Power transaction strategy generation method and device, equipment and storage medium

Abstract

The invention discloses a power transaction strategy generation method and device, equipment and a storage medium, and relates to the technical field of power, and the method comprises the steps: carrying out the power load prediction of a target region through a prediction model, and obtaining a demand side prediction load; determining a total electricity purchasing cost formula and a total electricity selling income formula of electricity selling parties in the target region according to a numerical relationship between the demand side prediction load and contract electricity purchasing power corresponding to the target region; and constructing an electricity selling profit expression of the electricity selling party based on the total electricity purchasing cost expression and the total electricity selling income expression, and generating a corresponding electricity transaction strategy when the profit of the electricity selling party is the highest in the target region according to the electricity selling profit expression. The power load of the target region is predicted through the prediction model, and the prediction precision is improved; and then an electricity selling profit expression of the electricity selling party is constructed based on the total electricity purchasing cost expression and the total electricity selling income expression of the electricity selling party in the target region, so that a corresponding electricity transaction strategy when the profit of the electricity selling party in the target region is the highest can be generated according to the electricity selling profit expression.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device, equipment and storage medium for generating an electric power trading strategy. Background Art

[0002] In the traditional electricity trading process, the electricity seller usually signs a contract with the power supplier in advance to purchase electricity and sell it to the electricity consumption area. However, since the contract period is often long, the uncertainty of the power load in the power consumption area during the contract period is high and the electricity price fluctuates. During this period, there are many possible trading strategies (for example, purchasing x kilowatts in the contract, purchasing y kilowatts in period a, and purchasing z kilowatts in period b), and the profits brought to the electricity seller by different trading strategies may vary greatly. Therefore, how to generate profit-maximizing electricity trading strategies has become one of the important research directions in the industry. Summary of the invention

[0003] The main purpose of this application is to provide a method, device, equipment and storage medium for generating an electricity trading strategy, aiming to solve the technical problem of how to generate an electricity trading strategy that maximizes profits.

[0004] To achieve the above objectives, the present application provides a method for generating a power trading strategy, the method comprising the following steps: Use the forecasting model to forecast the power load in the target area and obtain the demand-side forecast load; Determine the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area; The power selling profit formula of the power seller is constructed based on the total power purchase cost formula and the total power selling revenue formula, and the corresponding power trading strategy when the power seller has the highest profit in the target area is generated according to the power selling profit formula.

[0005] In one embodiment, before the step of forecasting the power load of the target area by using the forecast model to obtain the demand-side forecast load, the step further includes: Collect historical load data and historical key factors of the target area, and divide and merge the historical load data and the historical key factors into a training set, a test set and a validation set, wherein the historical key factors include weather factors, time factors, economic factors and social factors; The LM-BP neural network model is trained by using the training set, the test set and the validation set to obtain a prediction model, and the prediction model is used to predict the power load in the target area.

[0006] In one embodiment, the demand-side forecast load includes a plurality of time-sharing forecast loads, the contracted power purchase power includes a plurality of time-sharing power purchase powers, and the step of determining the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area according to the numerical relationship between the demand-side forecast load and the contracted power purchase power corresponding to the target area includes: When the time-sharing forecast load is equal to the time-sharing power purchase power, the contract power purchase cost is used as the first time-sharing power purchase cost; When the time-sharing forecast load is higher than the time-sharing power purchase power, an additional power purchase cost is calculated, and the sum of the additional power purchase cost and the contract power purchase cost is used as the second time-sharing power purchase cost; When the time-sharing forecast load is lower than the time-sharing power purchase power, calculating the additional power sales income; The total electricity purchase cost formula and the total electricity sales revenue formula of the electricity seller in the target area are determined based on the first time-of-use electricity purchase cost, the second time-of-use electricity purchase cost and the additional electricity sales revenue corresponding to each time period in the target area.

[0007] In one embodiment, when the time-sharing forecast load is higher than the time-sharing power purchase power, the step of calculating the additional power purchase cost includes: When the time-sharing predicted load is higher than the time-sharing power purchase power, determining a first deviation between the time-sharing predicted load and the time-sharing power purchase power; The additional electricity purchase cost is calculated according to the time-sharing electricity purchase price corresponding to the time-sharing electricity purchase power and the first deviation.

[0008] In one embodiment, when the time-sharing forecast load is lower than the time-sharing power purchase power, the step of calculating the additional power sales revenue includes: When the time-sharing predicted load is lower than the time-sharing power purchase power, determining a second deviation between the time-sharing predicted load and the time-sharing power purchase power; The additional electricity sales revenue is calculated according to the time-sharing electricity sales price corresponding to the time-sharing electricity purchase power and the second deviation.

[0009] In one embodiment, the step of constructing the electricity sales profit formula of the electricity seller based on the total electricity purchase cost formula and the total electricity sales revenue formula, and generating the corresponding power trading strategy when the profit of the electricity seller in the target area is the highest according to the electricity sales profit formula includes: Subtracting the total electricity sales revenue formula from the total electricity purchase cost formula to construct the electricity sales profit formula of the electricity seller; The maximum profit value of the electricity selling profit formula is determined, and the corresponding power trading strategy when the profit of the electricity seller is the highest in the target area is generated according to the electricity purchasing data and the electricity selling data corresponding to the maximum profit value.

[0010] In addition, to achieve the above purpose, the present application also proposes a power trading strategy generation device, the power trading strategy generation device comprising: The load forecasting module is used to forecast the power load in the target area through the forecasting model to obtain the demand-side forecast load; A cost determination module, used to determine a total power purchase cost formula and a total power sales revenue formula of the power seller in the target area according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area; A strategy generation module is used to construct the electricity sales profit formula of the electricity seller based on the total electricity purchase cost formula and the total electricity sales revenue formula, and generate a corresponding power trading strategy when the electricity seller has the highest profit in the target area according to the electricity sales profit formula.

[0011] In addition, to achieve the above-mentioned purpose, the present application also proposes an electricity trading strategy generation device, which includes: a memory, a processor, and an electricity trading strategy generation program stored on the memory and executable on the processor, and the electricity trading strategy generation program is configured to implement the steps of the electricity trading strategy generation method described above.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and stores an electricity trading strategy generation program. When the electricity trading strategy generation program is executed by a processor, it implements the steps of the electricity trading strategy generation method described above.

[0013] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer program product, which includes an electricity trading strategy generation program, and when the electricity trading strategy generation program is executed by a processor, it implements the steps of the electricity trading strategy generation method described above.

[0014] This application uses a prediction model to predict the power load of the target area to obtain the demand-side predicted load; according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area, the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area are determined; based on the total power purchase cost formula and the total power sales revenue formula, the power sales profit formula of the power seller is constructed, and according to the power sales profit formula, the corresponding power trading strategy when the power seller has the highest profit in the target area is generated. Since the above method of this application predicts the power load of the target area through a prediction model, the prediction accuracy is improved compared to the traditional manual prediction method; then, based on the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area, the power sales profit formula of the power seller is constructed, so that the corresponding power trading strategy when the power seller has the highest profit in the target area can be generated according to the power sales profit formula. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is a flow chart of the first embodiment of the method for generating a power trading strategy of the present application; Figure 2 This is a flow chart of the second embodiment of the method for generating a power trading strategy of the present application; Figure 3 This is a schematic diagram of the structure of the prediction model in the power trading strategy generation method of this application; Figure 4 This is a flow chart of the third embodiment of the method for generating a power trading strategy of the present application; Figure 5 This is a structural block diagram of the first embodiment of the power trading strategy generation device of the present application; Figure 6 A schematic diagram of the structure of a power trading strategy generation device in the hardware operating environment involved in the embodiment of the present application.

[0018] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0020] It should be noted that the execution subject of the embodiments of the present application may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, such as the above-mentioned power trading strategy generation device. The following embodiments are described below taking the power trading strategy generation device as an example.

