Power consumption decision optimization method and device and storage medium

Abstract

The invention discloses a power utilization decision optimization method and device and a storage medium, and the method comprises the steps: building a prediction data model based on a seasonal time sequence model, and enabling the prediction data model to be used for predicting the real-time electricity price and the photovoltaic output of a user; classifying the electrical load and the electrical equipment respectively, and constructing an electrical equipment model according to a classification result; based on the prediction data model and the electrical equipment model, building a user side demand response model by taking user market income maximization as a target; and solving the user side demand response model to obtain an optimized power utilization strategy. According to the invention, a prediction data model for predicting real-time electricity price and user photovoltaic output is established based on a seasonal time sequence model, and a user side demand response model is constructed based on the prediction data model and an electrical equipment model with user market revenue maximization as a target. The method can effectively adapt to the characteristics of periodic and fluctuation changes of time sequence data, and improves the power utilization decision optimization effect.

Description

Technical Field

[0001] The present invention relates to the field of power supply technology, and in particular to a method, device and storage medium for optimizing power consumption decision. Background Art

[0002] Demand response (DR) refers to the market-based participation behavior of electricity users in response to published price signals or incentive mechanisms to change their inherent electricity consumption behavior patterns. By taking effective price signals or incentives, electricity users can be guided to optimize their electricity consumption strategies, thereby improving energy efficiency and ensuring grid stability.

[0003] Existing electricity consumption decision optimization methods are usually based on Markov decision process to optimize electricity consumption decisions. When processing data with obvious seasonal changes, the accuracy is low, resulting in poor electricity consumption decision optimization effect. Summary of the invention

[0004] The present invention provides a method, device and storage medium for optimizing electricity consumption decisions, so as to solve the technical problem that the existing electricity consumption decision optimization method is usually based on the Markov decision process to optimize electricity consumption decisions, and has low accuracy when processing data with obvious seasonal changes, resulting in poor electricity consumption decision optimization effect.

[0005] The present invention provides a method for optimizing electricity consumption decision-making, comprising:

[0006] Establishing a prediction data model based on a seasonal time series model, wherein the prediction data model is used to predict real-time electricity prices and user photovoltaic output;

[0007] Classify the power load and electrical equipment respectively, and build the electrical equipment model according to the classification results;

[0008] Based on the prediction data model and the electrical equipment model, a user-side demand response model is constructed with the goal of maximizing user market benefits;

[0009] Solving the user-side demand response model obtains an optimized electricity consumption strategy.

[0010] Furthermore, the establishment of a forecasting data model based on a seasonal time series model includes:

[0011] The least square method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series;

[0012] The forecast data model is constructed based on the seasonal time series model parameters.

[0013] Furthermore, the least square method is used to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series, including:

[0014] Get time series data;

[0015] Performing a stationarity test on the time series data, and if the time series data is not stationary, performing a differential process on the time series data until the time series data is stationary;

[0016] Determining an autoregressive order and a moving average order based on the time series data;

[0017] The least square method is adopted to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series according to the autoregressive order and the moving average order.

[0018] Furthermore, the classification results include load classification results and equipment classification results, wherein the power load classification results include interruptible loads, shiftable loads and basic loads; the equipment classification results include: power equipment, power generation equipment and energy storage equipment.

[0019] Furthermore, the user-side demand response model is constructed based on the prediction data model and the electrical equipment model with the goal of maximizing user market benefits, including:

[0020] Based on the prediction data model and the electrical equipment model, an objective function is constructed with the goal of maximizing the user's market revenue, the power consumption decision of the user's own electrical equipment is used as a variable, and constraints are constructed with power load and equipment type;

[0021] A user-side demand response model is constructed according to the objective function, the variables and the constraint conditions.

[0022] The present invention also provides a device for optimizing power consumption decision, comprising:

[0023] A prediction data model building module, used to build a prediction data model based on a seasonal time series model, wherein the prediction data model is used to predict real-time electricity prices and user photovoltaic output;

[0024] An electrical equipment model building module is used to classify power loads and electrical equipment respectively, and build an electrical equipment model according to the classification results;

[0025] A demand response model building module, used to build a user-side demand response model based on the prediction data model and the electrical equipment model with the goal of maximizing user market benefits;

[0026] The power consumption strategy solving module is used to solve the user-side demand response model to obtain an optimized power consumption strategy.

