Medium-and-long-term electricity consumption prediction method and device of electricity consumption main body, medium and equipment
The GM(1,1) model iteratively processes historical data to enhance the accuracy of medium- and long-term electricity consumption forecasts, addressing the mismatch in existing methods and enabling precise power consumption predictions.
Patent Information
- Application Number
- CN202411330776.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2024-12-24
AI Technical Summary
Existing medium- and long-term electricity consumption forecasting methods struggle to achieve high-precision predictions due to mismatch with complex multi-subject consumption patterns, leading to significant forecasting errors.
A method involving gray prediction models, specifically the GM(1,1) model, is used to iteratively process historical electricity consumption data, generating accumulation sequences, and continuously updating the model to improve prediction accuracy for different electricity users.
The method enhances the relevance and accuracy of medium- and long-term electricity consumption forecasts by iteratively updating gray prediction models, allowing for precise power consumption predictions and enabling informed power dispatch and pricing strategies.
Smart Images
Figure CN119180380A_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to the field of power system power consumption analysis, and in particular to a method, device, medium and equipment for predicting medium- and long-term power consumption of power users. [Background technology]
[0002] In recent years, with the rapid development of science and technology and the continuous improvement of residents' personal economic capabilities, more and more electrical products have appeared in residents' daily lives, such as electronic products, hybrid electric vehicles, pure electric vehicles, etc., providing a more convenient and comfortable living environment and promoting the improvement of residents' living standards. At the same time, with the surge in the number of electrical products, the electricity consumption of different electricity users, such as residents, corporate users, and commercial users, has also shown a significant increase. Sustainable management of energy and efficient economic operation have become more important, which constitutes a coordination problem between electricity consumption demand and social and economic development. On the basis of ensuring the electricity consumption of various entities, improving electricity efficiency is a major response measure, which reduces the pollution of power generation to the environment, improves the safe and stable operation of the power system, and contributes to the sustainable development of society.
[0003] In particular, the medium- and long-term electricity consumption forecast is an important part of my country's existing power planning system, providing boundary conditions for subsequent power supply, power grid planning and other system-specific research. Its accuracy directly affects the quality of the entire power planning results, and is also an important indicator of the management level of power grid companies. At present, the medium- and long-term electricity consumption forecasting methods mainly include traditional forecasting methods, econometric model forecasting methods, and artificial intelligence forecasting methods. The forecasting errors still often fluctuate significantly in practical applications. The forecasting model is not fully matched with the current complex multi-subject electricity consumption situation, which makes it impossible to meet the high-precision forecasting needs of each subject's electricity consumption. [Summary of the invention]
[0004] The present invention provides a method, device, medium and equipment for predicting medium- and long-term electricity consumption of an electricity user, which solves the above-mentioned technical problems.
[0005] A first aspect of an embodiment of the present invention provides a method for predicting medium- and long-term electricity consumption of an electricity user, comprising the following steps:
[0006] Step 1, calculating the target time length between the current time node and the time node to be predicted, generating at least one intermediate time node according to the target time length, and establishing a time node set;
[0007] Step 2: Obtain historical electricity consumption data, where the historical electricity consumption data includes historical electricity consumption of different electricity users within a preset time range;
[0008] Step 3, processing the historical electricity consumption data to generate accumulation sequences corresponding to different electricity users, and generating a gray prediction model for electricity consumption of each electricity user based on the accumulation sequences;
[0009] Step 4, obtaining a first target time node closest to the current time node in the time node set, and generating a predicted power consumption of each power user at the first target time node based on the power consumption grey prediction model;
[0010] Step 5: using the predicted power consumption to update the power consumption grey prediction model, and deleting the first target time node from the time node set;
[0011] Step 6, repeat steps 4-5 until a gray prediction model of electricity consumption corresponding to different electricity users at the second target time node is generated to predict the electricity consumption of the target electricity user at the time node to be predicted, and the second target time node is closest to the time node to be predicted.
[0012] A second aspect of an embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for predicting medium- and long-term electricity consumption of an electricity user.
[0013] A third aspect of an embodiment of the present invention provides a medium- and long-term electricity consumption prediction device for an electricity user, comprising a computer-readable storage medium and a processor, wherein the processor implements the steps of the above-mentioned method for predicting the medium- and long-term electricity consumption of an electricity user when executing a computer program on the computer-readable storage medium.
[0014] A fourth aspect of an embodiment of the present invention provides a medium- and long-term electricity consumption prediction device for an electricity user, comprising a node generation module, an acquisition module, a construction module, a prediction module, an optimization module, and a calculation module.