[0021] The present application embodiment provides a method for generating a power trading strategy, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for generating a power trading strategy of the present application.

[0022] In this embodiment, the power trading strategy generation method includes the following steps: Step S10: forecast the power load in the target area through the forecasting model to obtain the demand-side forecast load.

[0023] It is understandable that the above prediction model can be a model for predicting the power load in the target area. Specifically, the above prediction model can be obtained after collecting historical data of relevant factors such as historical load data, and training the LM-BP (Levenberg-Marquardt Back Propagation, back propagation based on the Levenberg-Marquardt algorithm) neural network model according to the historical data. Among them, the Levenberg-Marquardt algorithm (LM algorithm) is an algorithm for optimization problems. It combines the advantages of the Gauss-Newton algorithm and the gradient descent algorithm. During the optimization process, the LM algorithm can automatically adjust the optimization direction according to the change of the error, thereby achieving a balance between convergence speed and stability.

[0024] It should be understood that the target area can be any area with electricity demand, such as residential areas, charging stations, shopping malls, office buildings, etc., and this embodiment does not limit this. The above-mentioned demand-side predicted load means the power load forecast value of the prediction model for the target area within the contract period (for example, within half a year).

[0025] Step S20: Determine the total electricity purchase cost formula and the total electricity sales revenue formula of the electricity seller in the target area according to the numerical relationship between the demand-side predicted load and the contracted electricity purchase power corresponding to the target area.

[0026] It should be noted that the above-mentioned total electricity purchase cost formula can be a relationship formula corresponding to the sum of all electricity purchased by the electricity seller from the power supply party within a certain time period, and the above-mentioned total electricity sales revenue formula can be a relationship formula corresponding to the sum of all electricity sold by the electricity seller to the power supply party within a certain time period.

[0027] It should be understood that the error between the demand-side forecast load and the contracted power purchase power corresponding to the target area should be proportional to the number of non-fixed power devices in the target area, that is, the more non-fixed power devices there are in the target area, the greater the error between the demand-side forecast load and the contracted power purchase power. In short, the more non-fixed power devices there are in a region, the more difficult it is to predict the corresponding demand-side forecast load. Therefore, in some target areas, it is inevitable that the demand-side forecast load will be higher or lower than the contracted power purchase power. At this time, the power seller can purchase additional electricity from the power supplier or sell excess electricity to ensure the user's electricity demand and the power seller's profit needs.

[0028] Step S30: constructing the electricity selling profit formula of the electricity seller based on the total electricity purchase cost formula and the total electricity selling revenue formula, and generating a corresponding power trading strategy when the electricity seller has the highest profit in the target area according to the electricity selling profit formula.

[0029] In a specific implementation, after constructing the electricity sales profit formula of the electricity seller, different variables can be brought in to solve the electricity sales profit formula, and the above-mentioned electricity trading strategy is generated based on the variables that make the electricity seller have the highest profit in the target area.

[0030] This embodiment uses a prediction model to predict the power load of the target area to obtain the demand-side predicted load; according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area, the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area are determined; based on the total power purchase cost formula and the total power sales revenue formula, the power sales profit formula of the power seller is constructed, and according to the power sales profit formula, the corresponding power trading strategy when the power seller has the highest profit in the target area is generated. Since the above method of this embodiment predicts the power load of the target area through a prediction model, the prediction accuracy is improved compared to the traditional manual prediction method; then, based on the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area, the power sales profit formula of the power seller is constructed, so that the corresponding power trading strategy when the power seller has the highest profit in the target area can be generated according to the power sales profit formula.

[0031] refer to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the method for generating a power trading strategy of the present application.

[0032] In a feasible implementation manner, before step S10, the following may also be included: Step S1: Collect historical load data and historical key factors of the target area, and divide and merge the historical load data and the historical key factors into a training set, a test set and a validation set. The historical key factors include weather factors, time factors, economic factors and social factors.