[0027] Furthermore, the prediction data model building module is also used for:

[0028] The least square method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series;

[0029] The forecast data model is constructed based on the seasonal time series model parameters.

[0030] Furthermore, the least square method is used to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series, including:

[0031] Get time series data;

[0032] Performing a stationarity test on the time series data, and if the time series data is not stationary, performing a differential process on the time series data until the time series data is stationary;

[0033] Determining an autoregressive order and a moving average order based on the time series data;

[0034] The least square method is adopted to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series according to the autoregressive order and the moving average order.

[0035] The present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the power consumption decision optimization method as described above is implemented.

[0036] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the electricity consumption decision optimization method as described above.

[0037] The embodiment of the present invention establishes a data model for predicting real-time electricity prices and user photovoltaic output based on a seasonal time series model, and constructs a user-side demand response model based on the prediction data model and the electrical equipment model with the goal of maximizing user market benefits. It can process time series data with obvious seasonal changes and effectively adapt to the characteristics of periodic and volatile changes in time series data, thereby effectively improving the prediction accuracy of real-time electricity prices and photovoltaic output, and further effectively improving the effect of optimizing electricity consumption decisions.

[0038] Furthermore, the least squares method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series, which can effectively capture the seasonal characteristics and trends of the time series data, thereby effectively improving the prediction accuracy of the model; and can adapt to the seasonal changes in electricity prices and photovoltaic output data, and remove seasonal influences through appropriate difference orders, making the model more flexible and able to adapt to data changes at different time scales. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of a method for optimizing power consumption decision-making provided by an embodiment of the present invention;

[0040] Figure 2 It is a schematic diagram of a demand response management process provided by an embodiment of the present invention;

[0041] Figure 3 It is a structural schematic diagram of a power consumption decision optimization device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0044] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0045] See also Figure 1 The present invention provides a method for optimizing electricity consumption decision-making, comprising:

[0046] S1. Establish a forecast data model based on the seasonal time series model, which is used to predict the real-time electricity price and the user's photovoltaic output;

[0047] In an embodiment of the present invention, a seasonal time series model can be used to establish a prediction data model. The seasonal time series model is a time series prediction model extended from the ARI MA model and is used to process data with seasonality. The seasonal time series model captures the seasonal changes of data by adding seasonal differences and seasonal autoregression and moving average terms. When establishing a prediction model for real-time electricity prices and user photovoltaic output, the SARI MA model can effectively consider seasonal factors, thereby effectively improving the accuracy of the prediction.

[0048] S2, classify the power load and electrical equipment respectively, and build an electrical equipment model according to the classification results;

[0049] In the embodiment of the present invention, electrical equipment and power loads can be classified according to the operation characteristics in time and space. The classification results include load classification results and equipment classification results, wherein the power load classification results include interruptible loads, shiftable loads and basic loads; the equipment classification results include: power equipment, power generation equipment and energy storage equipment.

[0050] In an embodiment of the present invention, an electrical equipment model is constructed based on the classification of power loads and electrical equipment, taking into account factors such as power consumption characteristics, response time and power costs, so that an accurate electrical equipment model can be constructed, and constraints of a user-side demand response model can be constructed based on the electrical equipment model, such as power load constraints and electrical equipment constraints.

[0051] S3. Based on the prediction data model and the electrical equipment model, a user-side demand response model is constructed with the goal of maximizing user market benefits;

[0052] In an embodiment of the present invention, a user-side demand response model is constructed based on a prediction data model and an electrical equipment model, and the characteristics of various electrical equipment described in the electrical equipment model are taken into consideration, including power consumption patterns, response times, adjustable capabilities, etc. Through these characteristics, the behavior of the equipment under different electricity prices or grid conditions can be understood. The classification of power loads in the electrical equipment model is also taken into consideration, and different types of power demand can be accurately predicted, thereby building a reliable user-side demand response model. According to the user-side demand response model, strategies related to user-side demand response can be solved, including user-side power optimization strategies.

[0053] S4. Solve the user-side demand response model to obtain the optimized electricity consumption strategy.

[0054] In the embodiment of the present invention, the user-side demand response model is a mixed integer linear programming model, which can be solved by the branch and bound method to obtain the user's optimized electricity consumption decision.

