CN114498732A

CN114498732A - Energy Internet optimization method, system and device and readable storage medium

Info

Publication number: CN114498732A
Application number: CN202111636830.XA
Authority: CN
Inventors: 梁军; 谢骏凯; 陈烨洪; 张继轩; 辛建江; 赵文仙; 刘国静; 蔚泉清; 张海波
Original assignee: State Grid Zhejiang Electric Power Co Ltd Shaoxing Shangyu District Power Supply Co; Shaoxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Current assignee: State Grid Zhejiang Electric Power Co Ltd Shaoxing Shangyu District Power Supply Co; Shaoxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date: 2021-12-29
Filing date: 2021-12-29
Publication date: 2022-05-13

Abstract

The invention discloses an energy Internet optimization method, a system, a device and a readable storage medium, wherein the method comprises the following steps: acquiring historical power generation data of a power generation device in the energy Internet; determining power supply information of the power generation device in a future time period based on the historical power generation data; and determining a distribution path of the power supply amount generated by the power generation device in the future time period based on the power supply information, and transmitting the distribution path of the power supply amount to an energy router. The substantial effects of the invention include: and determining future power supply information and a distribution path of power supply amount by using historical power generation data so as to optimize the energy Internet and improve the utilization efficiency and stability of energy.

Description

Energy Internet optimization method, system and device and readable storage medium

Technical Field

The invention relates to the technical field of internet, in particular to an energy internet optimization method, system and device and a readable storage medium.

Background

The energy internet can interconnect a large number of distributed power generation devices, distributed energy storage devices and distributed loads to form an energy peer-to-peer exchange and sharing network with bidirectional energy flow. The devices in the energy internet can be connected with each other through the energy router to realize the open and peer-to-peer exchange of energy.

With the development of the energy internet technology, higher requirements are put forward by the outside on the utilization efficiency of energy in the energy internet, the stability of the energy internet and the like. Therefore, it is necessary to provide an optimization method for the energy internet, which optimizes the energy internet.

Disclosure of Invention

Aiming at the problem that the optimization effect on the energy Internet is not ideal in the prior art, the invention provides an optimization method, a system, a device and a readable storage medium for the energy Internet.

The technical scheme of the invention is as follows.

An energy internet optimization method comprises the following steps:

acquiring historical power generation data of a power generation device in the energy Internet;

determining power supply information of the power generation device in a future time period based on the historical power generation data;

and determining a distribution path of the power supply amount generated by the power generation device in the future time period based on the power supply information, and transmitting the distribution path of the power supply amount to an energy router.

Preferably, the determining a distribution path of the amount of power supply generated by the power generation device in the future time period based on the power supply information and transmitting the distribution path of the amount of power supply to the energy router includes:

determining power supply variation corresponding to two adjacent sub-time periods in the future time period based on the power supply information;

judging whether the power supply variation is larger than a first electric quantity threshold value or not aiming at each power supply variation;

when the power supply variation is larger than the first electric quantity threshold value, segmenting the power supply quantity generated in the sub-time period with the largest power supply quantity in the two adjacent sub-time periods to obtain the segmented sub-power supply quantity;

and determining a distribution path of the sub-power supply amount, and sending the distribution path of the sub-power supply amount to the energy router, wherein one part of the sub-power supply amount after being split is used for supplying power to a load in the energy internet, and the other part of the sub-power supply amount after being split is used for transmitting to an energy storage device in the energy internet for storing energy.

Preferably, the method further comprises the following steps:

judging whether the power supply amount for supplying power to the load in the sub-time period in the future time period is smaller than a second power threshold value; when the power supply amount is smaller than the second power threshold value, the load is supplied with power based on the power generation device and the energy storage device in the sub-time period in the future time period.

acquiring weather forecast information;

adjusting the power supply information based on the weather forecast information to obtain adjusted power supply information;

and determining a distribution path of the power supply amount generated by the power generation device in the future time period based on the adjusted power supply information, and transmitting the distribution path of the power supply amount to an energy router.

The invention also provides an energy internet optimization system, which comprises:

the first acquisition module is used for acquiring historical power generation data of the power generation device in the energy Internet;

the first determination module is used for determining power supply information of the power generation device in a future time period based on the historical power generation data;

and the second determining module is used for determining a distribution path of the power supply amount generated by the power generation device in the future time period based on the power supply information and sending the distribution path of the power supply amount to an energy router.

Preferably, the second determining module is specifically configured to:

judging whether the power supply variable quantity is larger than a first electric quantity threshold value or not according to each power supply variable quantity;

when the power supply variable quantity is larger than the first electric quantity threshold value, segmenting the power supply quantity generated in the sub-time period with the largest power supply quantity in the two adjacent sub-time periods to obtain the segmented sub-power supply quantity;

Preferably, the system further comprises:

the judging module is used for judging whether the power supply amount for supplying power to the load in the sub-time period in the future time period is less than a second electric quantity threshold value or not;

and the power supply module is used for supplying power to the load based on the power generation device and the energy storage device in a sub-time period in the future time period when the power supply variation is smaller than the second electric quantity threshold.

Preferably, the second determining module further includes:

acquiring weather forecast information;

The invention also provides an energy Internet optimization device which comprises a processor, wherein the processor is used for executing the energy Internet optimization method.

The invention also provides a readable storage medium, which stores computer instructions, and after the computer reads the computer instructions in the storage medium, the computer executes the method for optimizing the energy internet.

The substantial effects of the invention include: and determining future power supply information and a distribution path of power supply amount by using historical power generation data so as to optimize the energy Internet and improve the utilization efficiency and stability of energy.

