An electric heating load prediction method and device based on error feedback tracking prediction

Abstract

The present application relates to a kind of based on error feedback tracking prediction electric heating load prediction method and device, including obtaining the electric heating load actual value and electric heating load prediction value of the electric heating load of the region to be predicted in preset historical time, according to the electric heating load actual value and electric heating load prediction value of preset historical time, obtain the electric heating load prediction correction value of the previous time of current time;According to the electric heating load prediction value of the previous time of current time, the electric heating load prediction correction value of the previous time of current time and the external influence factor independent variable value of current time, obtain the electric heating load prediction value of current time.The present application can provide similar prediction accuracy with deep learning prediction method under the premise, without training step, improve the explainability of model, while avoiding overfitting, greatly reduce data demand.The present application also relates to a kind of equipment and storage medium.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to an electric heat load prediction method and device based on error feedback tracking prediction. Background Art

[0002] The load of electric heating equipment exhibits both a degree of randomness and a close correlation with external factors such as weather. Existing load forecasting methods typically treat load data as time series data. Deep learning-based methods, such as long short-term memory (LSTM), train models on historical load data and then make predictions based on the resulting models. Current deep learning-based forecasting methods for electric heating loads suffer from the following drawbacks: 1. Overfitting: Deep learning methods like LSTM have high dataset requirements. Training datasets must be of a certain size and quality to achieve effective forecasts. If the dataset is small or of poor quality, overfitting can often occur, resulting in poor prediction performance for models that perform well on the training dataset. For non-time series data, such as image recognition, cross-validation and other methods are generally used to mitigate overfitting. However, for time series data, which has a strict order relationship between data, this approach cannot be applied. Instead, methods such as sliding window methods can be used. However, sliding window methods further divide the already small dataset into smaller ones, exacerbating model overfitting. 2. Black box problem: Deep learning-based methods are essentially based on deep neural networks and currently lack theoretical interpretability. This means that detailed analysis of forecast results and inference of long-term load trends and their influencing factors are impossible. 3. Prediction speed issue: Deep learning-based methods require training the forecast model using a large amount of existing data. The training process involves multiple rounds of iterative calculations. Every time the dataset changes, the model needs to be retrained, resulting in a significant consumption of computing resources for each forecast and slowing down the forecast speed.

[0003] These defects limit the universality and practicality of existing methods in load forecasting, and there is an urgent need for more interpretable and efficient technical solutions to cope with the complexity of electric heating equipment loads. Summary of the Invention

[0004] In response to the problems of universality and practicality of prediction methods based on deep learning, the present invention provides an electric heating load prediction method and device based on error feedback tracking prediction.

[0005] In a first aspect, the present invention provides a method for predicting electric and thermal loads based on error feedback tracking prediction, the method comprising:

[0006] Obtaining the actual value and predicted value of the electric heating load of the area to be predicted at a preset historical moment, wherein the preset historical moment includes a moment before the current moment and multiple consecutive historical moments;

[0007] Obtaining a predicted correction value of the electric heating load at a moment before the current moment based on the actual value of the electric heating load at the preset historical moment and the predicted value of the electric heating load;

[0008] The electric heating load prediction value at the current moment is obtained according to the electric heating load prediction value at the moment before the current moment, the electric heating load prediction correction value at the moment before the current moment and the independent variable value of the external influencing factor at the current moment.

[0009] Based on the above technical solution, further, the electric heating load forecast correction value at the moment before the current moment is obtained based on the actual electric heating load value and the electric heating load forecast value at the preset historical moment, specifically including:

[0010] Subtracting the actual value of the electric heating load at each historical moment from the corresponding electric heating load forecast value to obtain an electric heating load forecast error value at each historical moment;

[0011] The PID control parameters and the electric heating load prediction error value at the preset historical moment are input into a time domain expression to obtain the electric heating load prediction correction value at the moment before the current moment.

[0012] Based on the above technical solution, further, the PID control parameter and the electric heating load prediction error value at the preset historical moment are input into the time domain expression to obtain the electric heating load prediction correction value at the moment before the current moment, specifically including:

[0013] The moment before the current moment m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m -3 The electric heating load prediction error value e m-3 Input the time domain expression and get m The electric heating load prediction correction value Δ Y m-1 , wherein the time domain expression is:

[0014]

[0015] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, It is the differential parameter in the PID control parameter.