[0033] Step S2: The LM-BP neural network model is trained by using the training set, the test set and the validation set to obtain a prediction model, wherein the prediction model is used to predict the power load in the target area.

[0034] In the specific implementation, you can refer to Figure 3 , Figure 3This is a schematic diagram of the structure of the prediction model in the method for generating power trading strategies in this application. In the prediction model, the neural network is composed of a large number of neuron connections, which can learn and have memory capabilities. After multiple trainings, the expected output value can be obtained by inputting given parameters. The model consists of an input layer, a hidden layer, and an output layer. Each layer contains multiple neuron nodes. Each neuron receives the output of the neurons in the previous layer, and performs weighted summation according to weights and biases, and then performs nonlinear mapping through an activation function. The specific algorithm of the BP (Back Propagation) neural network includes a forward propagation stage and a back propagation stage. In the forward propagation stage, the algorithm starts from the input layer and calculates the output value of each neuron layer by layer until the output layer. The output value formula of a single neural unit is: output = activation\_function(sum(weight×input) + bias); Among them, activation_function represents the activation function, weight represents the connection weight, input represents the output of the previous layer of neurons, and bias represents the bias.

[0035] In the back propagation phase, the mean square error between the network output and the expected output is first calculated as the resulting error value, and then the error value of each neuron is calculated layer by layer starting from the output layer based on the error value. Then the LM algorithm comes into play, and the weights and biases are adjusted by calculating the Hessian matrix to accelerate the convergence process. Finally, the connection weights and biases are updated based on the Hessian matrix and gradient. The specific update formula is: weight'= weight + learning\_rate×error\_gradient×input; bias' = bias + learning\_rate×error\_gradient; Among them, learning_rate represents the learning rate of the prediction model, error_gradient is the error gradient calculated based on the Hessian matrix and gradient, weight' represents the updated weight, and bias' represents the updated bias.

[0036] After that, the above steps are repeated until the training error meets the preset conditions or the maximum number of iterations is reached.

[0037] In a feasible implementation manner, the demand-side forecast load includes a plurality of time-sharing forecast loads, the contracted power purchase power includes a plurality of time-sharing power purchase powers, and the step S20 may include: Step S201: When the time-sharing forecast load is equal to the time-sharing power purchase power, the contract power purchase cost is used as the first time-sharing power purchase cost.

[0038] It should be noted that the above-mentioned contract power purchase cost can be calculated by the following formula: ; in, is the contract power purchase cost, , , These are the electricity purchase prices during peak, flat and valley periods respectively; , , They are the total electricity purchased during peak, flat and valley periods respectively.

[0039] Step S202: When the time-sharing forecast load is higher than the time-sharing power purchase power, an additional power purchase cost is calculated, and the sum of the additional power purchase cost and the contract power purchase cost is used as a second time-sharing power purchase cost.

[0040] Step S203: When the time-sharing forecast load is lower than the time-sharing power purchase power, calculate the additional power sales revenue.

[0041] Step S204: determining a total electricity purchase cost formula and a total electricity sales revenue formula of the electricity seller in the target area based on the first time-of-use electricity purchase cost, the second time-of-use electricity purchase cost and the additional electricity sales revenue corresponding to each time period in the target area.

[0042] It should be understood that during the contract period, there may be differences between the demand-side forecast load and the contracted power purchase power corresponding to each time period. Therefore, they can be distinguished by dividing the demand-side forecast load into several time-sharing forecast loads according to the time period, and dividing the contracted power purchase power into several time-sharing power purchase powers according to the time period, thereby determining the power purchasing nodes and power selling nodes of the power seller in the target area in each time period, thereby making the above-mentioned total power purchase cost formula and the above-mentioned total power sales revenue formula more accurate.

[0043] This embodiment collects historical load data and historical key factors of the target area, and divides and merges the historical load data and the historical key factors into a training set, a test set and a validation set, wherein the historical key factors include weather factors, time factors, economic factors and social factors; the LM-BP neural network model is trained by the training set, the test set and the validation set to obtain a prediction model, which is used to predict the power load of the target area; when the time-sharing predicted load is equal to the time-sharing power purchase power, the contract power purchase cost is used as the first time-sharing power purchase cost; when the time-sharing predicted load is higher than the time-sharing power purchase power, the additional power purchase cost is calculated, and the sum of the additional power purchase cost and the contract power purchase cost is used as the second time-sharing power purchase cost; when the time-sharing predicted load is lower than the time-sharing power purchase power, the additional power sales revenue is calculated; based on the first time-sharing power purchase cost, the second time-sharing power purchase cost and the additional power sales revenue corresponding to each time period in the target area, the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area are determined. The above method of this embodiment trains the LM-BP neural network model through a training set, a test set and a validation set composed of the historical load data and historical key factors of the target area, so that the obtained prediction model can more accurately predict the power load of the target area; at the same time, it is set to purchase electricity when the time-sharing predicted load is higher than the time-sharing purchased electricity power, and to sell electricity when the time-sharing predicted load is lower than the time-sharing purchased electricity power, so as to ensure the electricity demand of users in the target area and the profit demand of the electricity seller.

[0044] refer to Figure 4 , Figure 4 This is a flow chart of the third embodiment of the method for generating a power trading strategy of the present application.

[0045] In a feasible implementation manner, the step S202 may include: Step S2021: When the time-sharing forecast load is higher than the time-sharing power purchase power, determine a first deviation between the time-sharing forecast load and the time-sharing power purchase power.

[0046] It should be noted that the first deviation refers to the value of electricity that the electricity seller needs to purchase in order to ensure the electricity demand of the user.

[0047] Step S2022: Calculate the additional electricity purchase cost according to the time-sharing electricity purchase price corresponding to the time-sharing electricity purchase power and the first deviation.

[0048] In a specific implementation, the product of multiplying the time-of-use electricity purchase price corresponding to the time-of-use electricity purchase power and the first deviation amount can be used as the additional electricity purchase cost.

[0049] In a feasible implementation manner, step S203 may include: Step S2031: When the time-sharing forecast load is lower than the time-sharing power purchase power, determine a second deviation between the time-sharing forecast load and the time-sharing power purchase power.

[0050] It should be noted that the first deviation refers to the value of electricity that the electricity seller needs to sell in order to ensure its own profit demand.

[0051] Step S2032: Calculate the additional electricity sales revenue according to the time-sharing electricity sales price corresponding to the time-sharing electricity purchase power and the second deviation.

[0052] In a specific implementation, the product of the time-sharing electricity selling price corresponding to the time-sharing electricity purchase power and the second deviation amount can be used as the additional electricity selling income.

[0053] In a feasible implementation manner, the step S30 may include: Step S301: subtract the total electricity sales revenue formula from the total electricity purchase cost formula to construct the electricity sales profit formula of the electricity seller.

[0054] It should be noted that the above electricity sales profit formula can be expressed as: ; Among them, U represents the profit from electricity sales, and R represents the additional income from electricity sales. represents the contractual electricity purchase cost, Represents the additional cost of purchasing electricity.

[0055] Step S302: determining the maximum profit value of the electricity selling profit formula, and generating a corresponding power trading strategy when the electricity seller has the highest profit in the target area according to the electricity purchasing data and the electricity selling data corresponding to the maximum profit value.

[0056] In the specific implementation, the genetic algorithm can be used and the CPLEX solver can be called to solve the above electricity sales profit formula, and determine the variables corresponding to the maximum U value (that is, the maximum profit value of the electricity sales profit formula). Then, based on these variables, the corresponding electricity trading strategy is generated when the electricity seller has the highest profit in the target area, such as purchasing a kilowatts in the contract, purchasing b kilowatts in the x period, purchasing c kilowatts in the y period, and selling d kilowatts in the z period.

[0057] In this embodiment, when the time-sharing forecast load is higher than the time-sharing power purchase power, a first deviation between the time-sharing forecast load and the time-sharing power purchase power is determined; the additional power purchase cost is calculated based on the time-sharing power purchase price corresponding to the time-sharing power purchase power and the first deviation; when the time-sharing forecast load is lower than the time-sharing power purchase power, a second deviation between the time-sharing forecast load and the time-sharing power purchase power is determined; the additional power sales revenue is calculated based on the time-sharing power sales price corresponding to the time-sharing power purchase power and the second deviation; the total power sales revenue formula is subtracted from the total power purchase cost formula to construct a power sales profit formula for the power seller; the maximum profit value of the power sales profit formula is determined, and the corresponding power trading strategy when the power seller has the highest profit in the target area is generated based on the power purchase data and power sales data corresponding to the maximum profit value. The above method of this embodiment calculates the additional electricity purchase cost according to the time-of-use electricity purchase price corresponding to the time-of-use electricity purchase power and the first deviation, calculates the additional electricity sales revenue according to the time-of-use electricity sales price corresponding to the time-of-use electricity purchase power and the second deviation, and constructs the electricity sales profit formula of the electricity seller on this basis to generate the corresponding power trading strategy when the electricity seller has the highest profit in the target area, thereby maximizing the revenue of the electricity seller while ensuring the electricity demand of users in the target area.

[0058] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the power trading strategy generation device of the present application.

[0059] like Figure 5 As shown, the power trading strategy generation device proposed in the embodiment of the present application includes: The load forecasting module 501 is used to forecast the power load of the target area through the forecasting model to obtain the demand-side forecast load; The cost determination module 502 is used to determine the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area; The strategy generation module 503 is used to construct the electricity sales profit formula of the electricity seller based on the total electricity purchase cost formula and the total electricity sales revenue formula, and generate the corresponding power trading strategy when the electricity seller has the highest profit in the target area according to the electricity sales profit formula.

[0060] This embodiment uses a prediction model to predict the power load of the target area to obtain the demand-side predicted load; according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area, the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area are determined; based on the total power purchase cost formula and the total power sales revenue formula, the power sales profit formula of the power seller is constructed, and according to the power sales profit formula, the corresponding power trading strategy when the power seller has the highest profit in the target area is generated. Since the above method of this embodiment predicts the power load of the target area through a prediction model, the prediction accuracy is improved compared to the traditional manual prediction method; then, based on the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area, the power sales profit formula of the power seller is constructed, so that the corresponding power trading strategy when the power seller has the highest profit in the target area can be generated according to the power sales profit formula.

[0061] Based on the first embodiment of the power trading strategy generating device of the present application, a second embodiment of the power trading strategy generating device of the present application is proposed.

[0062] In this embodiment, the load forecasting module 501 is also used to collect historical load data and historical key factors of the target area, and divide the historical load data and the historical key factors into a training set, a test set and a verification set, and the historical key factors include weather factors, time factors, economic factors and social factors; the LM-BP neural network model is trained by the training set, the test set and the verification set to obtain a prediction model, and the prediction model is used to predict the power load of the target area.

[0063] Furthermore, the demand-side forecast load includes several time-sharing forecast loads, the contracted power purchase power includes several time-sharing power purchase powers, and the cost determination module 502 is also used to use the contracted power purchase cost as the first time-sharing power purchase cost when the time-sharing forecast load is equal to the time-sharing power purchase power; when the time-sharing forecast load is higher than the time-sharing power purchase power, calculate the additional power purchase cost, and use the sum of the additional power purchase cost and the contracted power purchase cost as the second time-sharing power purchase cost; when the time-sharing forecast load is lower than the time-sharing power purchase power, calculate the additional power sales revenue; and determine the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area based on the first time-sharing power purchase cost, the second time-sharing power purchase cost and the additional power sales revenue corresponding to each time period in the target area.

[0064] Furthermore, the cost determination module 502 is also used to determine a first deviation between the time-sharing predicted load and the time-sharing purchased power when the time-sharing predicted load is higher than the time-sharing purchased power; and calculate the additional electricity purchasing cost based on the time-sharing electricity purchasing price corresponding to the time-sharing purchased power and the first deviation.

[0065] Furthermore, the cost determination module 502 is also used to determine a second deviation between the time-sharing predicted load and the time-sharing power purchase power when the time-sharing predicted load is lower than the time-sharing power purchase power; and calculate additional power sales revenue based on the time-sharing power sales price corresponding to the time-sharing power purchase power and the second deviation.

[0066] Furthermore, the strategy generation module 503 is also used to subtract the total electricity sales revenue formula from the total electricity purchase cost formula to construct the electricity sales profit formula of the electricity seller; determine the maximum profit value of the electricity sales profit formula, and generate the corresponding electricity trading strategy when the electricity seller has the highest profit in the target area based on the electricity purchase data and electricity sales data corresponding to the maximum profit value.

[0067] Other embodiments or specific implementation methods of the power trading strategy generation device of the present application can refer to the above-mentioned method embodiments, which will not be repeated here.

[0068] The present application provides an electricity trading strategy generating device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the electricity trading strategy generating method in the above-mentioned embodiment one.

[0069] Reference below Figure 6 , which shows a schematic diagram of the structure of a power trading strategy generation device suitable for implementing the embodiment of the present application. The power trading strategy generation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The power trading strategy generating device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0070] like Figure 6As shown, the power trading strategy generation device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory 1002 or the program loaded from the storage device 1003 to the random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the power trading strategy generation device are also stored. The processing device 1001, the read-only memory 1002 and the random access memory 1004 are connected to each other through a bus 1005. The input / output interface 1006 is also connected to the bus. Generally, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the power trading strategy generation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a power trading strategy generation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0071] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0072] The power trading strategy generation device provided by the present application adopts the power trading strategy generation method in the above embodiment, which can solve the technical problem of how to generate a profit-maximizing power trading strategy. Compared with the prior art, the beneficial effects of the power trading strategy generation device provided by the present application are the same as the beneficial effects of the power trading strategy generation method provided by the above embodiment, and the other technical features in the power trading strategy generation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0073] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0074] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0075] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the power trading strategy generating method in the above-mentioned embodiment.

[0076] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0077] The computer-readable storage medium may be included in the power trading strategy generation device; or may exist independently without being assembled into the power trading strategy generation device.

[0078] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the power trading strategy generation device, the power trading strategy generation device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++; and also include conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0079] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0081] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned power trading strategy generation method, and can solve the technical problem of how to generate a profit-maximizing power trading strategy. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the power trading strategy generation method provided in the above-mentioned embodiment, and will not be repeated here.

[0082] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned power trading strategy generation method when executed by a processor.

[0083] The computer program product provided in this application can solve the technical problem of power trading strategy generation. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the power trading strategy generation method provided in the above embodiment, which will not be repeated here.

[0084] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for generating a power trading strategy, characterized in that: The method comprises the following steps: Use the forecast model to forecast the power load in the target area and obtain the demand-side forecast load; Determine the total power purchase cost formula and the total power sales revenue formula of the power seller in the target area according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area; The power selling profit formula of the power seller is constructed based on the total power purchase cost formula and the total power selling revenue formula, and the corresponding power trading strategy when the power seller has the highest profit in the target area is generated according to the power selling profit formula.

2. The method for generating a power trading strategy according to claim 1, characterized in that: Before the step of forecasting the power load of the target area by using the forecast model to obtain the demand-side forecast load, the method further includes: Collect historical load data and historical key factors of the target area, and divide and merge the historical load data and the historical key factors into a training set, a test set and a validation set, wherein the historical key factors include weather factors, time factors, economic factors and social factors; The LM-BP neural network model is trained by using the training set, the test set and the validation set to obtain a prediction model, and the prediction model is used to predict the power load in the target area.

3. The method for generating a power trading strategy according to claim 1, characterized in that: The demand-side forecast load includes a plurality of time-sharing forecast loads, the contracted power purchase power includes a plurality of time-sharing power purchase powers, and the step of determining a total power purchase cost formula and a total power sales revenue formula of the power seller in the target area according to the numerical relationship between the demand-side forecast load and the contracted power purchase power corresponding to the target area includes: When the time-sharing forecast load is equal to the time-sharing power purchase power, the contract power purchase cost is used as the first time-sharing power purchase cost; When the time-sharing forecast load is higher than the time-sharing power purchase power, an additional power purchase cost is calculated, and the sum of the additional power purchase cost and the contract power purchase cost is used as the second time-sharing power purchase cost; When the time-sharing forecast load is lower than the time-sharing power purchase power, calculating the additional power sales income; The total electricity purchase cost formula and the total electricity sales revenue formula of the electricity seller in the target area are determined based on the first time-of-use electricity purchase cost, the second time-of-use electricity purchase cost and the additional electricity sales revenue corresponding to each time period in the target area.

4. The method for generating a power trading strategy according to claim 3, characterized in that: The step of calculating the additional electricity purchase cost when the time-sharing predicted load is higher than the time-sharing electricity purchase power comprises: When the time-sharing predicted load is higher than the time-sharing power purchase power, determining a first deviation between the time-sharing predicted load and the time-sharing power purchase power; The additional electricity purchase cost is calculated according to the time-sharing electricity purchase price corresponding to the time-sharing electricity purchase power and the first deviation.

5. The method for generating a power trading strategy according to claim 3, characterized in that: The step of calculating the additional electricity sales revenue when the time-sharing predicted load is lower than the time-sharing electricity purchase power comprises: When the time-sharing predicted load is lower than the time-sharing power purchase power, determining a second deviation between the time-sharing predicted load and the time-sharing power purchase power; The additional electricity sales revenue is calculated according to the time-sharing electricity sales price corresponding to the time-sharing electricity purchase power and the second deviation.

6. The method for generating a power trading strategy according to claim 1, characterized in that: The step of constructing the electricity selling profit formula of the electricity seller based on the total electricity purchase cost formula and the total electricity selling revenue formula, and generating the corresponding power trading strategy when the electricity seller has the highest profit in the target area according to the electricity selling profit formula, includes: Subtracting the total electricity sales revenue formula from the total electricity purchase cost formula to construct the electricity sales profit formula of the electricity seller; The maximum profit value of the electricity selling profit formula is determined, and the corresponding power trading strategy when the profit of the electricity seller is the highest in the target area is generated according to the electricity purchasing data and the electricity selling data corresponding to the maximum profit value.

7. A device for generating a power trading strategy, characterized in that: The power trading strategy generating device comprises: The load forecasting module is used to forecast the power load in the target area through the forecasting model to obtain the demand-side forecast load; A cost determination module, used to determine a total power purchase cost formula and a total power sales revenue formula of the power seller in the target area according to the numerical relationship between the demand-side predicted load and the contracted power purchase power corresponding to the target area; A strategy generation module is used to construct the electricity sales profit formula of the electricity seller based on the total electricity purchase cost formula and the total electricity sales revenue formula, and generate a corresponding power trading strategy when the electricity seller has the highest profit in the target area according to the electricity sales profit formula.

8. A power trading strategy generation device, characterized in that: The device comprises: a memory, a processor, and a power trading strategy generation program stored in the memory and executable on the processor, wherein the power trading strategy generation program is configured to implement the steps of the power trading strategy generation method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a power trading strategy generation program is stored on the storage medium. When the power trading strategy generation program is executed by a processor, the steps of the power trading strategy generation method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a power trading strategy generation program, and when the power trading strategy generation program is executed by a processor, the steps of the power trading strategy generation method according to any one of claims 1 to 6 are implemented.

Images