Drawings

Fig. 1 is a schematic diagram of an application scenario of an optimization method for energy internet according to some embodiments of the present disclosure;

FIG. 2 is an exemplary flow diagram illustrating the determination of a distribution path for an amount of power generated by a power generation device over a future time period according to some embodiments of the present description;

FIG. 3 is an exemplary flow diagram of determining distribution paths for sub-supply amounts in accordance with some embodiments described herein;

FIG. 4 is an exemplary flow diagram for powering a load based on a power generation device and an energy storage device, according to some embodiments of the present description;

FIG. 5 is yet another exemplary flow chart illustrating determining a distribution path for an amount of power generated by a power generation device over a future time period according to some embodiments of the present description.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions will be clearly and completely described below with reference to the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The technical solution of the present invention will be described in detail below with specific examples. Embodiments may be combined with each other and some details of the same or similar concepts or processes may not be repeated in some embodiments.

Example (b):

fig. 1 is a schematic diagram of an application scenario of an energy internet optimization method according to some embodiments of the present disclosure.

The optimization method of the energy internet can be used for optimizing the energy internet. As shown in FIG. 1, an application scenario of the energy Internet optimization method may include energy internets 110-1 to 110-n, an energy router 120 and a processor 130.

The energy internet may refer to a network between internal structures that enables bidirectional on-demand transmission and dynamic balanced use of energy. The energy internet may include a power generation device 111, a load 112, and an energy storage device 113. The power generation device 111 may include a wind power generation device 111-1 and a solar power generation device 111-2. The power generation device 111, the load 112, and the energy storage device 113 may be connected via an energy router 120 to realize energy exchange. For example, the power generator 111 is connected to the load 112 through the energy router 120 to transmit the power generated by the power generator 111 to the load 112. For another example, the power generation device 111 is connected to the energy storage device 113 through the energy router 120 to transmit the electric energy generated by the power generation device 111 to the energy storage device 113. As another example, the energy storage device 113 and the load 112 may be connected via an energy router to transfer the electrical energy in the energy storage device 113 to the load 112.

The energy router 120 may be coupled to the power generation device 111, the load 112, and the energy storage device 113 to control the flow of energy in the energy internet. In some embodiments, the energy router may control the flow of energy in one or more energy internetworks. For example, the energy router 120 may control the flow of energy in the energy internets 110-1-110-n.

The processor 130 may process data and/or information from the energy router. The processor may communicate with the energy router to provide various functions of the service. For example, the processor may obtain data (e.g., historical power generation data for the power generation device) from the energy router, predict power supply information for the power generation device over a future time period, and send the predicted data to the energy router. The processor may also be used to process data and/or information from external data sources (e.g., cloud data centers) outside the application scenario of the optimization method of the energy internet. For example, the processor may be configured to process weather forecast information to adjust power supply information for the power generation device over a future time period. In some embodiments, the processor may be a single server or a group of servers. The set of servers can be centralized or distributed (e.g., the processor can be a distributed system). In some embodiments, the processor may be local or remote. In some embodiments, the processor may be implemented on a cloud platform, or provided in a virtual manner. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.

It should be noted that the above description of the application scenario of the optimization method for the energy internet is only for convenience of description, and the present specification is not limited to the scope of the illustrated embodiments.

The optimization method of the energy Internet can be applied to an optimization system of the energy Internet. In some embodiments, an energy internet optimization system may include a first obtaining module, a first determining module, and a second determining module.

The first obtaining module can be used for obtaining historical power generation data of a power generation device in the energy Internet. For more on the power generation device and the historical power generation data, refer to fig. 2 and the related description thereof, and the details are not repeated here.

The first determination module may be configured to determine power supply information of the power generation device for a future time period based on historical power generation data. For more about the future time period and the power supply information, refer to fig. 2 and the related description thereof, which are not repeated herein.

The second determining module may be configured to determine a distribution path of the amount of power generated by the power generation apparatus in a future time period based on the power supply information, and transmit the distribution path of the amount of power to the energy router. For more details of the power supply amount, the distribution path, and the energy router, reference is made to fig. 2 and the related description thereof, which are not repeated herein.

In some embodiments, the second determining module may be further configured to determine, based on the power supply information, power supply variation amounts corresponding to two adjacent sub-time periods in a future time period; judging whether the power supply variation is larger than a first electric quantity threshold value or not according to each power supply variation; when the power supply variable quantity is larger than a first electric quantity threshold value, segmenting the power supply quantity generated in the sub-time period with the largest power supply quantity in the two adjacent sub-time periods to obtain the segmented sub-power supply quantity; and determining a distribution path of the sub-power supply amount, and sending the distribution path of the sub-power supply amount to the energy router, wherein one part of the split sub-power supply amount is used for supplying power to a load in the energy internet, and the other part of the split sub-power supply amount is used for transmitting to an energy storage device in the energy internet for storing energy.

In some embodiments, the second determination module may be further configured to obtain weather forecast information; adjusting the power supply information based on the weather forecast information to obtain adjusted power supply information; and determining a distribution path of the power supply amount generated by the power generation device in the future time period based on the adjusted power supply information, and transmitting the distribution path of the power supply amount to the energy router.

In some embodiments, the energy internet optimization system may further include a determination module and a power supply module.

The judging module may be configured to judge whether a power supply amount of the load supplied by the sub-period in the future period is less than a second power threshold. For more about the load, refer to fig. 3 and the related description thereof, and for more about the second power threshold, refer to fig. 4 and the related description thereof, which are not repeated herein.

