CN114757441A - Load prediction method and related device - Google Patents
Load prediction method and related device Download PDFInfo
- Publication number
- CN114757441A CN114757441A CN202210505381.3A CN202210505381A CN114757441A CN 114757441 A CN114757441 A CN 114757441A CN 202210505381 A CN202210505381 A CN 202210505381A CN 114757441 A CN114757441 A CN 114757441A
- Authority
- CN
- China
- Prior art keywords
- load
- prediction
- error
- target
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000011159 matrix material Substances 0.000 claims abstract description 35
- 230000007704 transition Effects 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims description 31
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 4
- 238000013277 forecasting method Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 9
- 230000008859 change Effects 0.000 abstract description 9
- 230000007613 environmental effect Effects 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 230000001788 irregular Effects 0.000 abstract description 5
- 239000013598 vector Substances 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Power Engineering (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a load prediction method and a related device, wherein the method comprises the following steps: acquiring relevant load current, target air temperature and target weather value of a preset moment before a target moment; inputting the relevant load current, the target air temperature and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value; based on BP network model prediction operation, respectively calculating a probability transition matrix and an initial error prediction value according to related load current; calculating a target error predicted value based on the probability transition matrix and the initial error predicted value; and calculating a target load predicted value according to the initial load predicted value and the target error predicted value. The method and the device solve the technical problems that in the prior art, analysis on environmental factors influencing load performance is lacked, and the load prediction effect aiming at irregular change is poor, so that the prediction result lacks accuracy and reliability.
Description
Technical Field
The present application relates to the field of load prediction technologies, and in particular, to a load prediction method and a related apparatus.
Background
Load forecasts can be divided into long-term, medium-term, and short-term load forecasts by time of forecast. At present, the method for predicting the short-term load of the power system mainly comprises a statistical technique, an expert system method and a neural network method. Short-term load models used in statistical techniques can be generally classified into time system models and regression models.
The time system model cannot make full use of other environmental factors that have a large impact on load performance, and the prediction is inaccurate and unstable. The regression model needs to know the functional relationship between the load and the meteorological variable in advance, and has large calculation amount, and can not process the unbalanced transient relationship between the environmental variable and the load. The expert system method utilizes the experience knowledge and the reasoning rule of the expert, improves the load prediction precision of holidays or major activity days, but has great difficulty in accurately converting the expert knowledge, the experience and the like into a series of rules. And the simple neural network model cannot control irregular load curves to change in the process of analyzing the load data, so that the actual prediction precision is low.
Disclosure of Invention
The application provides a load prediction method and a related device, which are used for solving the technical problems that in the prior art, analysis on environmental factors influencing load performance is lacked, and the prediction result is lacked in accuracy and reliability due to the fact that load prediction effect with irregular change is poor.
In view of this, a first aspect of the present application provides a load prediction method, including:
acquiring relevant load current, target air temperature and target weather value of a preset moment before a target moment;
Inputting the relevant load current, the target air temperature and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value;
based on BP network model prediction operation, respectively calculating a probability transition matrix and an initial error prediction value according to the related load current;
calculating a target error prediction value based on the probability transition matrix and the initial error prediction value;
and calculating a target load predicted value according to the initial load predicted value and the target error predicted value.
Optionally, the inputting the relevant load current, the target air temperature, and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value further includes:
obtaining historical relevant load current, historical air temperature and historical weather values at a preset time before the historical time, and constructing a training data set;
and performing prediction training on the initial load prediction network model through the training data set and the historical load current corresponding to the historical moment to obtain a preset load prediction network model.
Optionally, the predicting operation based on the BP network model separately calculates a probability transition matrix and an initial error prediction value according to the relevant load current, and includes:
Calculating an error sequence according to a load network calculated value obtained by predicting operation based on a BP network model and the related load current;
constructing a probability transition matrix according to the error sequence;
and inputting the error sequence into a preset error prediction network model for error prediction to obtain an initial error prediction value.
Optionally, the calculating a target error prediction value based on the probability transition matrix and the initial error prediction value includes:
and selecting different elements in the probability transition matrix according to the symbol difference of the initial error predicted value, and calculating a target error predicted value by combining the initial error predicted value.
A second aspect of the present application provides a load prediction apparatus, including:
the data acquisition module is used for acquiring relevant load current, target air temperature and target weather value at a preset moment before the target moment;
the load prediction module is used for inputting the relevant load current, the target air temperature and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value;
the error calculation module is used for predicting operation based on a BP network model and respectively calculating a probability transfer matrix and an initial error prediction value according to the related load current;
An error optimization module to calculate a target error prediction value based on the probability transition matrix and the initial error prediction value;
and the prediction optimization module is used for calculating a target load predicted value according to the initial load predicted value and the target error predicted value.
