power usage policy of the renewable energy system, a second power usage policy of the power grid for each sub-interval based on the difference condition and the predicted power rates for the sub-intervals comprises:

7. The power management method according to claim 6, wherein when the target trigger condition is that the predicted power generation amount is smaller than the predicted power consumption amount, and a difference between the predicted power generation amount and the predicted power consumption amount is larger than a preset threshold, the method further comprises:

8. The method of power management according to claim 6, further comprising:

9. The method of power management according to claim 1, further comprising: after determining the target power management policy that enables the predicted power rate of the target power use period to meet the preset power rate condition, the method further includes:

10. An electrical energy management device for use in a renewable energy system, the device comprising: