CN110717779A

CN110717779A - Electric power transaction system, method and application thereof

Info

Publication number: CN110717779A
Application number: CN201910824310.8A
Authority: CN
Inventors: 胡师彦; 董倩
Original assignee: Kunshan Quantum Kunci Quantum Technology Co Ltd
Current assignee: YIWO ARTIFICIAL INTELLIGENCE TECHNOLOGY (JIANGSU) Co.,Ltd.
Priority date: 2019-09-02
Filing date: 2019-09-02
Publication date: 2020-01-21

Abstract

The invention provides an electric power transaction system, an electric power transaction method and application thereof, wherein the electric power transaction method comprises the steps of respectively predicting the generated energy and the load demand of each user in a microgrid in the next transaction time window according to the preset time window of the microgrid electric power transaction system, and dividing all the users in the microgrid into an electric power seller set and an electric power buyer set based on the obtained generated energy and load demand of each user; establishing an electricity purchasing cost model and a seller benefit model, and collecting electric power to each electric power seller on the condition of minimizing the electricity purchasing cost of a system dispatcher and maximizing the benefit of the seller; and establishing a buyer benefit model, and distributing the power to the power buyers on the condition of maximizing the sum of the benefits of all the buyers. The invention solves the problem of unbalanced power supply and demand of a single user by establishing a reliable and stable power trading system in the community micro-grid, thereby not only improving the benefit of the user, but also reducing the interference to the main grid.

Description

Electric power transaction system, method and application thereof

Technical Field

The invention belongs to the technical field of electric power transaction, and particularly relates to an electric power transaction system, an electric power transaction method and application thereof.

Background

Big data technology, refers to the ability to quickly obtain valuable information from a wide variety of types of data. Electric power is the practice of big data concepts, technologies and methods in the electric power industry, and relates to each link of power generation, power transmission, power transformation, power distribution, power utilization and scheduling. With the construction of smart power grids and the application of the Internet of things, electric big data rapidly grow. By mining the big data of the electric power, the development requirement of the electric power industry can be improved, and the development requirement of economy can be served.

The artificial intelligence is to make the computer simulate the human logic thinking and advanced intelligence, and can be divided into three levels of computational intelligence, perception intelligence and cognitive intelligence: the intelligent computing is to make the machine/computer have high-performance computing capability and even exceed the computing capability of people to process mass data; the perception intelligence is to enable the machine to perceive the surrounding environment like a human, and comprises the following steps of hearing, vision, touch and the like; cognitive intelligence is to make a machine have human rational thinking ability and make correct decision. The integration of three kinds of ability finally lets the machine realize humanoid wisdom to comprehensive supplementary even substitute human work, with the help of artificial intelligence technique, can predict each user's photovoltaic power generation capacity and load demand in the little electric wire netting of community.

The mathematical modeling is to establish a mathematical model according to an actual problem, solve the mathematical model, and then solve the actual problem according to a result. The modeling process comprises model preparation, model assumption, model establishment, model solution and model inspection. The model preparation is to describe the problem by a mathematical language based on the understanding of the actual background of the problem; the model assumption is that some proper assumptions are provided according to the purpose of modeling, and necessary simplification is carried out on the problem; the model building is to use a proper mathematical tool to depict the mathematical relationship among the variable constants and build a corresponding mathematical structure; the model solution is to calculate all parameters in the model by using some algorithms; the model test is to compare the calculation result with the actual result to verify the accuracy of the model.

The community microgrid architecture adopted by the existing electric power transaction system generally requires a user side to install an energy storage device, but the energy storage device is high in cost, and the user is difficult to attract to install the energy storage device by himself under the condition that government is not strongly subsidized, promoted and installed, so that a novel energy storage architecture is needed; in addition, the transaction mechanisms in the current electric power transaction system are mainly classified into centralized and point-to-point, the point-to-point mechanism is very complex and is difficult to implement in a small-scale market such as a community microgrid, and the existing centralized mechanism lacks a fair pricing strategy and lacks protection on user privacy, so an improved transaction mechanism is needed to overcome the defects. Finally, existing power trading systems are based on assumptions, and do not take into account prediction errors, so a model is needed to handle power prediction errors.

Disclosure of Invention

In view of the above drawbacks of the prior art, an object of the present invention is to provide a power trading system, a method and an application thereof, which are used to solve the technical problem of unbalanced power supply and demand of each user in a microgrid in the power trading system in the prior art.

To achieve the above and other related objects, the present invention provides a power transaction method, including:

respectively predicting the generated energy and/or the load demand of each user in the microgrid in the next transaction time window according to a preset time window of the microgrid power transaction system, and dividing all users in the microgrid into a power seller set and a power buyer set based on the obtained generated energy and/or load demand of each user;

establishing an electricity purchasing cost model and a seller benefit model, and calculating the electricity purchasing cost of a system dispatcher and the benefit of a seller through the electricity purchasing cost model and the seller benefit model;

collecting power to each power seller on condition of minimizing the purchase cost of the system dispatcher and maximizing the benefit of the seller;

establishing a buyer benefit model, and calculating the sum of the benefits of the buyer through the buyer benefit model;

electricity is distributed to electricity buyers on the condition of maximizing the sum of the buyer's benefits.

In an embodiment, the step of predicting the power generation amount and the load demand amount of each user in the microgrid in the next transaction time window respectively according to the preset time window of the system includes:

acquiring the generated energy and the load demand of each user in the microgrid in real time to serve as electric power big data;

preprocessing the electric power big data to select proper characteristics and create a training sample and a testing sample;

training a user power prediction model based on the training samples;

evaluating the user power prediction model through the test sample to obtain an optimal user power prediction model;

and predicting the power generation amount and/or the load demand of the user in the next transaction time window through the optimal user power prediction model.

In one embodiment, the method further comprises, performing a compensation clearing on the transaction body based on the prediction error.

In one embodiment, the step of clearing the transaction subject for compensation based on the prediction error comprises:

performing compensation clearing according to the difference between the actual selling power of each power seller and the power collected to the seller; and/or

And performing compensation clearing according to the difference between the actual purchased power of each power buyer and the power distributed to the buyer.

In one embodiment, the method further comprises adaptively adjusting the transaction time window based on the prediction error and system operating pressure.

To achieve the above and other related objects, the present invention also provides an electric power transaction system, including:

the power forecasting module is used for respectively forecasting the generated energy and/or the load demand of each user in the microgrid in the next transaction time window according to the preset time window of the microgrid transaction system, and dividing all the users in the microgrid into a power seller set and a power buyer set based on the obtained generated energy and/or load demand of each user;

the electric power collection module is used for establishing an electricity purchasing cost model and a seller benefit model, calculating the electricity purchasing cost of a system dispatcher and the benefit of a seller through the electricity purchasing cost model and the seller benefit model, and collecting electric power to each electric power seller on the condition of minimizing the electricity purchasing cost of the system dispatcher and maximizing the benefit of the seller; and

the electric power distribution module is used for establishing a buyer benefit model and calculating the sum of the benefits of the buyers through the buyer benefit model, and distributing electric power to the electric power buyers on the condition of maximizing the sum of the benefits of the buyers.

In one embodiment, the power prediction module comprises:

the data loading submodule is used for acquiring the generated energy and the load demand of each user in the microgrid in real time to serve as electric power big data;

the preprocessing submodule is used for preprocessing the electric power big data so as to select proper characteristics and create a training sample and a testing sample;

the training sub-module is used for training a user power prediction model based on the training samples;

the evaluation sub-module is used for evaluating the user power prediction model through the test sample so as to obtain an optimal user power prediction model;

and the predicting submodule is used for predicting the power generation amount and/or the load demand of the user in the next transaction time window through the optimal user power predicting model.

In one embodiment, the system further comprises a prediction error processing module for performing compensation clearing on the transaction subject according to the prediction error.

In one embodiment, the prediction error processing module comprises:

for performing compensation clearing according to the difference between the actual sold electric power of each electric power seller and the electric power collected to the electric power seller; and/or

A buyer compensation liquidation submodule for liquidation of compensation according to a difference between actual purchased power of each electricity buyer and power distributed to the electricity buyer.

In an embodiment, the microgrid trading system further comprises a time window adjusting module for adjusting the time window according to the prediction error and the system operating pressure.

To achieve the above and other related objects, the present invention also provides a microgrid comprising

The system scheduler is connected with a main power grid and comprises a cloud energy storage device and the electric power transaction system;

the user side is connected with the system scheduler and comprises a plurality of users, and each user is provided with an electronic terminal, a load and a power generation device which are connected with the system scheduler through the electronic terminal;

wherein the system scheduler performs power trading by controlling the power trading system.

According to the invention, a reliable and stable power trading system is established in the community micro-grid, so that the problem of unbalanced power supply and demand of a single user is solved;

compared with the currently adopted surplus electricity internet access, the method not only greatly improves the electricity selling profits of sellers, but also greatly reduces the electricity purchasing cost of buyers and the interference on the main power grid;

the invention provides a compensation clearing model aiming at electric power prediction errors, and solves the problem of economic loss of a trading subject caused by the prediction errors.

Drawings

Fig. 1 shows a block diagram of the microgrid according to the present invention.

Fig. 2 is a block diagram of the power transaction system according to the present invention.

FIG. 3 is a schematic diagram of a time window based predictive transaction process according to the present invention.

Fig. 4 is a flow chart illustrating a power transaction method according to the present invention.

FIG. 5 is a schematic diagram of a prediction model learning algorithm of the power prediction module of the present invention.

FIG. 6 is a schematic diagram of power transactions among users in the community microgrid according to the present invention.

FIG. 7 is a schematic diagram showing the relationship between the convergence time of the optimal power pricing algorithm and the total number of users in the microgrid.

Fig. 8 is a schematic diagram showing the relationship between the convergence time of the power distribution algorithm and the total number of users in the microgrid.

Fig. 9 shows a compensation clearing flow diagram for the electric power seller of the present invention.

FIG. 10 shows a compensation clearing flow diagram for the electricity buyer of the present invention.

Fig. 11 is a block diagram showing the structure of the service device of the present invention.

Fig. 12 shows user power generation amount prediction data in an example of the present invention.

FIG. 13 illustrates predicted data for user power usage in an example of the invention.

Fig. 14 is a schematic diagram illustrating a comparison between the power transaction and the influence on the stability of the main grid in the power-on-grid mode according to the present invention.

Fig. 15 is a schematic diagram illustrating a comparison between the electricity transaction and the electricity purchasing cost of the buyer in the power-on-net mode according to the present invention.

Fig. 16 is a schematic diagram illustrating a comparison between power transaction and the electricity selling profit of the seller in the internet remaining power mode according to the present invention.

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.

Please refer to fig. 1-16. It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

Fig. 1 shows a block diagram of a community microgrid. As shown in fig. 1, the microgrid comprises a system scheduler 200 and a user side 300 which are connected with each other; the system dispatcher 200 is connected to a main grid 400, and can purchase electric power from the main grid 400 or sell surplus electric power to the main grid 400; the system scheduler 200 is used for completing electric power transaction by scheduling electric power; the user side 300 includes a plurality of community microgrid users, each of the users is provided with an electronic terminal 5, and a load 6 and a power generation device 7 connected with the system scheduler 200 through the electronic terminal 5, the load 6 refers to a device consuming power of the user, the power generation device 7 is a power generation device, the power generation device 7 may be a photovoltaic power generation device or a wind power generation device, for example, the electronic terminal 5 is used for measuring and recording power data produced and consumed by the user in real time, and transmitting the recorded data to the system scheduler 200 when necessary, and in the present invention, the electronic terminal 5 may be a bidirectional metering smart meter, for example.

As shown in fig. 1 and fig. 2, in order to solve the problem of unbalanced power supply and demand of a single user during a power transaction process, an embodiment of the present invention discloses a centralized power transaction system 100 based on big data and artificial intelligence in a community microgrid, where the power transaction system 100 may be, for example, built in the system scheduler 200, and is centrally controlled by the system scheduler 200 to complete a power transaction, and the power transaction system 100 mainly includes three progressive modules, namely, a power prediction module 1, a power transaction module 2, and a prediction error processing module 3. The power prediction module 1 is used for predicting the power generation amount and the load demand of each user in the microgrid in the next transaction time window respectively according to a preset time window of the microgrid transaction system, and dividing all the users in the microgrid into a power seller set and a power buyer set based on the obtained power generation amount and the load demand of each user; the electric power transaction module 2 comprises an electric power collection module and an electric power distribution module, wherein the electric power collection module is used for establishing an electricity purchasing cost model and a seller benefit model, calculating the electricity purchasing cost of a system dispatcher 200 and the benefit of a seller through the electricity purchasing cost model and the seller benefit model, collecting electric power to each electric power seller on the condition of minimizing the electricity purchasing cost of the system dispatcher 200 and maximizing the benefit of the seller, and the electric power distribution module is used for establishing a buyer benefit model, calculating the sum of the benefits of buyers through the buyer benefit model, and distributing electric power to the electric power buyers on the condition of maximizing the sum of the benefits of the buyers; the prediction error processing module 3 is used for carrying out compensation clearing on the transaction main body according to the prediction error. The specific operations performed by the power prediction module 1, the power transaction module 2 and the prediction error processing module 3 will be described in detail below with reference to fig. 4.

It should be noted that the power transaction system 100 and the method of the present invention are based on a cloud energy storage architecture and a time window prediction transaction model, where the cloud energy storage architecture refers to that an energy storage device is not installed at the user side 300, but a larger cloud energy storage device 8 is installed at the system scheduler 200, and each user shares the cloud energy storage device 8. . Fig. 3 shows a schematic diagram of a time window prediction transaction flow, as shown in fig. 3, each transaction time period is divided into three phases, namely a transaction mechanism running phase (first phase), a contract execution phase (second phase) and a prediction error processing phase (third phase). In the time period [ delta t, 2 delta t ], the transaction mechanism operation stage determines how the seller and the buyer transact by predicting the power supply and demand conditions of each user in the community microgrid in the next time period [2 delta t, 3 delta t ], and then the two parties sign a power transaction contract. Then, during the contract execution phase within time period [2 Δ t, 3 Δ t ], system scheduler 200 completes the power transaction between the customers by scheduling power. Finally, in the prediction error processing stage in [2 Δ t, 3 Δ t ], the system processes the power prediction error of the last transaction time period (i.e. time period [ Δ t, 2 Δ t ]).

Fig. 4 is a flowchart of the power transaction method of the present invention executed by the power transaction system 100 in fig. 1, and the power transaction method will now be described with reference to fig. 4.

In step S1, the system is initialized to initialize the time window Δ t, the error threshold δ, and the system pressure threshold ∈ with the initial value of the error Err set to 0 and the initial value of the system operating pressure P set to 0.

In step S2, it is determined whether the error value Err and the system operating pressure P are both less than the respective thresholds δ and ε.

If the result of the map determination is yes, step S3 is executed.

If the determination result is "no", step S8 is executed.

In step S3, power prediction is performed, power generation amount and load demand amount of each user in the microgrid in a next transaction time window are respectively predicted according to a preset time window of the microgrid power transaction system 100 (step S31), and all users in the microgrid are divided into a power seller set and a power buyer set based on the obtained power generation amount and load demand amount of each user (step S32).

In step S31, the step of predicting the power generation amount and the load demand amount of each user in the microgrid in the next trading time window according to the preset time window of the microgrid power trading system 100 includes:

step S311: all users in the community microgrid are represented by a set N:

N＝{1，2，...，i，...，n}

wherein i is a number of a user in the community microgrid (the numbers are the same when not described later);

step S312: the system collects the power data of the production and consumption of the user measured by the bidirectional metering intelligent electric meter in real time, and respectively forms the historical records of the minute level of the generated energy and the electricity consumption of each user as the big data of the power;

step S313: the electric power prediction module 1 preprocesses the electric power big data recorded in the last step, selects proper characteristics and creates a large-scale sample, wherein the preprocessing process comprises the steps of clustering, pre-filtering, normalization, characteristic selection and the like;

step S314: the power prediction module 1 adopts a radial basis function neural network to train a user power prediction model based on a training sample, and specifically, the power prediction module 1 adopts the radial basis function neural network to respectively train a user power generation amount prediction model and a user power consumption amount prediction model based on the training sample;

step S315: the power prediction module 1 evaluates the model through the test sample to obtain an optimal user power prediction model, and specifically, the power prediction module 1 evaluates the model through the test sample to obtain an optimal photovoltaic power generation prediction model and an optimal load demand prediction model;

step S316: the photovoltaic power generation prediction model predicts the photovoltaic power generation amount of the user i in the next transaction time window t asThe load demand forecasting model forecasts the load demand of the user i in the next transaction time window t to be

Fig. 5 shows a schematic diagram of a prediction model learning algorithm of the power prediction module 1. As shown in fig. 5, the power prediction module 1 includes a power data loading sub-module 11, configured to obtain, in real time, a power generation amount and a load demand amount of each user in the microgrid as power big data (corresponding to step S312); a preprocessing submodule 12, configured to preprocess the power big data to select an appropriate feature and create a training sample and a test sample (corresponding to step S313); a training sub-module 13 for training a user power prediction model based on the training samples (corresponding to step S314); an evaluation sub-module 14, configured to evaluate the power prediction model through the test sample to obtain an optimal user power prediction model (corresponding to step S315); and the prediction sub-module 15 is used for predicting the power generation amount and the load demand amount of the user in the next transaction time window through the optimal power prediction model (corresponding to the step S316). The user power prediction model comprises the user power generation amount prediction model and the user power consumption amount prediction model, and the optimal user power prediction model comprises the photovoltaic power generation prediction model and the load demand prediction model.

In step S32, the step of dividing all the users in the microgrid into a power seller group and a power buyer group based on the acquired power generation amount and load demand amount of each user includes:

step 321: based on the prediction in step S31

And

calculating net output electric quantity of user i in next transaction time window t

Step 322: when in use

When the user i is a power buyer, when

When the user i is the power seller, when

In time, the power supply and demand of the user i are balanced, so that the user i does not participate in power transaction;

step 323: all users in the community microgrid are divided into a set of electricity buyers B and a set of electricity sellers S, wherein

In step S4, the power transaction module 2 performs power transaction, and the present invention proposes a centralized power transaction scheme, where the power transaction is divided into two phases, namely, first, the system dispatcher 200 collects power from the set of sellers (corresponding to step S41 below), and then the system dispatcher 200 distributes power to the set of buyers (corresponding to step S42 below), that is, the power transaction module 2 includes a power collection module and a power distribution module. The power transaction diagram among users in the community microgrid is shown in fig. 6.

In step S41, in the power collection phase, the power collection module builds a purchase cost model and a seller benefit model, and calculates a purchase cost and a seller benefit of the system dispatcher 200 through the purchase cost model and the seller benefit model, so as to collect power to each power seller on the condition of minimizing the purchase cost of the system dispatcher 200 and maximizing the seller benefit.

Specifically, step S41 includes the following sub-steps:

step S411: establishing a power purchase cost model of the system scheduler 200:

i∈S，j∈B

wherein: p is the internal electricity transaction price proposed by the system dispatcher 200, the electricity purchase cost C of the system dispatcher 200_DSOTwo parts are included, the plus left item represents the cost of the system dispatcher 200 to purchase power from all vendors within the microgrid, and the right item represents the cost of the system dispatcher 200 to purchase additional demand power from the main grid 400;

step S412: establishing a benefit model of the power seller:

U_i＝k_iln(1+D_i)+p(G_i-D_i)

constraint conditions are as follows:

wherein benefit U of seller i_iComposed of two parts, the left item of plus sign represents seller i through consuming power D_iSatisfaction obtained, k_iIs the electricity usage benefit parameter for seller i, and the plus right term is the benefit that seller i obtains by selling excess electricity to system scheduler 200, among constraints

Is the lowest load demand that seller i must meet;

step S413: the mathematical formalization defines the optimization problem of the power phase collected by the system scheduler 200:

an objective function:

constraint conditions are as follows:

wherein the system dispatcher 200 seeks an optimal internal electricity trading price with the goal of minimizing the electricity purchasing cost and maximizing the seller's benefit;

step S414: solving the optimization problem in the power collection phase by using a distributed iterative algorithm:

the inputs to the algorithm include the price of electricity sold by the main grid 400And the price of electricity purchase

Set S of seller and set B of buyer, and photovoltaic power generation G corresponding to set S of seller and set B of buyer_iAnd load demand D_iSeller electricity usage efficiency parameter k_iThe output is the optimal power transaction price p inside the community microgrid^*The specific process is as follows:

wherein, firstly, initialization is carried out, the optimal internal electric power trade price is set as the electricity purchasing price of the main power grid 400, the minimum electricity purchasing cost of the system scheduler 200 is set as the price (Line 1-2) of all the electric power needed for purchasing from the main power grid 400, then a cycle iteration process is started, and the process is carried out in the step of

Within range, go through p such that

Minimum (Line 3 ~ 14), last p returned by the algorithm^*The optimal internal electric power transaction price is obtained, and the optimal internal electric power transaction price p is obtained^*Then, the electric energy consumed by the seller i in response to the optimal electricity price for maximizing the electricity selling profit can be calculated

In turn, the system dispatcher 200 collects from seller iThe electric energy of (1). Fig. 7 is a schematic diagram illustrating a relationship between the convergence time of the optimal power pricing algorithm (distributed iterative algorithm) and the number of users in the community microgrid, and as can be seen from fig. 7, the convergence time of the optimal power pricing algorithm is in a direct proportion to the number of users in the community microgrid.

In step S42, in the electricity distribution phase, a buyer benefit model is built through the electricity distribution module, and the sum of the benefits of the buyers is calculated through the buyer benefit model, so as to distribute electricity to the electricity buyers on the condition of maximizing the sum of the benefits of the buyers.

Specifically, the step S42 includes the following sub-steps:

step S421: establishing a comprehensive grading model of the power buyer:

wherein the comprehensive score PI of buyer i_iIs composed of three parts including historical power contribution ratio of buyer i

Current power demand fraction

And reliability

C_iIs the total amount of electricity sold to the community microgrid by buyer i within the statistical period of the system scheduler 200, C_TotalIs the total amount of electricity, D, sold to the community microgrid by all users during the statistical period of the scheduler 200_iIs the amount of power that buyer i needs to purchase during the current transaction period, D_TotalIs the total amount of electricity, N, that all users need to purchase during the current transaction period t_fRepresenting the number of times buyer i successfully executes the contract within the statistical period, N_TotalRepresents the total number of times of executing contracts by buyer i in the statistical period, wherein lambda (lambda > 0) and mu (mu > 0) are weighting factors which are set by the system scheduler 200 and respectively represent the importance contribution degree, the local load demand degree and the reliability;

step S422: establishing a benefit model of the power buyer based on the comprehensive grading model:

wherein F_iIs a benefit of buyer i, PI_iIs the composite score, s, of buyer i_iIs the amount of power requested by buyer i to the system dispatcher 200 according to his own policy, EA_iIs the amount of power that the system dispatcher 200 allocates to buyer i according to a certain power allocation policy;

step S423: the mathematical formalization defines the optimization problem of the power distribution phase of the system scheduler 200:

an objective function:

constraint conditions are as follows: EA of 0. ltoreq._i≤s_i

An optimal power request strategy of buyer i,

The optimal amount of electric energy allocated to buyer i for system scheduler 200,

wherein the goal of the E-distribution power phase system is to maximize the social welfare, i.e., the sum of the benefits of all the power buyers, and constraint 1 represents the power EA distributed to the buyers by the system dispatcher 200_iNo more power s than the buyer requests_i Constraint 2 indicates that the sum of the power distributed by the system dispatcher 200 to all buyers cannot exceed the sum of the power purchased from the set of sellers during the power collection phase

Step S424: solving the optimization problem in the power distribution stage by a water injection algorithm:

the algorithm firstly carries out initialization work (Line 1-4), secondly starts a cycle iteration process until the remaining power to be distributed is 0(Line 5-17), and finally returns a water volume set EA distributed by all water tanks, namely a power set EA (Line 18) distributed by all buyers, namely a set of optimal power distributed to all the buyers by the system scheduler 200, wherein the system scheduler 200 distributes electric energy to the buyers according to the optimal power corresponding to all the buyers in the power set EA. Fig. 8 is a schematic diagram illustrating a relationship between the convergence time of the optimal power distribution algorithm (water filling algorithm) and the number of users in the community microgrid, and it can be seen from fig. 8 that the convergence time of the optimal power distribution algorithm is in a direct proportion to the number of users in the community microgrid.

In step S5, error processing is performed by the prediction error processing module 3 to perform compensation liquidation on the transaction body according to the prediction error. Specifically, the prediction error processing module 3 solves the problem of economic loss of the transaction subject due to the electric power prediction error by executing a compensation liquidation model composed of a seller compensation liquidation model in the electric power collection stage and a buyer compensation liquidation model in the electric power distribution stage, fig. 9 shows a flowchart when the seller compensation liquidation model is executed for compensation liquidation (corresponding to step S51 hereinafter), and fig. 10 shows a flowchart when the buyer compensation liquidation model is executed for compensation liquidation (corresponding to step S52 hereinafter).

As shown in fig. 9, in step S51, the following steps are included:

step S511, seller j (j ∈ S) contracts with DSO (system dispatcher 200) based on the prediction;

step S512, the seller j (j belongs to S) and the DSO execute contracts based on the actual electric energy state;

step S513, after the contracts executed by the two parties in the electric power collecting stage are finished, the two-way metering intelligent electric meter is read to obtain the real photovoltaic power generation amount G of the seller j in the transaction time period t_j，actAnd load demand D_j，act；

Step S514, calculating error Delta E_j，sellAccording to the obtained real photovoltaic power generation G of the seller j in the transaction time t_j，actAnd load demand D_j，actThe actual selling power of the seller j can be obtained

Expressed as:

thus, the difference Δ E between the electricity actually sold by seller j and the electricity predicted to be sold_j，sellIs shown as

Step 515: when Δ E_j，sellWhen 0, seller j just provides the predicted saleable power to the system dispatcher 200 during the transaction period t, and thus settles normally when Δ E_j，sellAt > 0, seller j provides to scheduler 200 the full amount of not only the predicted saleable power, but also more Δ E during the transaction period t_j，sellSo that the scheduler 200 needs to compensate for the profit of seller j, which will increase by Δ E_j，sell*p_gbWhen Δ E is_j，sell< 0, seller j is not sufficient to provide predicted saleable power to the dispatcher 200 for the transaction period t, less Δ E_j，sellThe scheduler 200 purchases the lack of electric power Δ E from the main grid 400 in order to maintain the balance of power supply and demand in the community microgrid on the assumption that other users and the scheduler 200 perform error-free electric power transaction based on prediction_j，sellThus, seller j needs to compensate for the loss of the scheduler 200, and seller j's profit will be reduced by Δ E_j，sell*p_gs；

And step S516, settlement result.

As shown in fig. 10, in step S52, the following steps are included:

step S521, buyer i (i belongs to S) contracts with DSO (system scheduler 200) based on the prediction;

step S522, seller i (i belongs to S) and DSO execute contract based on actual electric energy state;

step S523: after the contract execution of both parties is finished in the electric power distribution stage, the real photovoltaic power generation amount G of the buyer i in the transaction time period t is obtained by reading the bidirectional metering intelligent electric meter_i，actAnd load demand D_i，act；

Step S524, calculating an error Delta E_i，reqSpecifically, by the buyeri actual photovoltaic power generation G in transaction time t_i，actAnd the load demand amount, and the actual power purchased by buyer i can be obtained

Expressed as:

therefore, the difference Δ E between the power actually purchased by buyer i and the power predicted to be purchased_i，reqIs shown as

Step S525, when Delta E_i，reqWhen 0, it is apparent that the buyer i has just purchased the predicted required power to the system scheduler 200 during the transaction period t, and thus normally settles when Δ E_i，reqAt > 0, buyer i purchases not only the predicted demand for power but also an excess of Δ E from the system dispatcher 200 during the transaction period t_i，reqAt this time, the system dispatcher 200 needs to purchase Δ E from the main grid 400_i，reqSo buyer i needs to compensate for the electricity purchase cost of the system scheduler 200, i.e. the electricity purchase cost of buyer i will increase by Δ E_i，req*p_gsWhen Δ E is_i，req< 0, buyer i has not sufficient to purchase the predicted required power, and has purchased less Δ E, to system scheduler 200 for the transaction time period t_i，reqAssuming that other users and the system dispatcher 200 perform error-free power transaction based on prediction, the system dispatcher 200 will sell power Δ E to the main grid 400 to maintain the power supply and demand balance in the community microgrid_i，reqTherefore, the profit obtained by the system dispatcher 200 through selling electricity should be compensated for buyer i, i.e., the electricity purchase cost of buyer i will be reduced by Δ E_i，req*p_gb。

In step S6, it is determined whether a system termination command is satisfied.

If the determination result is "yes", the step ends.

If the determination result is "no", it is necessary to go through step S7.

In step S7, the error Err and the system operating pressure P in step S2 are updated, specifically, the system operating pressure is monitored, the obtained system operating pressure is monitored and the obtained error is calculated to update the error Err and the system operating pressure P in step S2, and step S2 is executed again, and if the determination result in step S2 is "no", step S8 is executed.

In step S8, the trading time window Δ t is adjusted (e.g., decreased by a preset value based on the original trading time window) and the process returns to step S3 to predict the photovoltaic power generation and load demand of each residential user in the community microgrid in the next trading time window according to the adjusted trading time window Δ t, and the subsequent steps are performed.

To balance the prediction error and the system pressure, by adding the time window adjustment module 4 to the power trading system 100 (realized by adding the steps S7, S2, and S8), the trading time window can be adjusted by monitoring the acquired system operating pressure and calculating the acquired error until the optimal trading time window is adjusted. That is, the electric power trading system 100 of the present invention has a dynamic self-adapting feature, in other words, the electric power trading system 100 of the present invention operates in a closed loop and can be adjusted to an optimal trading time window.

As shown in fig. 11, the power transaction method and system of the present embodiment can be implemented by a service device 1, the service device includes a memory 503, a processor 501 and a communicator 502 connected to each other, the memory 501 stores a computer program, and the processor 501 executes the program to implement the web page word processing method.

The processor 501 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component; the memory 503 may include a Random Access Memory (RAM), and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory.

Note that the computer program in the memory 503 may be implemented in the form of a software functional unit and may be stored in a computer readable storage medium when the computer program is sold or used as a standalone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention.

The embodiment of the invention also provides a computer storage medium, which stores a computer program, wherein the program realizes the weld volume management and control method when being executed by a processor; the computer storage media include all forms of non-volatile memory, media and memory devices, including, for example: semiconductor memory devices such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.

The invention will be illustrated below by means of a specific example.

The system is initialized, and a community micro-grid consisting of 6 residential users is considered, wherein each user is provided with a photovoltaic power generation system and a bidirectional metering smart meter. Electricity selling price p of main grid 400_gsThe electricity purchase price p of the main grid 400 is set to 0.92 yuan/kWh_gbAt 0.37 yuan/kWh, the system scheduler 200 sets an initial trading time window of 1 hour.

Power prediction module 1 predicts community micro-scale based on power big data and artificial intelligence technologyThe photovoltaic power generation and load demand (i.e. user dynamic model) of each residential user in the power grid, and a prediction model learning algorithm diagram are shown in fig. 5. Predicted power generation amount G per user using prediction model_iAnd the amount of electricity used D_iAs shown in fig. 11 and 12, respectively.

And obtaining a prediction-based user dynamic model, and dividing all residential users in the community micro-grid into an electricity seller set and an electricity buyer set.

The electricity transaction module 2 solves the problem of electricity transaction between the seller set and the buyer set, and is divided into a stage of collecting electricity from the seller set by the system dispatcher 200 and a stage of distributing electricity to the buyer set by the system dispatcher 200, and the electricity transaction schematic diagram is shown in fig. 6.

In the collect power phase, the system collects power with the goal of simultaneously minimizing the purchase cost of the system scheduler 200 and maximizing the benefit of the seller by establishing a purchase cost model of the system scheduler 200 and a benefit model of the seller. The optimal power pricing problem of the power collecting phase is defined in a mathematical formalization mode as follows:

an objective function:

constraint conditions are as follows:

then, the optimal power trading price p of the problem is solved through the distributed iterative algorithm provided by the invention, and a schematic diagram of the relationship between the convergence time of the optimal power pricing algorithm and the number of users in the community microgrid is shown in fig. 7.

Table 1 shows the collected power process for the 11 th transaction period:

wherein is p^*Is the optimal electricity price obtained by solving the optimal electricity pricing problem,

is the electric energy consumed by the seller i in response to the optimal electricity price in order to maximize the electricity selling profit,the system dispatcher 200 is the power collected from seller i.

Step six: in the power distribution phase, the system distributes power with the goal of maximizing social welfare (the sum of all the buyers 'benefits) by building a buyer's benefit model. The optimal power distribution problem of the power distribution phase is defined in a mathematical formalization mode as follows:

an objective function:

constraint conditions are as follows: EA of 0. ltoreq._i≤s_i

The optimal power distribution strategy for this problem is then solved by the water-filling algorithm proposed above in the present invention. Fig. 8 shows a schematic diagram of a relationship between the convergence time of the optimal power distribution algorithm and the number of users in the community microgrid.

Table 2 shows the process of distributing power for the 11 th transaction period:

wherein the content of the first and second substances,

an optimal power request strategy of buyer i,Optimal power allocated to buyer i for system dispatcher 200, E_exFor the difference between the total amount of power purchased from the seller and the total amount of power distributed to the buyer, other definitions are detailed above, and will not be described herein.

The prediction error processing module 3 runs a compensation clearing model to solve the problem of economic loss of a transaction main body caused by electric power prediction errors. The compensation liquidation model is composed of a compensation liquidation model of a seller in the collection power phase (as shown in fig. 9) and a compensation liquidation model of a buyer in the distribution power phase (as shown in fig. 10).

The power trading system 100 balances system operating pressure and prediction error by constantly monitoring system operating pressure and calculating power prediction error to find a trading time window at which the operating pressure and prediction error best balance.

Compared with the rest power grid, the stability of the main power grid 400, the electricity purchasing cost of the buyer and the electricity selling profit of the seller are improved, the electricity interaction amount of the micro power grid and the main power grid 400 in the electricity transaction mode is reduced by 72.6% on average, the electricity purchasing cost of the buyer is reduced by 46.2% on average, and the electricity selling profit of the seller is improved by 62.5% on average, as shown in fig. 11, 12 and 13.

The invention provides a centralized electric power transaction system 100 based on big data and artificial intelligence in a community microgrid, and solves the problem that the power supply and demand of a single user in the community microgrid are unbalanced. The system is stable and reliable through experimental verification, and the adopted electric power pricing algorithm and distribution algorithm are simple and efficient. Compared with the currently adopted surplus electricity internet access, the method not only greatly improves the electricity selling profits of sellers, but also greatly reduces the electricity purchasing cost of buyers and the interference on the main power grid 400.