[0015] The node generation module is used to calculate the target time length between the current time node and the time node to be predicted, generate at least one intermediate time node according to the target time length, and establish a time node set;
[0016] The acquisition module is used to acquire historical electricity consumption data, and the historical electricity consumption data includes historical electricity consumption of different electricity users within a preset time range;
[0017] The construction module is used to process the historical electricity consumption data to generate accumulation sequences corresponding to different electricity users, and generate a gray prediction model for electricity consumption of each electricity user based on the accumulation sequences;
[0018] The prediction module is used to obtain a first target time node closest to the current time node in the time node set, and generate a predicted power consumption of each power user at the first target time node based on the power consumption grey prediction model;
[0019] The updating module is used to update the power consumption grey prediction model using the predicted power consumption, and delete the first target time node from the time node set;
[0020] The control module is used to repeatedly drive the prediction module and the update module until a gray prediction model of electricity consumption corresponding to different electricity users at a second target time node is generated, so as to predict the electricity consumption of the target electricity user at the time node to be predicted, and the second target time node is closest to the time node to be predicted.
[0021] The beneficial effects of the present invention are as follows: the present invention provides a method, device, medium and equipment for predicting the medium- and long-term electricity consumption of electricity users, establishes gray electricity consumption prediction models for different electricity users respectively, and continuously iterates and updates the gray electricity consumption prediction model during the prediction process, thereby improving the pertinence and accuracy of the prediction results.
[0022] In order to make the above-mentioned objects, features and advantages of the invention more obvious and easy to understand, the preferred embodiments of the present invention are specifically cited below and described in detail with reference to the attached drawings.
Brief Description of the Drawings
[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0024] Figure 1 It is a flowchart of the method for predicting the medium- and long-term electricity consumption of the electricity user provided in Example 1;
[0025] Figure 2 It is a structural schematic diagram of a medium- and long-term electricity consumption prediction device for an electricity user provided in Example 2;
[0026] Figure 3 It is a structural diagram of the medium- and long-term electricity consumption prediction device for the electricity user provided in Example 3. [Specific implementation method]
[0027] In the following description, the specific embodiments of the present application will be described with reference to the steps and symbols performed by one or more computers, unless otherwise stated. Therefore, these steps and operations will be mentioned several times as being performed by a computer, and the computer execution referred to herein includes the operation of a computer processing unit by an electronic signal representing data in a structured form. This operation converts the data or maintains it at a location in the memory system of the computer, which can be reconfigured or otherwise change the operation of the computer in a manner familiar to testers in the field. The data structure maintained by the data is a physical location in the memory, which has specific characteristics defined by the data format. However, the principles of the present application are described in the above text, which does not represent a limitation, and testers in the field will understand that the various steps and operations described below can also be implemented in hardware.
[0028] The principles of the present application may be operated using many other general or specific purpose computing, communication environments or configurations. Examples of well-known computing systems, environments and configurations suitable for use with the present application may include, but are not limited to, handheld phones, personal computers, servers, multiprocessor systems, microcomputer-based systems, mainframe computers, and distributed computing environments, including any of the above systems or devices.
[0029] The terms "first", "second", and "third" in this application are used to distinguish different objects rather than to describe a specific order. In addition, the terms "include", "have", and any variations thereof are intended to cover non-exclusive inclusions.
[0030] The processing device may be a server, a physical host, a UE or other device, and may also exist in the form of a device cluster. The UE may be a smart phone, a tablet computer, a laptop computer, a personal digital assistant (PDA), a desktop computer, an all-in-one computer or other different types of terminal devices.
[0031] Next, we will introduce the regional electricity consumption prediction method provided by this application.
[0032] Figure 1 1 is a flow chart of a method for predicting the medium- and long-term electricity consumption of an electricity user provided in Example 1. Figure 1 As shown, the following steps are included:
[0033] Step 1, calculating the target time length between the current time node and the time node to be predicted, generating at least one intermediate time node according to the target time length, and establishing a time node set;
[0034] Step 2: Obtain historical electricity consumption data, where the historical electricity consumption data includes historical electricity consumption of different electricity users within a preset time range;
[0035] Step 3, processing the historical electricity consumption data to generate accumulation sequences corresponding to different electricity users, and generating a gray prediction model for electricity consumption of each electricity user based on the accumulation sequences;
[0036] Step 4, obtaining a first target time node closest to the current time node in the time node set, and generating a predicted power consumption of each power user at the first target time node based on the power consumption grey prediction model;
[0037] Step 5: using the predicted power consumption to update the power consumption grey prediction model, and deleting the first target time node from the time node set;
[0038] Step 6, repeat steps 4-5 until a gray prediction model of electricity consumption corresponding to different electricity users at the second target time node is generated to predict the electricity consumption of the target electricity user at the time node to be predicted, and the second target time node is closest to the time node to be predicted.