[0055] The embodiment of the present invention establishes a data model for predicting real-time electricity prices and user photovoltaic output based on a seasonal time series model, and constructs a user-side demand response model based on the prediction data model and the electrical equipment model with the goal of maximizing user market benefits. It can process time series data with obvious seasonal changes and effectively adapt to the characteristics of periodic and volatile changes in time series data, thereby effectively improving the prediction accuracy of real-time electricity prices and photovoltaic output, and further effectively improving the effect of optimizing electricity consumption decisions.

[0056] In one embodiment, S1, establishing a forecasting data model based on a seasonal time series model, comprising:

[0057] S11. Use the least squares method to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series;

[0058] In the embodiment of the present invention, the seasonal time series model parameters include autoregressive order, difference order, moving average order, etc.

[0059] S12. Construct a forecast data model based on seasonal time series model parameters.

[0060] In an embodiment of the present invention, the least squares method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series, which can effectively capture the seasonal characteristics and trends of the time series data, thereby effectively improving the prediction accuracy of the model; and can adapt to the seasonal changes in electricity prices and photovoltaic output data, and remove seasonal effects through appropriate difference orders, making the model more flexible and able to adapt to data changes at different time scales.

[0061] In one embodiment, S11, using the least squares method to determine seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series, includes:

[0062] S111, obtaining time series data;

[0063] In the embodiment of the present invention, time series data may be acquired through a database, and the time series data may be time series data of real-time electricity price and photovoltaic output to be processed.

[0064] S112, performing a stationarity test on the time series data. If the time series data is not stationary, performing a differential process on the time series data until the time series data is stationary;

[0065] In the embodiment of the present invention, a statistical test method may be used to detect the stationarity of the time series, such as an ADF test, a KPSS test, and the like.

[0066] S113, determining the autoregressive order and the moving average order according to the time series data;

[0067] In the embodiment of the present invention, the orders of autoregression (AR) and moving average (MA) may be determined through autocorrelation function (ACF) and partial autocorrelation function (PACF) graphs.

[0068] S114. Using the least squares method, the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series are determined according to the autoregressive order and the moving average order.

[0069] In the embodiment of the present invention, the least square method is used to minimize the sum of squares of the model prediction errors, thereby obtaining the optimal model parameters, which can further determine the accurate seasonal time series model parameters.

[0070] In one embodiment, step S3, based on the prediction data model and the electrical equipment model, constructing a user-side demand response model with the goal of maximizing user market benefits, includes:

[0071] S31. Based on the prediction data model and the electrical equipment model, an objective function is constructed with the goal of maximizing the user's market benefits, the power consumption decision of the user's own electrical equipment is used as a variable, and the power load and equipment type are used to construct constraint conditions;

[0072] S32. Construct a user-side demand response model based on the objective function, variables and constraints.

[0073] In the embodiment of the present invention, the objective function may also be to complete all electricity usage arrangements within a specified time period and minimize electricity costs while keeping the total electricity usage unchanged.

[0074] By constructing a user-side demand response model, the embodiment of the present invention can optimize the user's electricity consumption decision according to the prediction data model and the electrical equipment model, so as to help the user reduce electricity consumption during peak hours or transfer part of the electricity demand to off-peak hours, thereby reducing the peak-to-valley difference of the power grid and improving the overall energy utilization efficiency.

[0075] In one embodiment, step S2, respectively classifies the power load and electrical equipment, and constructs an electrical equipment model based on the classification results. The electrical equipment and power load can also be classified and modeled with a simulation step length of 15 minutes for a single period and 96 periods of a day as a planned optimization cycle.

[0076] In the embodiment of the present invention, the power load includes an interruptible load, a shiftable load and a basic load, wherein:

[0077] Interruptible load x: This type of load can interrupt power consumption at any time. The power consumption decision vector is mainly subject to the following constraints: First, a certain amount of power E must be consumed within a certain time period [t1, t2] x ; Second, the load size p x With upper and lower limits [p x_min ,p x_max ]; Third, the total load of the user ∑p x With upper limit E max .

[0078] Shiftable load y: Once this type of load starts to use electricity, it must complete the current working stage before stopping. The power consumption decision vector is mainly subject to the following constraints: first, it has n working stages, and the number of time periods required for each working stage is b1, b2, ..., b n , the electricity consumption decision only needs to select the starting time k of each working stage y ; The second is the total load of users∑(p x +p y ) has an upper limit E max .

[0079] Basic load z: Load that cannot be interrupted or shifted, also called basic load p z , which does not need to be considered in actual demand response.

[0080] Electrical equipment includes power generation equipment and energy storage equipment, including:

[0081] Power generation equipment v: Under normal circumstances, the electricity price is always higher than the on-grid electricity price of renewable energy such as photovoltaic or wind power, so the power generation equipment always gives priority to supplying electricity to users themselves. The decision vector of the power generation equipment is the amount of electricity c generated and used by the user in each period v The main constraints are: First, the amount of electricity generated and used by users c v Less than or equal to power output p v ; The second is the amount of electricity generated and used by the user c v Less than the total load of the user∑(p x +p y +p z ).

[0082] Energy storage device b: The decision vector of the energy storage device is the charge amount p in each period b and discharge capacity p d , and the energy storage device cannot be charged and discharged at the same time, mainly subject to the following constraints: First, the charging capacity p b and discharge capacity p d With upper and lower limits [p b_min ,p b_max ] and [p d_min,p d_max ]; secondly, considering the existence of power generation equipment, the discharge capacity p d Plus the amount of electricity generated and consumed by the user c v Less than the total load of the user∑(p x +p y +p z ); Third, the state of charge s of the energy storage device has upper and lower limits [s min ,s max ], the initial state is s min , and the charge and discharge efficiencies are η b and η d .

[0083] See also Figure 2 In one embodiment, a demand response management process diagram is provided. Figure 2 At the beginning of a period, the modeling and constraints of the user's electrical equipment are updated, the power generation output and real-time electricity price forecast of the ARI MA model are further updated, and the demand response management model for the future period is solved, that is, the power optimization decision for the future period is obtained. This period ends and the known variables or parameter values ​​are recorded for the next stage of prediction and solution.

[0084] The implementation of the embodiments of the present invention has the following beneficial effects:

[0085] The embodiment of the present invention establishes a data model for predicting real-time electricity prices and user photovoltaic output based on a seasonal time series model, and constructs a user-side demand response model based on the prediction data model and the electrical equipment model with the goal of maximizing user market benefits. It can process time series data with obvious seasonal changes and effectively adapt to the characteristics of periodic and volatile changes in time series data, thereby effectively improving the prediction accuracy of real-time electricity prices and photovoltaic output, and further effectively improving the effect of optimizing electricity consumption decisions.

[0086] Furthermore, the least squares method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series, which can effectively capture the seasonal characteristics and trends of the time series data, thereby effectively improving the prediction accuracy of the model; and can adapt to the seasonal changes in electricity prices and photovoltaic output data, and remove seasonal influences through appropriate difference orders, making the model more flexible and able to adapt to data changes at different time scales.

[0087] See also Figure 3 Based on the same inventive concept as the above embodiment, the present invention also provides a power consumption decision optimization device, comprising:

[0088] A prediction data model building module 10 is used to build a prediction data model based on a seasonal time series model, and the prediction data model is used to predict real-time electricity prices and user photovoltaic output;

[0089] The electrical equipment model building module 20 is used to classify the power load and the electrical equipment respectively, and build the electrical equipment model according to the classification results;

[0090] A demand response model building module 30 is used to build a user-side demand response model based on the prediction data model and the electrical equipment model with the goal of maximizing the user's market benefits;

[0091] The power consumption strategy solving module 40 is used to solve the user-side demand response model to obtain an optimized power consumption strategy.

[0092] In one embodiment, the prediction data model building module 10 is further used to:

[0093] The least square method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series;

[0094] Build a forecast data model based on seasonal time series model parameters.

[0095] In one embodiment, the least square method is used to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series, including:

[0096] Get time series data;

[0097] Perform a stationarity test on the time series data. If the time series data is not stationary, perform differential processing on the time series data until the time series data becomes stationary.

[0098] Determine the autoregressive order and moving average order based on time series data;

[0099] The least squares method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and photovoltaic output series according to the autoregressive order and the moving average order.