[0016] Based on the above technical solution, further, the electric heating load forecast correction value at the moment before the current moment is obtained based on the actual electric heating load value and the electric heating load forecast value at the preset historical moment, specifically including:

[0017] Subtracting the actual value of the electric heating load at each historical moment from the corresponding electric heating load forecast value to obtain an electric heating load forecast error value at each historical moment;

[0018] The PID control parameters and the electric heating load prediction error value at the preset historical moment are input into the transfer function to obtain the electric heating load prediction correction value at the moment before the current moment.

[0019] Based on the above technical solution, further, the PID control parameter and the electric heating load prediction error value at the preset historical moment are input into the transfer function to obtain the electric heating load prediction correction value at the moment before the current moment, specifically including:

[0020] The first m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m The electric heating load prediction error value at time -1 e m-3 Input the transfer function and get m The electric heating load prediction correction value Δ at time -1 Y m-1 , where the transfer function:

[0021]

[0022] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, is the differential parameter in the PID control parameter, It is an operator.

[0023] Based on the above technical solution, further, the electric heating load prediction value at the current moment is obtained according to the electric heating load prediction value at the moment before the current moment, the electric heating load prediction correction value at the moment before the current moment, and the independent variable value of the external influencing factor at the current moment, specifically including:

[0024] According to the electric heating load prediction value at the previous moment , the electric heating load prediction correction value Δ at the moment before the current moment Y m-1 and the external influencing factor independent variable value at the current moment X m Input the correction formula to obtain the electric heating load forecast value at the current moment ;

[0025] The correction formula is ,in d is a first-order difference operator.

[0026] Based on the above technical solution, further, the independent variable value of the external influencing factor is weather data.

[0027] In a second aspect, the present invention further provides an electric heating load prediction device based on error feedback tracking prediction, the device comprising:

[0028] An acquisition module is used to obtain the actual value and predicted value of the electric heating load of the area to be predicted at a preset historical moment, wherein the preset historical moment includes the moment before the current moment and multiple consecutive historical moments;

[0029] a calculation module for obtaining a predicted correction value of the electric heating load at a moment before the current moment based on the actual value of the electric heating load at the preset historical moment and the predicted value of the electric heating load;

[0030] The correction module is used to obtain the electric heating load prediction value at the current moment based on the electric heating load prediction value at the moment before the current moment, the electric heating load prediction correction value at the moment before the current moment and the independent variable value of the external influencing factor at the current moment.

[0031] Based on the above technical solution, further, the calculation module is specifically used to subtract the actual value of the electric heating load at each historical moment from the corresponding electric heating load forecast value to obtain the electric heating load forecast error value at each historical moment;

[0032] The PID control parameters and the electric heating load prediction error value at the preset historical moment are input into a time domain expression to obtain the electric heating load prediction correction value at the moment before the current moment.

[0033] Based on the above technical solution, further, the calculation module is specifically used to calculate the previous moment of the current moment m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2e m-2 Hedi m -3 The electric heating load prediction error value e m-3 Input the time domain expression and get m The electric heating load prediction correction value Δ Y m-1 , wherein the time domain expression is:

[0034]

[0035] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, It is the differential parameter in the PID control parameter.

[0036] Based on the above technical solution, further, the calculation module is specifically used to subtract the actual value of the electric heating load at each historical moment from the corresponding electric heating load forecast value to obtain the electric heating load forecast error value at each historical moment;

[0037] The PID control parameters and the electric heating load prediction error value at the preset historical moment are input into the transfer function to obtain the electric heating load prediction correction value at the moment before the current moment.

[0038] Based on the above technical solution, further, the calculation module is specifically used to convert the m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m The electric heating load prediction error value at time -1 e m-3 Input the transfer function and get m The electric heating load prediction correction value Δ at time -1 Y m-1 , where the transfer function:

[0039]

[0040] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, is the differential parameter in the PID control parameter, It is an operator.