[0039] The above embodiment provides a method for predicting the medium- and long-term electricity consumption of electricity users. Grey electricity consumption prediction models are established for different electricity users respectively. During the prediction process, the grey electricity consumption prediction model is continuously iteratively updated according to the electricity consumption prediction data of adjacent time periods, thereby improving the pertinence and accuracy of the prediction results.
[0040] Let's continue with the above Figure 1 The various steps in the illustrated embodiment and the specific implementation methods that may be used in practical applications.
[0041] In a preferred implementation, the prediction result can also be put into practical application, which has further application value. For example, in a preferred embodiment, the method for predicting regional power consumption of the present invention further includes a control step, specifically: generating an early warning instruction based on the total predicted power consumption of all entities in the target area in the future time period, and the early warning instruction is used to remind the target user to execute the preset power dispatch plan and / or preset electricity price adjustment plan of the target area.
[0042] It is understandable that due to the fact that electricity is difficult to store or the storage cost is high, and it must also be based on safety considerations, the entire power supply system, from the production link, transportation link to the supply link, involves complex scheduling content. Therefore, when determining the prediction results of electricity consumption data, the power scheduling strategy for the target area can be further generated and processed accordingly based on the prediction results, so as to automatically allocate the scheduling content involved in the production link, transportation link or supply link in the target area.
[0043] For example, some regions may adopt a dynamic pricing approach to incentivize electricity consumption in the region based on considerations of both electricity consumption and power generation, so as to achieve the goal of low-cost electricity consumption and improved electricity efficiency, or appropriately suppress electricity consumption in the region to achieve the goal of high-cost electricity consumption and reduced electricity consumption. Typically, a step-by-step pricing strategy can be used to adjust electricity prices.
[0044] It is understandable that different electricity users, including commercial entities, industrial entities, and residential users, have different electricity usage patterns and different electricity prices. After obtaining the first historical electricity usage data of the target area, the present invention can classify and sort the data according to different entities, thereby obtaining the electricity usage data of each electricity user, and establishing a prediction model corresponding to each electricity user in a targeted manner.
[0045] In a specific embodiment, the gray prediction model of electricity consumption of the present application is the GM (1,1) model. The gray prediction model (Grey Pred ict i on Mode l) is a mathematical model for time series prediction with a small amount of data, which has the advantages of less required information, high accuracy, simple calculation, and easy verification. The gray prediction model processes the original data to generate a new sequence, called the "accumulated generated sequence", and then models and predicts the sequence. The GM (1,1) model is a relatively commonly used gray prediction model. The first 1 indicates that the model is a first-order differential equation model, and the second 1 indicates that the model is a single variable.
[0046] It can be understood that establishing a grey prediction model specifically includes the following steps: constructing a cumulative generation sequence, calculating a neighboring mean sequence, constructing a data matrix and a vector, estimating parameter values using the least squares method, bringing the parameter values into the model, and performing predictions, etc. The above steps are conventional technical solutions known to those skilled in the art and will not be described in detail herein.
[0047] In a preferred embodiment, the updating of the power consumption grey prediction model using the predicted power consumption specifically includes the following steps:
[0048] S501, replacing the earliest electricity consumption data in the historical electricity consumption data with the predicted electricity consumption of the electricity user, and arranging and updating the historical electricity consumption data in chronological order;
[0049] S502, generating accumulation sequences corresponding to different electricity users based on the updated historical electricity consumption data;
[0050] S503, constructing a GM(1,1) grey differential equation, and fitting the parameter values of the GM(1,1) grey differential equation according to the cumulative sequence and the least square method to generate the grey prediction model for electricity consumption.
[0051] In a more preferred embodiment, the updating of the power consumption grey prediction model using the predicted power consumption further includes:
[0052] S504, querying the seasonal impact coefficient table to obtain the seasonal impact coefficient corresponding to the target electricity user at the first target time node;
[0053] S505, optimizing the predicted power consumption of the target power user at the first target time node according to the seasonal impact coefficient;
[0054] S506, using the optimized predicted power consumption to update the target power user's power consumption grey prediction model, so as to increase the influence of factors such as season when using the grey model to predict future power consumption, and obtain a more accurate prediction result.
[0055] It can be understood that the medium- and long-term electricity consumption forecast of the present invention is mainly to forecast the electricity consumption of the electricity user in n years, n>2, such as forecasting the electricity consumption in 3 years and 5 years. The preferred embodiment can set different numbers of intermediate time nodes according to the length of this time. Specifically, the generation of at least one intermediate time node according to the target time length is specifically:
[0056] S101, establishing a preset node quantity table, wherein the preset node quantity table includes the number of intermediate nodes corresponding to different target time length ranges, and different electricity users have different or the same number of intermediate nodes in the same target time length range;
[0057] S102, querying the preset node quantity table, and obtaining the target intermediate node quantity of the corresponding power-using entity according to the target time length between the current time node and the time node to be predicted;
[0058] S103: Generate at least one intermediate time node corresponding to the target time length according to the target number of intermediate nodes.
[0059] In a preferred embodiment, the at least one intermediate time node divides the target time length into multiple time periods of the same time length, or the at least one intermediate time node divides the target time length into multiple time periods of decreasing time lengths. It can be understood that the more time nodes there are, the more iterations of the gray model, and the more accurate the prediction results obtained. Or when the predicted years are long, the time interval can also be uneven, that is, the number of iterations close to the current time node is relatively small, and the number of iterations close to the time node to be predicted increases, thereby increasing the accuracy of the prediction while ensuring efficiency.
[0060] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0061] The embodiment of the present invention further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned method for predicting the medium- and long-term electricity consumption of an electricity user is implemented.
[0062] Figure 2 is a schematic diagram of the structure of the medium- and long-term electricity consumption prediction device for the electricity user provided in Example 2. Figure 2 As shown, it includes a node generation module 100, an acquisition module 200, a construction module 300, a prediction module 4400, an optimization module 500 and a calculation module 600.
[0063] The node generation module 100 is used to calculate the target time length between the current time node and the time node to be predicted, generate at least one intermediate time node according to the target time length, and establish a time node set;
[0064] The acquisition module 200 is used to acquire historical electricity consumption data, and the historical electricity consumption data includes historical electricity consumption of different electricity users within a preset time range;
[0065] The construction module 300 is used to process the historical electricity consumption data to generate accumulation sequences corresponding to different electricity users, and generate a gray prediction model for electricity consumption of each electricity user based on the accumulation sequences;
[0066] The prediction module 400 is used to obtain a first target time node closest to the current time node in the time node set, and generate a predicted power consumption of each power user at the first target time node based on the power consumption grey prediction model;
[0067] The updating module 500 is used to update the power consumption grey prediction model using the predicted power consumption, and delete the first target time node from the time node set;
[0068] The control module 600 is used to repeatedly drive the prediction module and the update module until a gray prediction model of electricity consumption corresponding to different electricity users at the second target time node is generated to predict the electricity consumption of the target electricity user at the time node to be predicted, and the second target time node is closest to the time node to be predicted.
[0069] The above embodiment provides a medium- and long-term electricity consumption prediction device for electricity users, establishes electricity consumption grey prediction models for different electricity users respectively, and continuously iterates and updates the electricity consumption grey prediction model during the prediction process, thereby improving the pertinence and accuracy of the prediction results.
[0070] In a preferred embodiment, the update module 500 specifically includes:
[0071] A replacement unit, used to replace the earliest electricity consumption data in the historical electricity consumption data with the predicted electricity consumption of the electricity user, and to sort and update the historical electricity consumption data in chronological order;
[0072] A sequence generating unit, configured to generate accumulation sequences corresponding to different electricity users based on the updated historical electricity consumption data;
[0073] The model building unit is used to construct the GM (1, 1) grey differential equation, and to fit the parameter values of the GM (1, 1) grey differential equation according to the cumulative sequence and the least square method to generate the grey prediction model for electricity consumption.
[0074] In a preferred embodiment, the update module 500 also includes an optimization unit, which is used to query the seasonal impact coefficient table to obtain the seasonal impact coefficient corresponding to the target electricity user at the first target time node; and to optimize the predicted electricity consumption of the target electricity user at the first target time node according to the seasonal impact coefficient, so as to update the gray prediction model of electricity consumption of the target electricity user using the optimized predicted electricity consumption.