[0100] In one embodiment, the classification results include load classification results and equipment classification results, wherein the power load classification results include interruptible loads, shiftable loads and basic loads; the equipment classification results include: power equipment, power generation equipment and energy storage equipment.

[0101] In one embodiment, the demand response model building module 30 is further used to:

[0102] Based on the prediction data model and the electrical equipment model, the objective function is constructed with the goal of maximizing the user's market benefits, the power consumption decision of the user's own electrical equipment is used as a variable, and the power load and equipment type are used to construct the constraint conditions;

[0103] A user-side demand response model is constructed based on the objective function, variables and constraints.

[0104] Correspondingly, an embodiment of the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the power consumption decision optimization method of any one of the above embodiments is implemented.

[0105] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment, such as the demand response model building module 30, are implemented.

[0106] Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the demand response model construction module 30 is used to construct a user-side demand response model based on a prediction data model and an electrical equipment model with the goal of maximizing user market benefits.

[0107] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0108] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0109] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (F l ash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0110] Among them, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0111] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to perform the electricity consumption decision optimization of any one of the above embodiments.

[0112] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing electricity consumption decision, characterized in that: include: Establishing a prediction data model based on a seasonal time series model, wherein the prediction data model is used to predict real-time electricity prices and user photovoltaic output; Classify the power load and electrical equipment respectively, and build the electrical equipment model according to the classification results; Based on the prediction data model and the electrical equipment model, a user-side demand response model is constructed with the goal of maximizing user market benefits; Solving the user-side demand response model obtains an optimized electricity consumption strategy.

2. The method for optimizing electricity consumption decision-making according to claim 1, characterized in that: The method of establishing a forecasting data model based on a seasonal time series model includes: The least square method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series; The forecast data model is constructed based on the seasonal time series model parameters.

3. The method for optimizing electricity consumption decision-making according to claim 2, characterized in that: The least square method is used to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series, including: Get time series data; Performing a stationarity test on the time series data, and if the time series data is not stationary, performing a differential process on the time series data until the time series data is stationary; Determining an autoregressive order and a moving average order based on the time series data; The least square method is adopted to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series according to the autoregressive order and the moving average order.

4. The method for optimizing electricity consumption decision-making according to claim 1, characterized in that: The classification results include load classification results and equipment classification results, wherein the power load classification results include interruptible loads, shiftable loads and basic loads; the equipment classification results include: power equipment, power generation equipment and energy storage equipment.

5. The method for optimizing electricity consumption decision according to claim 1, characterized in that: The method of constructing a user-side demand response model based on the prediction data model and the electrical equipment model with the goal of maximizing user market benefits includes: Based on the prediction data model and the electrical equipment model, an objective function is constructed with the goal of maximizing the user's market revenue, the power consumption decision of the user's own electrical equipment is used as a variable, and constraints are constructed with power load and equipment type; A user-side demand response model is constructed according to the objective function, the variables and the constraint conditions.

6. A device for optimizing power consumption decision, characterized in that: include: A prediction data model building module, used to build a prediction data model based on a seasonal time series model, wherein the prediction data model is used to predict real-time electricity prices and user photovoltaic output; An electrical equipment model building module is used to classify power loads and electrical equipment respectively, and build an electrical equipment model according to the classification results; A demand response model building module, used to build a user-side demand response model based on the prediction data model and the electrical equipment model with the goal of maximizing user market benefits; The power consumption strategy solving module is used to solve the user-side demand response model to obtain an optimized power consumption strategy.

7. The power consumption decision optimization device according to claim 6, characterized in that: The prediction data model building module is also used for: The least square method is used to determine the parameters of the seasonal time series model applicable to the electricity price series and the photovoltaic output series; The forecast data model is constructed based on the seasonal time series model parameters.

8. The power consumption decision optimization device according to claim 7, characterized in that: The least square method is used to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series, including: Get time series data; Performing a stationarity test on the time series data, and if the time series data is not stationary, performing a differential process on the time series data until the time series data is stationary; Determining an autoregressive order and a moving average order based on the time series data; The least square method is adopted to determine the seasonal time series model parameters applicable to the electricity price series and the photovoltaic output series according to the autoregressive order and the moving average order.

9. A terminal device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for optimizing electricity consumption decision-making as described in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power consumption decision optimization method according to any one of claims 1 to 5.

Images