The power supply module may be configured to supply power to the load based on the power generation device and the energy storage device in a sub-period of the future period when the power supply amount is smaller than the second power threshold. For more details of the energy storage device, refer to fig. 3 and the related description thereof, which are not repeated herein.

It should be understood that the energy internet optimization system and its modules can be implemented in various ways. For example, in some embodiments, a processing device and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system (e.g., a microprocessor or specially designed hardware). Those skilled in the art will appreciate that the processing devices and modules thereof described above may be implemented via computer-executable instructions. The system and its modules of the present specification may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, or the like, but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above description of the energy internet optimization system and its modules is for convenience only and should not limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, each module of the optimization system of the energy internet may be a different module in one system, or may be a module that implements the functions of two or more modules described above. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.

FIG. 2 is an exemplary flow diagram illustrating determining distribution paths for an amount of power generated by a power generation device over a future time period according to some embodiments of the present description. As shown in fig. 2, the process 200 includes the following steps:

step 210, obtaining historical power generation data of a power generation device in the energy Internet. Step 210 may be performed by a first acquisition module.

A power generation device may refer to a device that converts various forms of energy (e.g., solar energy, wind energy, etc.) into electrical energy. In some embodiments, the power generation device may include a wind power generation device and a solar power generation device. In some embodiments, the power generation device may also include a device that converts other energy sources into electrical energy, for example, the power generation device may also include a hydro-power generation device that converts the potential energy of water into electrical energy.

In some embodiments, the power generation means in the energy internet may be one or more. In some embodiments, the plurality of power generation devices in the energy internet may be the same or different kinds of power generation devices. For example, the energy internet may include two different power generation devices, a wind power generation device and a solar power generation device.

The historical power generation data may refer to power data generated by a power generation device in the energy internet in a past time period. In some embodiments, the historical generation data may be obtained directly from an energy router of the energy internet.

And step 220, determining power supply information of the power generation device in a future time period based on the historical power generation data. Step 220 may be performed by a first determination module.

The future time period may refer to a time period after the current time. In some embodiments, the length of the future time period may be directly preset. For example, the future time period may be preset to three days in the future.

In some embodiments, the future time period may be divided into a plurality of sub-time periods. The length of the sub-periods in the future period may also be predetermined. For example, the future time period may be preset to three days in the future, and every 12 hours of the three days in the future may be regarded as one sub-time period.

The power supply information may refer to power supply amount information corresponding to the amount of power supplied by the power generation apparatus in the energy internet at each time period.

In some embodiments, the power supply information of the power generation device for the future time period may be determined according to a machine learning model.

In some embodiments, the historical power generation data in the preset past time period of the total power supply amount of the plurality of power generation apparatuses may be used as an input of the total power supply amount prediction model and output as power supply information of the power generation apparatuses in the future time period. Wherein the preset elapsed time period may be preset.

For example, at time zero of 10/4/2030, historical power generation data {800, 900, 1000, 950, 900, 900} of the total power generation amount of the plurality of power generation devices for the past three days, i.e., 1/10/2030 to 3/10/2030 may be input to the total power supply amount prediction model, and power supply information of the power generation devices for the next three days, i.e., 4/10/2030 to 6/10/2030, may be determined as {600, 800, 900, 1050, 900, 950 }. Wherein, the historical power generation data {800, 900, 1000, 950, 900, 900} represents that the total power generation amount of a plurality of power generation devices in the energy internet in 2030, 10 and 1 days 00: 00-12: 00, 10 and 1 days 12: 00-24: 00, 10 and 2 days 00: 00-12: 00, 10 and 2 days 12: 00-24: 00, 10 and 3 days 00: 00-12: 00, 10 and 3 days 12: 00-24: 00 is respectively 800kWh, 900kWh, 1000kWh, 950kWh, 900 kWh; the power supply information {600, 800, 900, 1050, 900, 950} represents the predicted total power generation amounts of the plurality of power generation devices in the ranges of 600kWh, 800kWh, 900kWh, and 950kWh in 2030, 4:00 to 12:00 in 2030, 4: 12:00 to 24:00 in 2030, 5: 00 to 12:00 in 2030, 5: 00 to 24:00 in 2030, 6: 00 to 12:00 in 2030, 6: 00 to 24:00 in 2030, and 10, 6, and 12:00 to 24:00 in 2030.

It should be understood that the length of time of the historical power generation data is not directly related to the length of time of the future time period to be predicted. For example, the power supply information of the power generation device for three days in the future may be predicted based on the historical power generation data of the total power generation amount of the plurality of power generation devices for the past year. In addition, every 12 hours will also be regarded as one sub-period in a similar example hereinafter in this specification. Therefore, when the future time period or the time period of the historical power generation data is three days, there are six sub-time periods; when the future time period or the time period of the historical power generation data is two days in the future, there are four time periods. The description is made here, and the description of the division of the sub-period will not be repeated in the similar examples below in this specification.

In some embodiments, the total power supply prediction model may include, but is not limited to, a support vector machine model, a Logistic regression model, a naive bayes classification model, a gaussian distributed bayes classification model, a decision tree model, a random forest model, a KNN classification model, and a neural network model.

In some embodiments, the total power supply prediction model may be trained based on a large amount of historical power generation data.

In some embodiments, historical power generation data of the total amount of power of the plurality of power generation devices corresponding to the sample historical time period may be used as the training sample. The identification of the training sample may be historical power generation data of the total amount of power of each power generation device corresponding to the sample time period. Wherein the sample time period is a time period after the sample history time period. Inputting a large number of training samples with marks into an initial total power supply amount prediction model, updating parameters of the initial total power supply amount prediction model through training, and when the trained model meets preset conditions, finishing the training to obtain the trained total power supply amount prediction model.

In some embodiments, the historical power generation data of each power generation device may be input into the corresponding energy power supply prediction model, and the power supply information corresponding to each power generation device in the future time period may be determined. For example, historical power generation data of the wind power generation device can be input into a corresponding wind power supply prediction model, and power supply information corresponding to the wind power generation device in the energy internet in a future time period can be determined. For another example, historical power generation data of the solar power generation device can be input into the corresponding solar power supply prediction model, and power supply information corresponding to the solar power generation device in the energy internet in a future time period can be determined.

In some embodiments, the wind power supply prediction model may be used to obtain power supply information corresponding to a plurality of wind power generation devices in a future time period based on input data representing a relationship between the plurality of wind power generation devices. The input data of the wind power supply prediction model is historical power generation data of a plurality of wind power generation devices and relations among each wind power generation device (for example, relations among the wind power generation devices comprise distance relations, azimuth relations and the like). And the output data of the wind power supply prediction model is the power supply information corresponding to each wind power generation device in the future time period.

The input data may be data characteristic of wind power plants represented by a graph in a theoretical sense, and data characteristic of relations between wind power plants. The graph is a data structure composed of nodes and edges/paths, and may include a plurality of nodes and a plurality of edges/paths connecting the plurality of nodes. The nodes correspond to historical power generation data of the wind power generation devices, and the sides correspond to relationships among the wind power generation devices.

The attributes of the nodes may include historical power generation data of the wind power generators, wherein the historical power generation data of the wind power generators may include a historical time period during which the wind power generators supply power and a power supply amount corresponding to the time period, for example, an energy internet may include two wind power generators, and the historical power generation data of one wind power generator in the past three days is {100, 120, 150, 140, 130, 150}, and the historical power generation data of the other wind power generator in the past three days is {200, 210, 180, 160, 190, 170}, and the historical power generation data of the two wind power generators may be regarded as two nodes.

The attributes of the edges may include the direction and distance relationship between the wind power generation devices, for example, an energy internet includes two wind power generation devices, one of the wind power generation devices a is used as a central point, the other wind power generation device B is located, and the north direction 10M can be used as an edge of a node.

The wind power supply prediction model can be a graph neural network, the nodes, the edges and the attributes of the nodes and the edges are used as the input of the graph neural network, the output data corresponding to the nodes to be predicted can be obtained, and each node to be predicted corresponds to each wind power generation device. The graph neural network is a neural network directly acting on the graph, and can enable each node in the graph to exchange attribute information with each other through edges based on an information propagation mechanism, so that the node information of the node is continuously updated until a stopping condition is met. And outputting power supply information of the wind power generation device corresponding to the node in the future time period based on the updated node information of the node to be predicted corresponding to each wind power generation device.

For example, the historical power generation data of the past three days of the wind power generation device a and the wind power generation device B may be {100, 120, 150, 140, 130, 130}, {200, 210, 180, 160, 160, 170} as the input of the nodes of the wind power supply prediction model, and the relationship between the wind power generation devices a and B, that is, the wind power generation device B is located in the north direction 10M of the wind power generation device a as the input of the edge between the nodes of the wind power generation devices a and B in the wind power supply prediction model, to determine that the power supply information of the wind power generation devices a and B in the three days in the future is {120, 120, 140, 150, 150, 140}, {180, 200, 170, 150, 160, 170}, respectively.

The parameters of the wind power supply prediction model can be obtained through training. The training samples include historical power generation data of the plurality of sample wind power generation devices within the first sample historical time period, and relationships between the plurality of sample wind power generation devices. The label during training is historical power generation data of the wind power generation device in a plurality of second sample historical time periods, wherein the second sample historical time periods are time periods after the first sample historical time periods. Historical power generation data in the training samples can be directly obtained from historical data of an energy internet, and the relation between the sample wind power generation devices can be obtained by measuring the positions of the sample wind power generation devices.

In real life, it is difficult to determine the change law of different winds, but a certain wind has a front-back relationship in position, for example, a certain wind blows from south to north to a position A to a position B. When one wind power generation device generates power by using wind, the wind power generation device affects the size, direction and the like of the wind, and the power generation condition of the wind power generation device at other positions is affected. Therefore, some embodiments of the present disclosure may represent data among a plurality of wind power generation devices by way of a graph, and may better represent the relationship among the wind power generation devices and the mutual influence thereof while representing the characteristics of the historical power generation data of the wind power generation devices, so as to improve the accuracy of the power supply information of each wind power generation device in the future time period predicted by the wind power supply prediction model.

In some embodiments, the power supply information of the corresponding energy power generation device in the future time period may also be determined based on other energy power supply prediction models, for example, historical power generation data of the solar power generation device may be input into the solar power supply prediction model, and the power supply information corresponding to the solar power generation device in the future time period may be determined.

Illustratively, historical electricity utilization data {150, 170, 160, 180, 150, 170} of the solar power generation device in the past three days is input into the solar power supply prediction model, and power supply information of the solar power generation device in the future three days is determined to be {160, 170, 160, 190, 170, 200 }.

In some embodiments, the solar power supply prediction model may be trained and acquired based on a large amount of historical power generation data for the solar power plant.

In some embodiments, the historical power generation data of the solar power generation device for the sample historical time period may be used as a training sample. The identification of the training sample may be historical power generation data of the solar power plant for the sample time period. Wherein the sample time period is a time period after the sample history time period. Inputting a large number of training samples with marks into the initial solar power supply prediction model, updating parameters of the initial solar power supply prediction model through training, and obtaining the trained solar power supply prediction model after the training is finished when the trained model meets preset conditions. In some embodiments, the solar power generation device may be implemented based on a deep neural network.

In some embodiments, the power supply information of the power generation devices in the energy internet for the future time period is determined based on the power supply information of the respective power generation devices for the future time period.

In some embodiments, the power supply amount of each power generation device in the sub-time period of the future time period may be summed to determine the power supply information of the power generation devices in the energy internet in the future time period. Illustratively, a certain energy internet includes a wind power generation device a, a wind power generation device B and a solar power generation device, and it has been determined that power supply information of the wind power generation device a, the wind power generation device B and the solar power generation device on three days in the future is {120, 120, 140, 150, 150, 140}, {180, 200, 170, 150, 160, 170}, {160, 170, 160, 190, 170, 200}, respectively, so that it can be determined that power supply information of the power generation device on the energy internet on three days in the future is {460, 490, 470, 490, 480, 510 }.

And step 230, determining a distribution path of the power supply generated by the power generation device in the future time period based on the power supply information, and transmitting the distribution path of the power supply to the energy router. Step 230 may be performed by a second determination module.

The distribution path may refer to a path flow direction of the amount of power generated by the power generation device. Based on the distribution route, the usage of the amount of power generated by the power generation device can be specified. For example, the distribution path of the amount of power generated by the power generation apparatus in the future time period may be a load path, i.e., a path indicating the amount of power generated by the power generation apparatus for supplying power to the load.

In some embodiments, the distribution path of the amount of power generated by the power generation device in the future time period may be one or more. For example, the distribution path of the amount of power generated by the power generation device in the future time period may be a load path and an energy storage device path. For more on the load and the energy storage device, refer to fig. 3 and the related description thereof, and the detailed description thereof is omitted.

In some embodiments, the power supply information may be modeled or processed using various data analysis algorithms, such as regression analysis, discriminant analysis, and the like, to determine a distribution path of the amount of power generated by the power generation device in a future time period.

In some embodiments, the power supply information may be processed based on a first power threshold to determine a distribution path of the amount of power generated by the power generation device for a future time period. For more details on processing the power supply information based on the first power threshold and determining the distribution path of the power supply generated by the power generation device in the future time period, refer to fig. 3 and the related description thereof, and are not repeated herein.

An energy router may refer to a device that deploys electrical energy in the energy internet. In some embodiments, the distribution path of the power supply may be sent to the energy router. The energy router distributes the electric energy generated by the power generation device based on the received power supply amount distribution path.

In some embodiments, the energy router may control the flow of electrical energy within an energy internet. For example, the energy router may control the amount of power provided by the power supply device in an energy internet to flow to the load in the energy internet. In some embodiments, an energy router may control the flow of electrical energy between multiple energy internets. For example, an energy router may control the amount of power provided by a power supply device in one energy internet to flow to a load in another energy internet.

FIG. 3 is an exemplary flow diagram illustrating determining distribution paths for sub-supply amounts in accordance with some embodiments described herein. As shown in fig. 3, the process 230 includes the following steps. In some embodiments, the flow 230 may be performed by the second determination module.

In step 231, based on the power supply information, the power supply variation corresponding to two adjacent sub-periods in the future period is determined.

The sub-period refers to a period formed by dividing a future period. See fig. 2 and its associated description for more details regarding sub-periods.

The power supply variation amount can refer to the absolute variation amount of the power supply amount corresponding to two adjacent sub-time periods in the future time period of the power generation device in the energy internet.

In some embodiments, the power supply change amount may be determined based on the power supply amounts of two adjacent sub-periods of the future period. In some embodiments, when there are a plurality of future time periods, a change in the amount of power supplied between the last sub-period in the last future time period and the first sub-period in the next future time period may be determined to determine the subsequent power supply amount slicing.

In some embodiments, the amount of change in power supply may be determined by equation (1):

l_n→n+1＝|P_n+1-P_n| (1)

wherein l_n→n+1For the power supply variation amount, P, of the power generation device in the nth to the (n + 1) th time periods of the future time periods_n+1For the power supply quantity, P, of the power generation device in the energy internet in the (n + 1) th time slot in the future time slot_nAnd the power supply amount of the power generation device in the energy internet in the nth time period in the future time period is used. P_n+1And P_nSee fig. 2 and its associated description, for a manner of determiningAnd will not be described in detail.

Illustratively, the power supply amount of the power generation device in the energy internet in the first sub-period of the future time period is 150kWh, the power supply amount of the power generation device in the second sub-period of the future time period is 100kWh, and then the power supply variation amount of the power generation device in the energy internet from the first sub-period to the second sub-period is 50 kWh.

In step 232, it is determined whether the power supply variation is greater than the first power threshold for each power supply variation.

The first electric quantity threshold value can refer to a threshold value used for judging whether the power supply quantity of the power generation device in the energy internet changes excessively in different time periods.

In some embodiments, the first charge amount threshold may be predetermined. For example, the first charge threshold may be preset to 50 kWh.

When the power supply variation corresponding to two adjacent sub-time periods in the future time period is smaller than or equal to the first electric quantity threshold value, all the power supply quantity generated by the power generation device in the energy internet is provided for the load to use in the previous sub-time period of the two adjacent sub-time periods in the future time period.

The load may refer to a device using electric energy. In some embodiments, the load may be a device that utilizes electrical energy for production, for example, the load may be a machine tool that utilizes electrical energy to produce automotive parts. In some embodiments, the load may also be other devices, for example, the load may also be a smart home.

And 233, when the power supply variation is larger than the first electric quantity threshold, segmenting the power supply quantity generated in the sub-time period with the maximum power supply quantity in the sub-time period with the power supply variation, and obtaining the segmented sub-power supply quantity.

The sub-power supply amount may refer to a power supply amount obtained by dividing a power supply amount generated by a power generation device in the power internet.

In some embodiments, when the power supply variation is greater than the first power threshold, the time period with the smallest power supply amount in the sub-time period in which the power supply variation is located may not be processed, and the power supply amount generated in the time period with the largest power supply amount in the sub-time period in which the power supply variation is located may be split to obtain two split sub-power supply amounts. For example, when the amount of power supplied for the first sub-period of the future period is 180kWh, the amount of power supplied for the second sub-period is 100kWh, and the first power threshold is 50 kWh. Then, it may be determined that the second sub-period does not need to be sliced, and the power supply amount of the first sub-period needs to be sliced.

For more details on how to determine the magnitude of the sub-power supply amount, refer to step 234 in this specification, and will not be described here.

And 234, determining a distribution path of the sub-power supply amount, and sending the distribution path of the sub-power supply amount to the energy router, wherein one part of the split sub-power supply amount is used for supplying power to a load in the energy internet, and the other part of the split sub-power supply amount is used for transmitting to an energy storage device in the energy internet for storing energy.

The energy storage device is a device which can store electric energy and can supply the stored electric energy to a load for use.

In some embodiments, the sub-supply amount for transferring to the energy storage device in the energy internet for storing energy may be determined by equation (2):

p₁＝l_n→n+1-l₀ (2)

wherein p is₁Sub-supply for storing energy for energy storage means for transmission to an energy internet_n→n+1The power supply variation amount l of the power generation device from the nth sub-period to the (n + 1) th sub-period in the future period₀Is a first charge threshold.

In some embodiments, the amount of sub-power used to power a load in the energy internet may be determined by equation (3):

p₂＝max(P_n，P_n+1)-p₁ (3)

wherein p is₂Sub-supply for supplying a load in an energy internet, P_nFor the power supply of the n-th sub-period of the future time period, P, of the power generation device in the energy internet_n+1As in the energy InternetThe power supply amount p of the power generation device in the (n + 1) th sub-period in the future period₁And the sub-power supply quantity is used for transmitting the energy to the energy storage device in the energy Internet for storing energy.

In some embodiments, if the sub-period required to be sliced is a later-in-time period of two adjacent sub-periods, when the power supply variation of the next adjacent sub-period is determined, the determination is performed based on the sub-power supply amount for supplying power to the load that is sliced in the later-in-time sub-period of the two adjacent sub-periods and the power supply amount of the next sub-period. For example, the preset future time period may be two days in the future, and every 12 hours in the two days in the future is taken as a sub-time period, the power supply information of the energy internet on the two days in the future is {100, 180, 120, 130}, and the first power threshold is 40 kWh. Since the amount of change in the power supply between the first sub-period with the power supply of 100kWh and the second sub-period with the power supply of 180kWh is greater than the first power threshold value, the second sub-period needs to be sliced, wherein the power supply of 40kWh is used for energy storage and the power supply of 140kWh is used for power supply of the load. At this time, the power supply variation amount between the sub power supply amount of 140kWh for supplying power to the load in the second sub-period and the power supply amount of 120kWh for the third sub-period is smaller than the first power amount threshold, so that the power supply amount in the second sub-period is not cut again, and the power supply amount in the third sub-period is not cut.

In some embodiments, the power supply amount of the sub-period with the excessive power supply variation of two adjacent sub-periods may also be divided in other manners.

In some embodiments, the distribution path of the sub-supply amount may be determined based on the usage of the different sub-supply amounts, and the distribution path of the sub-supply amount may be transmitted to the energy router. The sub-power supply quantity for supplying power to the load in the energy internet can be transmitted to the load path, and the energy storage device for transmitting the power to the energy internet stores energy to obtain the sub-power supply quantity which is transmitted to the energy storage device path.

When the power supply amount of the adjacent sub-time periods is changed too much, the voltage fluctuation amplitude in the energy Internet is caused to be too large, the normal work of the energy Internet is influenced, and the load in the energy Internet is easily damaged. By segmenting the power supply quantity of the adjacent sub-time periods with large power supply variation, the problem that the voltage fluctuation amplitude in the energy Internet is too large due to too large power supply variation of the adjacent sub-time periods is solved, the utilization efficiency of energy is improved, the voltage supplied to the load is stabilized, the loss possibly caused by too large voltage fluctuation amplitude to the load in the energy Internet is reduced, and the service life of the load is prolonged. Some embodiments of the present disclosure may determine not only the power supply variation of the adjacent sub-time periods in the future time period, but also determine the power supply variation of the adjacent sub-time periods between multiple future time periods, so as to avoid negative effects on the energy internet caused by the too large power supply variation between multiple future time periods.

FIG. 4 is an exemplary flow diagram for powering a load based on a power generation device and an energy storage device, according to some embodiments described herein. As shown in fig. 4, the process 400 includes the following steps:

step 410, determining whether the power supply amount for supplying power to the load in the sub-time period in the future time period is greater than a second power threshold. Step 410 may be performed by a decision module.

The second power threshold may refer to a minimum amount of power required to maintain a normal operation of a load in the energy internet.

In some embodiments, the second charge amount thresholds for the plurality of sub-periods of time within the future time period may be the same or different.

In some embodiments, the second charge amount threshold may be determined based on the load.