Optionally, the method further includes:
the training data acquisition module is used for acquiring historical relevant load current, historical air temperature and historical weather values at a preset time before a historical time and constructing a training data set;
and the prediction model training module is used for performing prediction training on the initial load prediction network model through the training data set and the historical load current corresponding to the historical moment to obtain a preset load prediction network model.
Optionally, the error calculating module is specifically configured to:
calculating an error sequence according to a load network calculated value obtained by predicting operation based on a BP network model and the related load current;
constructing a probability transition matrix according to the error sequence;
and inputting the error sequence into a preset error prediction network model for error prediction to obtain an initial error prediction value.
Optionally, the error optimization module is specifically configured to:
and selecting different elements in the probability transition matrix according to the symbol difference of the initial error predicted value, and calculating a target error predicted value by combining the initial error predicted value.
A third aspect of the application provides a load prediction apparatus comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the load prediction method of the first aspect according to instructions in the program code.
A fourth aspect of the present application provides a computer-readable storage medium for storing program code for executing the load prediction method of the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
in the present application, a load prediction method is provided, including: acquiring relevant load current, target air temperature and target weather value of a preset moment before a target moment; inputting the relevant load current, the target air temperature and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value; based on BP network model prediction operation, respectively calculating a probability transition matrix and an initial error prediction value according to related load current; calculating a target error predicted value based on the probability transition matrix and the initial error predicted value; and calculating a target load predicted value according to the initial load predicted value and the target error predicted value.
According to the load forecasting method, the load data at the target moment is obtained, meanwhile, the temperature and the weather value within the corresponding time are also obtained, comprehensive load analysis factors are formed, and the influence of the environment on load change is considered, so that the forecasting result is more reliable; but also can avoid the influence of irregular change of the load to a certain extent; in addition, the load prediction error is optimized, adjusted and calculated, the obtained target error prediction value can reflect the fluctuation condition of the load more accurately, and the target load prediction value obtained based on the target error prediction value is more accurate and reliable. Therefore, the method and the device can solve the technical problems that in the prior art, analysis on environmental factors influencing load performance is lacked, and the prediction effect is poor aiming at irregularly changed loads, so that the prediction result is lacked in accuracy and reliability.
Drawings
Fig. 1 is a schematic flowchart of a load prediction method according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a load prediction apparatus according to an embodiment of the present application;
fig. 3 is a topological schematic diagram of a BP neural network structure provided in the embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For ease of understanding, referring to fig. 1, an embodiment of a load prediction method provided in the present application includes:
The previous preset time can be set according to actual conditions, for example, the load current of the previous 4 times of the target time is selected for analysis, the current time can be recorded as t, the previous 4 times are respectively t-1, t-2, t-3 and t-4, and the corresponding related load current is It-1、It-2、It-3、It-4Also a load current at time t can be obtained, i.e. ItFor subsequent analysis.
The target temperature is a temperature value, and for the convenience of analysis and the guarantee of the stability of data change, the average temperature within a certain time is selected as the target temperature K1t(ii) a Specifically, the following calculation can be made:
K1t=(K1max+K1min)/2
wherein, K1max、K1minRespectively, the highest air temperature and the lowest air temperature corresponding to the time t.
The target weather can be expressed by adopting a characteristic value and is recorded as K2tThe specific values are 0, 0.5 and 1, which respectively represent sunny days, cloudy days and rainy days. More detailed classification can be further divided according to actual conditions, and the classification is reasonable and is not described in detail. And obtaining the average air temperature and the weather characteristic value corresponding to the load forecasting time through weather forecast information.
And 102, inputting the relevant load current, the target air temperature and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value.
The preset load prediction network model is a model trained by load data, temperature and weather data and can be directly used in a load prediction task. The specific network model framework may be a BP neural network, or other types of network frameworks, which are not limited herein.
The related load current, the target air temperature and the target weather value can be input into the model in a data sequence mode, and an initial load predicted value obtained through prediction is recorded as IT. The initial load predicted value cannot reflect the influence of load fluctuation, and certain accuracy is lacked, so that subsequent error adjustment and optimization are required.
Further, step 102, before, further comprising:
acquiring historical relevant load current, historical air temperature and historical weather values at preset moments before the historical moments, and constructing a training data set;
and carrying out prediction training on the initial load prediction network model through the historical load current corresponding to the training data set and the historical moment to obtain a preset load prediction network model.