[0075] In a preferred embodiment, the node generation module 100 specifically includes:
[0076] A table establishment unit, used to establish a preset node quantity table, wherein the preset node quantity table includes the number of intermediate nodes corresponding to different target time length ranges, and different electricity users have different or the same number of intermediate nodes in the same target time length range;
[0077] A query unit, used to query the preset node quantity table, and obtain the target intermediate node quantity of the corresponding power-using entity according to the target time length between the current time node and the time node to be predicted;
[0078] A node generation unit is used to generate at least one intermediate time node corresponding to the target time length according to the target intermediate node quantity.
[0079] In a preferred embodiment, the at least one intermediate time node divides the target time length into a plurality of time periods of equal time length, or the at least one intermediate time node divides the target time length into a plurality of time periods of successively decreasing time length.
[0080] In a preferred embodiment, the medium- and long-term electricity consumption prediction device for the electricity user also includes a control module, which is used to generate an early warning instruction based on the predicted electricity consumption of all electricity users at each time node in the time node set, and the early warning instruction is used to remind the target user to execute a preset power dispatch plan and / or a preset electricity price adjustment plan for the electricity user.
[0081] An embodiment of the present invention also provides a medium- and long-term electricity consumption prediction device for an electricity user, comprising a computer-readable storage medium and a processor, wherein the processor implements the steps of the above-mentioned medium- and long-term electricity consumption prediction method for an electricity user when executing a computer program on the computer-readable storage medium.
[0082] Figure 3 : is a schematic diagram of the structure of a medium- and long-term electricity consumption prediction device for an electricity user provided in Embodiment 3 of the present invention, such as Figure 3 As shown, the medium- and long-term electricity consumption prediction device 8 of the electricity user in this embodiment includes: a processor 80, a readable storage medium 81, and a computer program 82 stored in the readable storage medium 81 and executable on the processor 80. When the processor 80 executes the computer program 82, the steps in the above-mentioned various method embodiments are implemented, for example Figure 1 Alternatively, when the processor 80 executes the computer program 82, the functions of each module in the above-mentioned device embodiments are realized, for example Figure 2 Functionality of the modules shown.
[0083] Exemplarily, the computer program 82 may be divided into one or more modules, which are stored in the readable storage medium 81 and executed by the processor 80 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 82 in the medium- and long-term power consumption prediction device 8 of the power user.
[0084] The medium- and long-term electricity consumption prediction device 8 of the electricity user may include, but is not limited to, a processor 80 and a readable storage medium 81. Those skilled in the art will understand that Figure 3It is only an example of the medium- and long-term electricity consumption prediction device 8 for the electricity user, and does not constitute a limitation of the medium- and long-term electricity consumption prediction device 8 for the electricity user. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the medium- and long-term electricity consumption prediction device for the electricity user may also include a power management module, an operation processing module, input and output devices, a network access device, a bus, etc.
[0085] The processor 80 may be a central processing unit (CPU), or 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.
[0086] The readable storage medium 81 may be an internal storage unit of the medium- and long-term electricity consumption prediction device 8 of the electricity user, such as a hard disk or memory of the medium- and long-term electricity consumption prediction device 8 of the electricity user. The readable storage medium 81 may also be an external storage device of the medium- and long-term electricity consumption prediction device 8 of the electricity user, such as a plug-in hard disk, a smart memory card (SmartMed iaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the medium- and long-term electricity consumption prediction device 8 of the electricity user. Further, the readable storage medium 81 may also include both an internal storage unit and an external storage device of the medium- and long-term electricity consumption prediction device 8 of the electricity user. The readable storage medium 81 is used to store the computer program and other programs and data required by the medium- and long-term electricity consumption prediction device of the electricity user. The readable storage medium 81 may also be used to temporarily store data that has been output or is to be output.
[0087] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0088] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0089] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0090] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0091] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0092] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0093] The present invention is not limited to what is described in the specification and implementation modes, and therefore additional advantages and modifications can be easily realized by those skilled in the art. Therefore, without departing from the spirit and scope of the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details, representative devices, and illustrative examples shown and described herein.
Claims
1. A method for predicting medium- and long-term electricity consumption of an electricity user, characterized in that: The following steps are involved: Step 1, calculating the target time length between the current time node and the time node to be predicted, generating at least one intermediate time node according to the target time length, and establishing a time node set; Step 2: Obtain historical electricity consumption data, where the historical electricity consumption data includes historical electricity consumption of different electricity users within a preset time range; Step 3, processing the historical electricity consumption data to generate accumulation sequences corresponding to different electricity users, and generating a gray prediction model for electricity consumption of each electricity user based on the accumulation sequences; Step 4, obtaining a first target time node closest to the current time node in the time node set, and generating a predicted power consumption of each power user at the first target time node based on the power consumption grey prediction model; Step 5: using the predicted power consumption to update the power consumption grey prediction model, and deleting the first target time node from the time node set; Step 6, repeat steps 4-5 until a gray prediction model of electricity consumption corresponding to different electricity users at the second target time node is generated to predict the electricity consumption of the target electricity user at the time node to be predicted, and the second target time node is closest to the time node to be predicted.
2. The method for predicting medium- and long-term electricity consumption of electricity users according to claim 1 is characterized in that: The method of updating the power consumption grey prediction model by using the predicted power consumption specifically comprises the following steps: Replacing the earliest electricity consumption data in the historical electricity consumption data with the predicted electricity consumption of the electricity user, and arranging and updating the historical electricity consumption data in chronological order; Generate accumulation sequences corresponding to different electricity users based on the updated historical electricity consumption data; A GM(1,1) grey differential equation is constructed, and each parameter value of the GM(1,1) grey differential equation is fitted according to the cumulative sequence and the least square method to generate the grey prediction model for electricity consumption.
3. The method for predicting the medium- and long-term electricity consumption of the electricity user according to claim 2 is characterized in that: The method of updating the power consumption grey prediction model by using the predicted power consumption further includes: Query the seasonal impact coefficient table to obtain the seasonal impact coefficient corresponding to the target electricity user at the first target time node; Optimizing the predicted power consumption of the target power user at the first target time node according to the seasonal impact coefficient; The optimized predicted power consumption is used to update the power consumption grey prediction model of the target power consumer.
4. The method for predicting medium- and long-term electricity consumption of an electricity user according to any one of claims 1 to 3, characterized in that: At least one intermediate time node is generated according to the target time length, specifically: Establishing a preset node quantity table, wherein the preset node quantity table includes the number of intermediate nodes corresponding to different target time length ranges, and different electricity users have different or the same number of intermediate nodes in the same target time length range; Query the preset node quantity table, and obtain the target intermediate node quantity of the corresponding power-using entity according to the target time length between the current time node and the time node to be predicted; At least one intermediate time node corresponding to the target time length is generated according to the target intermediate node quantity.
5. The method for predicting medium- and long-term electricity consumption of electricity users according to claim 4 is characterized in that: The at least one intermediate time node divides the target time length into a plurality of time periods of equal time length, or the at least one intermediate time node divides the target time length into a plurality of time periods of successively decreasing time length.
6. The method for predicting medium- and long-term electricity consumption of electricity users according to claim 4, characterized in that: It also includes a control step, specifically: generating a warning instruction based on the predicted power consumption of all electricity users at each time node in the time node set, and the warning instruction is used to remind the target user to execute a preset power dispatch plan and / or a preset electricity price adjustment plan for the electricity user.
7. A device for predicting medium- and long-term electricity consumption of an electricity user, characterized in that: It includes node generation module, acquisition module, construction module, prediction module, optimization module and calculation module. The node generation module is used to calculate the target time length between the current time node and the time node to be predicted, generate at least one intermediate time node according to the target time length, and establish a time node set; The acquisition module is used to acquire historical electricity consumption data, and the historical electricity consumption data includes historical electricity consumption of different electricity users within a preset time range; The construction module is used to process the historical electricity consumption data to generate accumulation sequences corresponding to different electricity users, and generate a gray prediction model for electricity consumption of each electricity user based on the accumulation sequences; The prediction module is used to obtain a first target time node closest to the current time node in the time node set, and generate a predicted power consumption of each power user at the first target time node based on the power consumption grey prediction model; The updating module is used to update the power consumption grey prediction model using the predicted power consumption, and delete the first target time node from the time node set; The control module is used to repeatedly drive the prediction module and the update module until a gray prediction model of electricity consumption corresponding to different electricity users at a second target time node is generated, so as to predict the electricity consumption of the target electricity user at the time node to be predicted, and the second target time node is closest to the time node to be predicted.
8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for predicting the medium- and long-term electricity consumption of an electricity user as described in any one of claims 1 to 6 above is implemented.
9. A device for predicting medium- and long-term electricity consumption of an electricity user, comprising a computer-readable storage medium and a processor, characterized in that: When the processor executes the computer program on the computer-readable storage medium, the processor implements the steps of the method for predicting the medium- and long-term electricity consumption of an electricity user as described in any one of claims 1 to 6 above.