In some embodiments, the second charge threshold may be determined based on a minimum amount of charge required to operate the load in a sub-period of time within the future period of time in the energy internet. Wherein, the minimum electric quantity required by the load can be preset. For example, if the energy internet is operated with a load that consumes at least 20kWh per hour, and each sub-period of the future time period is 8 hours long, then the second threshold amount of power may be determined to be 160 kWh.

In some embodiments, the second power threshold may be determined based on a prediction of power usage by the load for each sub-period of time in a future period of time based on a load power usage model. For example, if the load electricity usage model determines that the electricity usage of the load for a sub-period of the future time period is 150kWh, the second electricity threshold corresponding to the sub-period may be determined to be 150 kWh. For more contents of predicting the power consumption of each sub-period load in the future period, refer to fig. 5 and its related description, which are not repeated herein.

The second power threshold is determined by predicting the power usage of the load for the sub-period in the future period. Such operation can make the data more realistic, thereby ensuring the normal operation of the load in the energy internet.

In some embodiments, the second charge amount threshold may also be determined in other ways, for example, it may be directly preset.

In some embodiments, when the power supply amount of the power generation device in the energy internet in the sub-time period in the future time period is larger than or equal to the second power threshold value, the load is supplied based on the power generation device in the energy internet.

In some embodiments, it may also be determined whether an amount of power supplied to power the load for a sub-period of the future period is greater than a third power threshold.

The third power threshold may refer to a maximum power required to maintain a normal operation of a load in the energy internet.

In some embodiments, the third charge amount threshold may be determined based on the load. In some embodiments, the third charge threshold may be determined based on a highest charge required to operate the load in a sub-period of time within the future period of time in the energy internet. Wherein the maximum amount of power required by the load may be preset. For example, if the energy internet is operated at a load that consumes at most 30kWh per hour, and each sub-period in the future is 8 hours long, then the third threshold amount of power can be determined to be 240 kWh.

In some embodiments, the third charge threshold may also be determined in other ways, for example, it may be preset directly.

In some embodiments, when the power supply amount for supplying power to the load in the sub-period of the future period is greater than the third power threshold, a part of the power supply amount greater than the third power threshold is split, and the part of the power supply amount is transmitted to the energy storage device in the energy internet for energy storage. For example, the amount of power supplied for a sub-period of the future time period is 300kWh, and the third threshold amount of power is 240 kWh. Then, the power supply amount of the sub-time period is divided, and a part of the power supply amount of the sub-time period, namely the power supply amount of 60kWh, of which the power supply amount is larger than the third power threshold value is transmitted to an energy storage device in the energy internet for energy storage, and the divided power supply amount of the sub-time period, namely the power supply amount of 240kWh, is used for supplying power to the load. In some embodiments, when the amount of power supplied to the load in the sub-period of the future period is greater than the third threshold amount of power, the amount of power supplied does not need to be sliced based on the third threshold amount of power.

And step 420, when the power supply amount is smaller than the second power threshold, supplying power to the load based on the power generation device and the energy storage device in a sub-time period in the future time period. Step 420 may be performed by the power module.

In some embodiments, when the power supply amount of the sub-period in the future period is less than the second power threshold, in the sub-period in the future period, the energy storage device is added to supply power to the load on the basis of the power generation device pair.

In some embodiments, the amount of power supplied by the energy storage device to power the load may be determined based on a second power threshold. The amount of power supplied by the energy storage device to the load may be determined by equation (4):

l_en＝l₂-P_n (4)

wherein l_enThe amount of power supplied to the load by the energy storage device in the nth sub-period of the future period, l₂Is the second charge threshold, P_nFor generating electricity in the energy internetThe amount of power supplied in the nth sub-period in the future period.

For example, if the amount of power supplied during a sub-period of the future time period is 100kWh and the second power threshold is 150kWh, it can be determined that the amount of power required by the energy storage device to power the load during the sub-period is 50 kWh.

In some embodiments, the power supply amount of the load supplied by the energy storage device may also be determined in other manners, for example, the power supply amount of the load supplied by the energy storage device is directly preset in advance.

In some cases, since the power supply variation amount of two adjacent sub-periods in the future period is too large, the power supply amounts of the two sub-periods in the future period need to be split, so that the split power supply amount is smaller than the second power supply amount, which may cause the load to fail to work normally. In some cases, due to weather changes, the electric quantity provided by the power generation device is low, and the load can also be caused to work abnormally, when the power supply quantity provided by the power generation device is too small to maintain the load to work abnormally, the load is supplied with power based on the energy storage device on the basis of supplying power to the load based on the power generation device, so that the normal operation of the energy internet is ensured. In addition, the part of the power supply quantity of the power generation device in the sub-time period, which is greater than the third electric quantity threshold value, is segmented, on the premise that the normal operation of the load in the energy Internet is ensured, the redundant electric quantity generated by the power generation device is stored, and the utilization rate of energy is improved.

FIG. 5 is yet another exemplary flow chart illustrating determining a distribution path for an amount of power generated by a power generation device over a future time period according to some embodiments of the present description. As shown in fig. 5, the process 500 includes the following steps. In some embodiments, the flow 230 may be performed by the second determination module.

Step 510, weather forecast information is obtained.

The weather forecast information may refer to forecast information on weather in a future time period. The weather forecast information may include cloud drawings, temperature, wind power, sunshine intensity, sunshine time, etc. In some embodiments, the weather forecast information may be obtained in a variety of ways, for example, directly over a network.

And step 520, adjusting the power supply information based on the weather forecast information to obtain the adjusted power supply information.

In some embodiments, the power supply information may be adjusted according to a preset rule based on the weather forecast information, so as to obtain the adjusted power supply information. The preset rule may be preset empirically. For example, the power generation device in the energy internet is a solar power generation device, the power supply information for predicting weather forecast information to three days in the future is {600, 700, 650, 720, 680, 730}, but the predicted cloud amount in the second time period with 700kWh is larger than the cloud amount threshold value according to the acquired cloud images of the three days in the future, so that the power supply amount in the second time period in the power supply information is multiplied by an adjustment coefficient of 0.6 according to a preset rule, and the power supply information of the future time period after adjustment is {600, 420, 650, 720, 680, 730}, wherein the cloud amount threshold value and the adjustment coefficient can be determined in advance. For the prediction of the power supply information in the future time period, refer to fig. 2 and the related description thereof, which are not described herein again.

Through adjusting the predicted power supply information in the future time period based on the weather forecast information, the adjusted power supply information can be closer to the actual situation, the prediction accuracy is improved, and the normal operation of the energy internet is ensured.

In some embodiments, weather forecast information may also be used as an input to the energy supply prediction model. And determining power supply information of the power generation device in a future time period based on the weather forecast data and the historical power generation data. For example, weather forecast data and historical power generation data of the solar power generation device can be input into the solar power supply prediction model, and power supply information of the solar power generation device in a future time period can be determined. Accordingly, when the solar power supply prediction model is trained, the training data may include historical weather data in addition to the training samples of the solar power supply prediction model described in fig. 2. Wherein, the historical weather data can be directly obtained through a network.

In some embodiments, when the power consumption of the load in the energy internet is affected by weather, the power consumption of the load in each sub-period in the future period may be further determined based on the weather forecast information. The weather forecast information of each sub-time period in the future time period can be input into the load electricity utilization prediction model, and the load electricity utilization quantity of each sub-time period in the future time period is output. For example, when the load is an air conditioner, the amount of electricity used by the air conditioner in each sub-period in the future period may be determined based on weather forecast information in the future period.

In some embodiments, the load power usage prediction model may include, but is not limited to, a support vector machine model, a Logistic regression model, a naive bayes classification model, a gaussian distributed bayes classification model, a decision tree model, a random forest model, a KNN classification model, and a neural network model.

In some embodiments, the load power usage prediction model may be trained based on a large amount of historical data.

In some embodiments, the weather information corresponding to each historical time period may be a training sample. The identification of the training samples may be the power usage of the load for each historical time period. The weather information corresponding to each historical time period can be acquired from a network, and the power consumption of the load corresponding to each historical time period can be acquired from historical data of the energy internet. Inputting a training sample with an identifier into the initial load power utilization prediction model, updating parameters of the initial load power utilization prediction model through training, and obtaining the trained load power utilization prediction model after the training is finished when the trained model meets preset conditions.

And step 530, determining a distribution path of the power supply generated by the power generation device in the future time period based on the adjusted power supply information, and sending the distribution path of the power supply to the energy router.

The flow of step 530 is substantially the same as step 230, and is described with reference to fig. 2 and related descriptions, which are not repeated herein.

It should be noted that the above descriptions about the respective flows are only for illustration and explanation, and do not limit the applicable scope of the present specification. Various modifications and alterations to the various processes described above will become apparent to those skilled in the art in light of the present disclosure. However, such modifications and variations are intended to be within the scope of the present description.

The present specification also provides a computer-readable storage medium. The storage medium stores computer instructions, and after the computer reads the computer instructions in the storage medium, the computer realizes the method for optimizing the energy Internet.

Through the description of the above embodiments, those skilled in the art will understand that, for convenience and simplicity of description, only the division of the above functional modules is used as an example, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of a specific device is divided into different functional modules to complete all or part of the above described functions.

In the embodiments provided in this application, it should be understood that the disclosed structures and methods may be implemented in other ways. For example, the above-described embodiments with respect to structures are merely illustrative, and for example, a module or a unit may be divided into only one logic function, and may have another division manner in actual implementation, for example, a plurality of units or components may be combined or may be integrated into another structure, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, structures or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed to a plurality of different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or partially contributed to by the prior art, or all or part of the technical solutions may be embodied in the form of a software product, where the software product is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An energy internet optimization method is characterized by comprising the following steps:

2. The method as claimed in claim 1, wherein the determining a distribution path of the amount of power generated by the power generation device in the future time period based on the power supply information and sending the distribution path of the amount of power to an energy router comprises:

3. The method for optimizing energy internet according to claim 1 or 2, further comprising:

judging whether the power supply amount for supplying power to the load in the sub-time period in the future time period is smaller than a second power threshold value;

when the power supply amount is smaller than the second power threshold value, the load is supplied with power based on the power generation device and the energy storage device in the sub-time period in the future time period.

4. The method as claimed in claim 1, wherein the determining the distribution path of the power supply generated by the power generation device in the future time period based on the power supply information and sending the distribution path of the power supply to an energy router comprises:

acquiring weather forecast information;

5. An energy internet optimization system, comprising:

6. The system according to claim 5, wherein the second determining module is specifically configured to:

7. The system for optimizing energy internet as claimed in claim 5 or 6, wherein the system further comprises: the judging module is used for judging whether the power supply amount for supplying power to the load in the sub-time period in the future time period is less than a second electric quantity threshold value or not;

8. The system for optimizing energy internet as claimed in claim 6, wherein the second determining module further comprises:

acquiring weather forecast information;

9. An energy internet optimization device, comprising a processor, wherein the processor is used for executing the energy internet optimization method according to any one of claims 1 to 4.

10. A readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer performs the method for optimizing the energy internet according to any one of claims 1 to 4.