In the description herein, numerous specific details are provided, such as examples of components and/or methods, to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that an embodiment of the invention can be practiced without one or more of the specific details, or with other apparatus, systems, assemblies, methods, components, materials, parts, and/or the like. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of embodiments of the invention.

Reference throughout this specification to "one embodiment", "an embodiment", or "a specific embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment, and not necessarily all embodiments, of the present invention. Thus, respective appearances of the phrases "in one embodiment", "in an embodiment", or "in a specific embodiment" in various places throughout this specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures, or characteristics of any specific embodiment of the present invention may be combined in any suitable manner with one or more other embodiments. It is to be understood that other variations and modifications of the embodiments of the invention described and illustrated herein are possible in light of the teachings herein and are to be considered as part of the spirit and scope of the present invention.

It will also be appreciated that one or more of the elements shown in the figures can also be implemented in a more separated or integrated manner, or even removed for inoperability in some circumstances or provided for usefulness in accordance with a particular application.

Additionally, any reference arrows in the drawings/figures should be considered only as exemplary, and not limiting, unless otherwise expressly specified. Further, as used herein, the term "or" is generally intended to mean "and/or" unless otherwise indicated. Combinations of components or steps will also be considered as being noted where terminology is foreseen as rendering the ability to separate or combine is unclear.

As used in the description herein and throughout the claims that follow, "a", "an", and "the" include plural references unless otherwise indicated. Also, as used in the description herein and throughout the claims that follow, unless otherwise indicated, the meaning of "in …" includes "in …" and "on … (on)".

The above description of illustrated embodiments of the invention, including what is described in the abstract of the specification, is not intended to be exhaustive or to limit the invention to the precise forms disclosed herein. While specific embodiments of, and examples for, the invention are described herein for illustrative purposes only, various equivalent modifications are possible within the spirit and scope of the present invention, as those skilled in the relevant art will recognize and appreciate. As indicated, these modifications may be made to the present invention in light of the foregoing description of illustrated embodiments of the present invention and are to be included within the spirit and scope of the present invention.

The systems and methods have been described herein in general terms as the details aid in understanding the invention. Furthermore, various specific details have been given to provide a general understanding of the embodiments of the invention. One skilled in the relevant art will recognize, however, that an embodiment of the invention can be practiced without one or more of the specific details, or with other apparatus, systems, assemblies, methods, components, materials, parts, and/or the like. In other instances, well-known structures, materials, and/or operations are not specifically shown or described in detail to avoid obscuring aspects of embodiments of the invention.

Thus, although the present invention has been described herein with reference to particular embodiments thereof, a latitude of modification, various changes and substitutions are intended in the foregoing disclosures, and it will be appreciated that in some instances some features of the invention will be employed without a corresponding use of other features without departing from the scope and spirit of the invention as set forth. Thus, many modifications may be made to adapt a particular situation or material to the essential scope and spirit of the present invention. It is intended that the invention not be limited to the particular terms used in following claims and/or to the particular embodiment disclosed as the best mode contemplated for carrying out this invention, but that the invention will include any and all embodiments and equivalents falling within the scope of the appended claims. Accordingly, the scope of the invention is to be determined solely by the appended claims.

Claims

1. A microgrid power transaction method is characterized by comprising the following steps:

2. The microgrid power trading method of claim 1, wherein the step of predicting the power generation capacity and the load demand of each user within the microgrid in a next trading time window respectively according to a preset time window of the system comprises:

training a user power prediction model based on the training samples;

evaluating the power prediction model through the test sample to obtain an optimal user power prediction model;

3. The microgrid power trading method of claim 1, further comprising a compensation clearing of trading bodies based on prediction errors.

4. The microgrid power trading method of claim 3, wherein the step of clearing compensation for trading bodies according to prediction errors comprises:

performing compensation clearing according to the difference between the actual sold electricity of each electricity seller and the electricity collected to the electricity seller; and/or

5. The microgrid power trading method of any one of claims 1 to 4, further comprising adaptively adjusting the trading time window according to a prediction error and system operating pressure.

6. A microgrid transaction system, comprising:

the electric power prediction module is used for respectively predicting the generated energy and/or the load demand of each user in the microgrid in the next transaction time window according to the preset time window of the microgrid transaction system, and dividing all the users in the microgrid into an electric power seller set and/or an electric power buyer set based on the obtained generated energy and load demand of each user;

7. The microgrid power trading system of claim 6, wherein the power prediction module comprises:

8. The microgrid trading system of claim 6, further comprising a prediction error processing module for performing compensation clearing on trading subjects according to prediction errors.

9. The microgrid trading system of claim 8, wherein the prediction error processing module comprises:

A buyer compensation liquidation submodule for liquidation of compensation according to the difference between the actual purchase power of each said electricity buyer and the power distributed to that buyer.

10. The microgrid trading system of any one of claims 6 to 9, further comprising a time window adjustment module for adjusting a time window according to a prediction error and a system operating pressure.

11. A microgrid, comprising:

a system scheduler connected to a main grid, the system scheduler comprising a cloud energy storage and an electric power trading system according to any one of claims 6 to 10;