[0041] Based on the above technical solution, further, the correction module is specifically used to calculate the electric heating load prediction value at the previous moment according to the current moment. , the electric heating load prediction correction value Δ at the moment before the current moment Y m-1 and the external influencing factor independent variable value at the current moment X m Input the correction formula to obtain the electric heating load forecast value at the current moment ;

[0042] The correction formula is ,in d is a first-order difference operator.

[0043] Based on the above technical solution, further, the independent variable value of the external influencing factor is weather data.

[0044] In a third aspect, the present invention further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the electric heating load prediction method based on error feedback tracking prediction described in any one of the first aspects is implemented.

[0045] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the electric heating load prediction method based on error feedback tracking prediction described in any one of the first aspects.

[0046] The present invention provides a method and device for predicting electric heating loads based on error feedback tracking prediction. The method comprises obtaining the actual electric heating load value and the predicted electric heating load value of the area to be predicted at a preset historical moment; obtaining a corrected electric heating load prediction value for the moment before the current moment based on the actual electric heating load value and the predicted electric heating load value at the preset historical moment; and obtaining the predicted electric heating load value for the current moment based on the predicted electric heating load value for the moment before the current moment, the corrected electric heating load prediction value for the moment before the current moment, and the independent variable value of the external influencing factor at the current moment. This invention can provide prediction accuracy similar to that of deep learning prediction methods without requiring a training step, improving the interpretability of the model, while avoiding overfitting and significantly reducing data requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which constitute part of the present invention, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0048] Figure 11 is a flow chart of an electric and thermal load prediction method based on error feedback tracking prediction provided by an embodiment of the present invention;

[0049] Figure 2 1 is a flow chart of an electric and thermal load prediction method based on error feedback tracking prediction provided by another embodiment of the present invention;

[0050] Figure 3 1 is a flow chart of an electric and thermal load prediction method based on error feedback tracking prediction provided by another embodiment of the present invention;

[0051] Figure 4 It is a module schematic diagram of an electric heating load prediction device based on error feedback tracking prediction provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0052] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other.

[0053] The following detailed description is an exemplary description and is intended to provide further detailed description of the present invention. Unless otherwise indicated, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0054] The following will be combined with the Figure 1 , the electric heating load prediction method based on error feedback tracking prediction provided by an embodiment of the present invention is described, comprising the following steps:

[0055] S1. Obtaining the actual value and predicted value of the electric heating load of the area to be predicted at a preset historical moment, wherein the preset historical moment includes a moment before the current moment and a plurality of consecutive historical moments.

[0056] Specifically, the preset historical moments include the moment before the current moment m, ie, the m-1th historical moment, the m-2th historical moment, and the m-3th historical moment.

[0057] The electric heating load in the present invention refers to the load used for electric heating during the heating period. At each historical moment, the actual value of the electric heating load and the predicted value of the electric heating load are statistically recorded.

[0058] S2. Obtain a predicted corrected value of the electric heating load at a moment before the current moment based on the actual value of the electric heating load at the preset historical moment and the predicted value of the electric heating load.

[0059] S3. Obtain the electric heating load prediction value at the current moment according to the electric heating load prediction value at the moment before the current moment, the electric heating load prediction correction value at the moment before the current moment, and the independent variable value of the external influencing factor at the current moment.

[0060] Specifically, the independent variables of external influencing factors include weather data such as temperature, which is not specifically limited in this application.

[0061] Based on the above embodiment, step S2 further specifically includes:

[0062] S21 . Subtract the actual value of the electric heating load at each historical moment from the corresponding predicted value of the electric heating load to obtain an electric heating load prediction error value at each historical moment.

[0063] S22. Input the PID control parameter and the electric heating load prediction error value at the preset historical moment into a time domain expression to obtain the electric heating load prediction correction value at the moment before the current moment.

[0064] Based on the above embodiment, step S22 further specifically includes:

[0065] The moment before the current moment m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m -3 The electric heating load prediction error value e m-3 Input the time domain expression and get m The electric heating load prediction correction value Δ Y m-1 , wherein the time domain expression is:

[0066]

[0067] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, It is the differential parameter in the PID control parameter.

[0068] Based on the above embodiment, step S2 further specifically includes:

[0069] S21′, subtracting the actual value of the electric heating load at each historical moment from the corresponding electric heating load forecast value to obtain an electric heating load forecast error value at each historical moment.

[0070] S22', inputting the PID control parameter and the electric heating load prediction error value at the preset historical moment into a transfer function to obtain the electric heating load prediction correction value at the moment before the current moment.

[0071] Based on the above embodiment, step S22′ further specifically includes:

[0072] The first m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m The electric heating load prediction error value at time -1 e m-3 Input the transfer function and get m The electric heating load prediction correction value Δ at time -1 Y m-1 , where the transfer function:

[0073]

[0074] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, is the differential parameter in the PID control parameter, It is an operator.

[0075] Specifically, in this embodiment, the time domain expression in step S22 and the transfer function in step 22 ′ can be converted into each other through Laplace transform.

[0076] Based on the above embodiment, step S3 further specifically includes:

[0077] According to the electric heating load prediction value at the previous moment , the electric heating load prediction correction value Δ at the moment before the current moment Y m-1 and the external influencing factor independent variable value at the current moment X m Input the correction formula to obtain the electric heating load forecast value at the current moment .

[0078] The correction formula is ,in d is a first-order difference operator.

[0079] Based on the above embodiment, further, the independent variable value of the external influencing factor is weather data.

[0080] This embodiment involves an electric heating load prediction method based on error feedback tracking prediction, including obtaining the actual electric heating load value and electric heating load prediction value of the electric heating load in the area to be predicted at a preset historical moment, obtaining the electric heating load prediction correction value at the moment before the current moment based on the actual electric heating load value and electric heating load prediction value at the preset historical moment; and obtaining the electric heating load prediction value at the current moment based on the electric heating load prediction value at the moment before the current moment, the electric heating load prediction correction value at the moment before the current moment, and the independent variable value of the external influencing factor at the current moment. This embodiment can provide similar prediction accuracy to deep learning prediction methods without the need for a training step, improving the interpretability of the model, while avoiding overfitting and significantly reducing data requirements.

[0081] Specifically, this embodiment can be implemented in a PID controller.

[0082] The following is an explanation of the technical effects of this embodiment:

[0083] 1. Stability judgment of prediction model: It can provide the stability criterion of the prediction model. According to the Julius criterion of discrete systems, the Julius table can be written for the transfer function as shown in Table 1:

[0084]

[0085] Table 1 Julius table

[0086] in

[0087]

[0088]

[0089] The transfer function is guaranteed to be stable as long as the following conditions are met:

[0090]

[0091] in is the denominator polynomial of the transfer function.

[0092] The prediction error is predictable: The prediction method proposed in this embodiment can calculate its steady-state prediction error by the following method:

[0093]

[0094] For step input , the error result of the steady-state prediction error is

[0095]

[0096] In this embodiment, the data volume requirement is small and the prediction speed is fast: Unlike the deep learning method that requires a large amount of data for model pre-training, the method proposed in the present invention only needs historical values ​​and predicted values ​​at several past moments to complete the prediction, with a small data requirement and a fast prediction speed.

[0097] This paper proposes a prediction method based on error feedback tracking prediction, which can solve the "black box" problem of traditional deep learning prediction methods, while significantly reducing data requirements and improving prediction speed. Furthermore, by using a stability criterion for the prediction method, the stability of the prediction model can be ensured in advance.

[0098] The following will be combined with the Figure 2 and Figure 3 , the electric heating load prediction method based on error feedback tracking prediction provided by an embodiment of the present invention is described in actual scenarios:

[0099] This embodiment adopts a method based on error feedback tracking prediction, which can improve the interpretability of the model while avoiding overfitting and significantly reducing data requirements under the premise of prediction accuracy similar to that of deep learning prediction methods. Figure 3 As shown, they are described below.

[0100] The prediction principle block diagram is shown in Figure 2. The steps of ARDL prediction are as follows: express k The actual value of the variable to be predicted at time , express k The predicted value of the variable to be predicted at any moment, express k The value of the independent variable at any given moment, such as weather data.

[0101] Prediction steps:

[0102] 1. Obtaining historical forecast errors

[0103] Historical forecast errors

[0104] In the picture represents the actual value of the variable to be predicted at time K, Indicates the predicted value of the variable to be predicted at time K, Represents the value of the independent variable at time K, such as weather data.

[0105] 2. The error-based correction value is obtained by the following time domain expression:

[0106]

[0107] in are the coefficients of the PID controller.

[0108] At the same time, the correction value based on the error can also be obtained through the following discrete transfer function. The discrete transfer function between the predicted value and the actual value is:

[0109]

[0110] in .

[0111] It should be noted that the above time domain expression and transfer function are equivalent.

[0112] 3. Weather data correction and forecast

[0113]

[0114] Where d is the first-order difference operator.

[0115] This embodiment can provide similar prediction accuracy as deep learning prediction methods without the need for training steps, improve the interpretability of the model, avoid overfitting, and significantly reduce data requirements.

[0116] The following will be combined with the Figure 4 The electric heating load prediction device based on error feedback tracking prediction provided by an embodiment of the present invention is described. The device includes:

[0117] The acquisition module is used to obtain the actual value and predicted value of the electric heating load of the area to be predicted at a preset historical moment, where the preset historical moment includes the moment before the current moment and multiple consecutive historical moments.

[0118] The calculation module is used to obtain the electric heating load forecast correction value at the moment before the current moment based on the actual value of the electric heating load and the electric heating load forecast value at the preset historical moment.

[0119] The correction module is used to obtain the electric heating load prediction value at the current moment based on the electric heating load prediction value at the moment before the current moment, the electric heating load prediction correction value at the moment before the current moment and the independent variable value of the external influencing factor at the current moment.

[0120] Based on the above embodiment, further, the calculation module is specifically used to subtract the actual value of the electric heating load at each historical moment from the corresponding electric heating load prediction value to obtain the electric heating load prediction error value at each historical moment.

[0121] The PID control parameters and the electric heating load prediction error value at the preset historical moment are input into a time domain expression to obtain the electric heating load prediction correction value at the moment before the current moment.

[0122] Based on the above embodiment, further, the calculation module is specifically used to calculate the first moment before the current moment. m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m -3 The electric heating load prediction error value e m-3 Input the time domain expression and get m The electric heating load prediction correction value Δ Y m-1 , wherein the time domain expression is:

[0123]

[0124] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, It is the differential parameter in the PID control parameter.

[0125] Based on the above embodiment, further, the calculation module is specifically used to subtract the actual value of the electric heating load at each historical moment from the corresponding electric heating load prediction value to obtain the electric heating load prediction error value at each historical moment.

[0126] The PID control parameters and the electric heating load prediction error value at the preset historical moment are input into the transfer function to obtain the electric heating load prediction correction value at the moment before the current moment.

[0127] Based on the above embodiment, further, the calculation module is specifically used to convert the m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m The electric heating load prediction error value at time -1 e m-3 Input the transfer function and get m The electric heating load prediction correction value Δ at time -1 Y m-1 , where the transfer function:

[0128]

[0129] in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, is the differential parameter in the PID control parameter, It is an operator.

[0130] Based on the above embodiment, further, the correction module is specifically used to calculate the electric heating load prediction value at the previous moment according to the current moment. , the electric heating load prediction correction value Δ at the moment before the current moment Y m-1 and the external influencing factor independent variable value at the current moment X m Input the correction formula to obtain the electric heating load forecast value at the current moment .

[0131] The correction formula is ,in d is a first-order difference operator.

[0132] Based on the above embodiment, further, the independent variable value of the external influencing factor is weather data.

[0133] This embodiment involves an electric heating load prediction device based on error feedback tracking prediction, which can improve the interpretability of the model while avoiding overfitting and significantly reducing data requirements under the premise of prediction accuracy similar to that of deep learning prediction methods.

[0134] In addition, an embodiment of the present invention includes a computer device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the electric heating load prediction method based on error feedback tracking prediction described in any one of the above technical solutions.

[0135] An embodiment of the present invention further includes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the electric heating load prediction method based on error feedback tracking prediction described in any one of the above technical solutions.

[0136] It is understood from common technical knowledge that the present invention may be implemented by other embodiments that do not depart from its spirit or essential features. Therefore, the embodiments disclosed above are, in all respects, merely illustrative and not exclusive. All modifications within the scope of the present invention or equivalent to the scope of the present invention are intended to be encompassed by the present invention.

[0137] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for predicting electric and thermal loads based on error feedback tracking prediction, characterized in that: The method comprises: Obtaining the actual value and predicted value of the electric heating load of the area to be predicted at a preset historical moment, wherein the preset historical moment includes a moment before the current moment and multiple consecutive historical moments; Obtaining a predicted correction value of the electric heating load at a moment before the current moment based on the actual value of the electric heating load at the preset historical moment and the predicted value of the electric heating load; Obtaining the electric heating load forecast value at the current moment according to the electric heating load forecast value at the moment before the current moment, the electric heating load forecast correction value at the moment before the current moment, and the independent variable value of the external influencing factor at the current moment; The step of obtaining the electric heating load forecast correction value at a moment before the current moment based on the actual electric heating load value and the electric heating load forecast value at the preset historical moment specifically includes: Subtracting the actual value of the electric heating load at each historical moment from the corresponding electric heating load forecast value to obtain an electric heating load forecast error value at each historical moment; Inputting the PID control parameter and the electric heating load prediction error value at the preset historical moment into a time domain expression or transfer function to obtain the electric heating load prediction correction value at the moment before the current moment; The step of obtaining the electric heating load forecast value at the current moment based on the electric heating load forecast value at the moment before the current moment, the electric heating load forecast correction value at the moment before the current moment, and the independent variable value of the external influencing factor at the current moment specifically includes: According to the electric heating load prediction value at the previous moment , the electric heating load prediction correction value Δ at the moment before the current moment Y m-1 and the external influencing factor independent variable value at the current moment X m Input the correction formula to obtain the electric heating load forecast value at the current moment ; The correction formula is ,in d is a first-order difference operator.

2. The method according to claim 1, characterized in that Inputting the PID control parameter and the electric heating load prediction error value at the preset historical moment into the time domain expression to obtain the electric heating load prediction correction value at the moment before the current moment specifically includes: The moment before the current moment, that is, m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m -3 The electric heating load prediction error value e m-3 Input the time domain expression and get m The electric heating load prediction correction value Δ at time -1 Y m-1 , wherein the time domain expression is: in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, It is the differential parameter in the PID control parameter.

3. The method according to claim 1, characterized in that Inputting the PID control parameter and the electric heating load prediction error value at the preset historical moment into the transfer function to obtain the electric heating load prediction correction value at the moment before the current moment specifically includes: The first m The electric heating load prediction error value at time -1 e m-1 , No. m The electric heating load prediction error value at time -2 e m-2 Hedi m -3 The electric heating load prediction error value e m-3 Input the transfer function and get m The electric heating load prediction correction value Δ at time -1 Y m-1 , where the transfer function: in, is the proportional parameter in the PID control parameters, is the integral parameter in the PID control parameters, is the differential parameter in the PID control parameter, It is an operator.

4. The method according to claim 1, wherein The external influencing factor independent variable value is weather data.

5. An electric heating load prediction device based on error feedback tracking prediction that implements the electric heating load prediction method based on error feedback tracking prediction according to any one of claims 1 to 4, characterized in that: include: An acquisition module is used to obtain the actual value and predicted value of the electric heating load of the area to be predicted at a preset historical moment, wherein the preset historical moment includes the moment before the current moment and multiple consecutive historical moments; a calculation module for obtaining a predicted correction value of the electric heating load at a moment before the current moment based on the actual value of the electric heating load at the preset historical moment and the predicted value of the electric heating load; The correction module is used to obtain the electric heating load prediction value at the current moment based on the electric heating load prediction value at the moment before the current moment, the electric heating load prediction correction value at the moment before the current moment and the independent variable value of the external influencing factor at the current moment.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the electric heating load prediction method based on error feedback tracking prediction according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the electric heating load prediction method based on error feedback tracking prediction according to any one of claims 1 to 4 is implemented.

Images