The form of the training data set is consistent with the data form of the target moment, and the training data set is mainly used for training a model; the data in the training data set can be historical moment data, specific load current at each moment is already defined, and the prediction performance of the model can be optimized according to the difference between the training prediction result and the real result.
The initial load prediction network model constructed in this embodiment is based on a BP neural network model, and model training is performed with the relevant load current, air temperature, and weather as inputs and the load current at the current time as an output, that is, a target model at the training position. Referring to fig. 3, a basic topology structure of the BP neural network model in this embodiment is shown in fig. 3, and includes an input layer, two hidden layers, and an output layer, where the output of the network can be expressed as:
wherein, a1、a2、a3Respectively output vectors of the two hidden layers and output vector of the output layer, W1 T、W2 T、W3 TAre weight matrix in network layer, f (-) is implicit from activation function, X, Y is input vector and output vector of network model respectivelyAn amount; n is1、n2、n3Inputting vectors for different network layers; b1、b2、b3Threshold vectors for different network layers; purelin (·) is a linear activation function.
And 103, respectively calculating a probability transition matrix and an initial error prediction value according to the related load current based on the BP network model prediction operation.
Further, step 103 includes:
calculating an error sequence according to a load network calculated value and a related load current obtained by the prediction operation based on the BP network model;
constructing a probability transition matrix according to the error sequence;
and inputting the error sequence into a preset error prediction network model for error prediction to obtain an initial error prediction value.
The load network calculation value can be subjected to network model prediction calculation according to the related load currents at the four moments, namely It-1、It-2、It-3、It-4Corresponding air temperature and weather characteristic values are additionally required, and the load network calculated value may be expressed as I'tWherein T is 1, 2.
From the load network calculated values, the corresponding error sequence, i.e. Δ I, can be calculatedt=I′t-ItMultiple error sequences may be calculated based on different load network calculations. The process of constructing the probability transition matrix according to the error sequence is as follows: when Δ ItAt > 0, record state p1When Δ It< 0, recording the status p2(ii) a Transition probabilities between different states can be computed to form a probability transition matrix P:
wherein p is11=d1/(d1+d2) Represents a slave state p1Transition to state p2Probability of p12Similarly; d1Is delta ItIs greater than 0 andΔIt+1a number > 0; d2Is Δ It> 0 and Δ It+1A number of < 0.
In the same way, p 21=d3/(d3+d4) Represents a slave state p2Transition to state p1Probability of p22Similarly; d3Is delta It< 0 and Δ It+1A number > 0; d4Is Δ It< 0 and Δ It+1A number of < 0.
The preset error prediction network model is similar to the preset load prediction network model and is a network model trained in advance, and the difference is that the functions are different, namely the prediction error is used as the prediction error, and the load is predicted as the prediction load; and inputting the error sequence into a preset error prediction network model for error prediction to obtain an initial error prediction value. In order to adapt to the influence of load fluctuation change and accurately reflect the load condition, the initial error predicted value is not directly adopted to correct the load predicted value in the embodiment, but the error predicted value delta I is further optimizedT。
And 104, calculating a target error predicted value based on the probability transition matrix and the initial error predicted value.
Further, step 104 includes:
and selecting different elements in the probability transfer matrix according to the symbol difference of the initial error predicted value, and calculating the target error predicted value by combining the initial error predicted value.
The sign difference of the initial error prediction value can be determined by comparing with 0 value, and the specific process is as follows: if Δ ITIs > 0, then delta I'T=ΔIT×p11-ΔIT×p12If Δ IT< 0, then Δ I' T=ΔIT×p21-ΔIT×p22. Wherein, delta I'TNamely the target error predicted value.
And 105, calculating a target load predicted value according to the initial load predicted value and the target error predicted value.
The specific calculation process of the target load predicted value is as follows: i'T=IT+ΔI′T。
According to the load forecasting method, the load data at the target moment are obtained, meanwhile, the temperature and the weather value within the corresponding time are also obtained, comprehensive load analysis factors are formed, and the influence of the environment on load change is considered, so that a forecasting result is more reliable; but also can avoid the influence of irregular change of the load to a certain extent; in addition, the load prediction error is optimized, adjusted and calculated, the obtained target error prediction value can reflect the fluctuation condition of the load more accurately, and the target load prediction value obtained based on the target error prediction value is more accurate and reliable. Therefore, the method and the device can solve the technical problems that in the prior art, analysis on environmental factors influencing load performance is lacked, and the prediction effect is poor aiming at irregularly changed loads, so that the prediction result is lacked in accuracy and reliability.
To facilitate understanding, referring to fig. 2, the present application provides an embodiment of a load prediction apparatus, comprising:
A data obtaining module 201, configured to obtain a relevant load current, a target air temperature, and a target weather value at a preset time before a target time;
the load forecasting module 202 is used for inputting the relevant load current, the target air temperature and the target weather value into a preset load forecasting network model for load forecasting to obtain an initial load forecasting value;
the error calculation module 203 is used for calculating a probability transition matrix and an initial error prediction value respectively according to the related load current based on the BP network model prediction operation;
an error optimization module 204, configured to calculate a target error prediction value based on the probability transition matrix and the initial error prediction value;
and the prediction optimization module 205 is configured to calculate a target load predicted value according to the initial load predicted value and the target error predicted value.
Further, still include:
a training data acquisition module 206, configured to acquire historical relevant load current, historical air temperature, and historical weather value at a preset time before a historical time, and construct a training data set;
and the prediction model training module 207 is used for performing prediction training on the initial load prediction network model through the historical load current corresponding to the training data set and the historical moment to obtain a preset load prediction network model.
Further, the error calculation module 203 is specifically configured to:
calculating an error sequence according to a load network calculated value and a related load current obtained by the prediction operation based on the BP network model;
constructing a probability transition matrix according to the error sequence;
and inputting the error sequence into a preset error prediction network model for error prediction to obtain an initial error prediction value.
Further, the error optimization module 204 is specifically configured to:
and selecting different elements in the probability transition matrix according to the symbol difference of the initial error predicted value, and calculating the target error predicted value by combining the initial error predicted value.
The application also provides a load prediction device, which comprises a processor and a memory;
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is configured to execute the load prediction method in the above method embodiment according to instructions in the program code.
The present application also provides a computer-readable storage medium for storing program code for executing the load prediction method in the above method embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, or portions or all or portions of the technical solutions that contribute to the prior art, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U-disk, a portable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.
Claims (10)
1. A method of load prediction, comprising:
acquiring relevant load current, target air temperature and target weather value of a preset moment before a target moment;
inputting the relevant load current, the target air temperature and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value;
based on BP network model prediction operation, respectively calculating a probability transition matrix and an initial error prediction value according to the related load current;
calculating a target error prediction value based on the probability transition matrix and the initial error prediction value;
and calculating a target load predicted value according to the initial load predicted value and the target error predicted value.
2. The load forecasting method according to claim 1, wherein the step of inputting the relevant load current, the target air temperature and the target weather value into a preset load forecasting network model for load forecasting to obtain an initial load forecasting value further comprises:
acquiring historical relevant load current, historical air temperature and historical weather values at preset moments before the historical moments, and constructing a training data set;
and carrying out prediction training on the initial load prediction network model through the historical load current corresponding to the training data set and the historical moment to obtain a preset load prediction network model.
3. The load prediction method of claim 1, wherein the BP-based network model prediction operation separately computes a probability transition matrix and an initial error prediction value from the associated load currents, comprising:
calculating an error sequence according to a load network calculated value obtained by predicting operation based on a BP network model and the related load current;
constructing a probability transfer matrix according to the error sequence;
and inputting the error sequence into a preset error prediction network model for error prediction to obtain an initial error prediction value.
4. The load prediction method of claim 1, wherein the calculating a target error prediction value based on the probability transition matrix and the initial error prediction value comprises:
and selecting different elements in the probability transition matrix according to the symbol difference of the initial error predicted value, and calculating a target error predicted value by combining the initial error predicted value.
5. A load prediction apparatus, comprising:
the data acquisition module is used for acquiring relevant load current, target air temperature and target weather value at a preset moment before the target moment;
the load prediction module is used for inputting the relevant load current, the target air temperature and the target weather value into a preset load prediction network model for load prediction to obtain an initial load prediction value;
the error calculation module is used for predicting operation based on a BP network model and respectively calculating a probability transition matrix and an initial error prediction value according to the related load current;
an error optimization module to calculate a target error prediction value based on the probability transition matrix and the initial error prediction value;
and the prediction optimization module is used for calculating a target load predicted value according to the initial load predicted value and the target error predicted value.
6. The load prediction device of claim 5, further comprising:
the training data acquisition module is used for acquiring historical relevant load current, historical air temperature and historical weather values at a preset time before a historical time and constructing a training data set;
and the prediction model training module is used for carrying out prediction training on the initial load prediction network model through the training data set and the historical load current corresponding to the historical moment to obtain a preset load prediction network model.
7. The load prediction device of claim 5, wherein the error calculation module is specifically configured to:
calculating an error sequence according to a load network calculated value obtained by predicting operation based on a BP network model and the related load current;
constructing a probability transition matrix according to the error sequence;
and inputting the error sequence into a preset error prediction network model for error prediction to obtain an initial error prediction value.
8. The load prediction device of claim 5, wherein the error optimization module is specifically configured to:
and selecting different elements in the probability transfer matrix according to the symbol difference of the initial error predicted value, and calculating a target error predicted value by combining the initial error predicted value.
9. A load prediction device, characterized in that the device comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the load prediction method of any one of claims 1-4 according to instructions in the program code.
10. A computer-readable storage medium for storing program code for performing the load prediction method of any one of claims 1-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210505381.3A CN114757441A (en) | 2022-05-10 | 2022-05-10 | Load prediction method and related device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210505381.3A CN114757441A (en) | 2022-05-10 | 2022-05-10 | Load prediction method and related device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114757441A true CN114757441A (en) | 2022-07-15 |
Family
ID=82335765
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210505381.3A Pending CN114757441A (en) | 2022-05-10 | 2022-05-10 | Load prediction method and related device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114757441A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116484201A (en) * | 2023-04-28 | 2023-07-25 | 中国长江三峡集团有限公司 | New energy power grid load prediction method and device and electronic equipment |
CN117318055A (en) * | 2023-12-01 | 2023-12-29 | 山东理工昊明新能源有限公司 | Power load prediction model processing method and device, electronic equipment and storage medium |
-
2022
- 2022-05-10 CN CN202210505381.3A patent/CN114757441A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116484201A (en) * | 2023-04-28 | 2023-07-25 | 中国长江三峡集团有限公司 | New energy power grid load prediction method and device and electronic equipment |
CN116484201B (en) * | 2023-04-28 | 2024-05-17 | 中国长江三峡集团有限公司 | New energy power grid load prediction method and device and electronic equipment |
CN117318055A (en) * | 2023-12-01 | 2023-12-29 | 山东理工昊明新能源有限公司 | Power load prediction model processing method and device, electronic equipment and storage medium |
CN117318055B (en) * | 2023-12-01 | 2024-03-01 | 山东理工昊明新能源有限公司 | Power load prediction model processing method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106600059B (en) | Intelligent power grid short-term load prediction method based on improved RBF neural network | |
CN114757441A (en) | Load prediction method and related device | |
CN110059867B (en) | Wind speed prediction method combining SWLSTM and GPR | |
CN110781595B (en) | Method, device, terminal and medium for predicting energy use efficiency (PUE) | |
CN110019420B (en) | Data sequence prediction method and computing device | |
CN111461445B (en) | Short-term wind speed prediction method and device, computer equipment and storage medium | |
CN115018209B (en) | Long-term prediction method and equipment for operation error of digital electric energy metering system | |
CN111191814A (en) | Electricity price prediction method, system and computer readable storage medium | |
Yi et al. | Intelligent prediction of transmission line project cost based on least squares support vector machine optimized by particle swarm optimization | |
CN112651519A (en) | Secondary equipment fault positioning method and system based on deep learning theory | |
CN112766603A (en) | Traffic flow prediction method, system, computer device and storage medium | |
CN110807508B (en) | Bus peak load prediction method considering complex weather influence | |
CN115392627A (en) | Online risk assessment method and system for power distribution network | |
CN117909888B (en) | Intelligent artificial intelligence climate prediction method | |
Wu et al. | A novel hybrid genetic algorithm and simulated annealing for feature selection and kernel optimization in support vector regression | |
CN116706907B (en) | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment | |
CN113095547A (en) | Short-term wind power prediction method based on GRA-LSTM-ICE model | |
CN116933037A (en) | Photovoltaic output prediction method based on multi-model fusion and related device | |
CN112115984A (en) | Tea garden abnormal data correction method and system based on deep learning and storage medium | |
CN115952928A (en) | Short-term power load prediction method, device, equipment and storage medium | |
CN112446550B (en) | Short-term building load probability density prediction method | |
CN114861967A (en) | Power load prediction method, system, device and storage medium | |
CN114066068A (en) | Short-term power load prediction method, device, equipment and storage medium | |
Zhu et al. | Hybrid of genetic algorithm and simulated annealing for support vector regression optimization in rainfall forecasting | |
Shen et al. | An interval analysis scheme based on empirical error and MCMC to quantify uncertainty of wind speed |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |