CN110570023A - short-term commercial power load prediction method based on SARIMA-GRNN-SVM - Google Patents
short-term commercial power load prediction method based on SARIMA-GRNN-SVM Download PDFInfo
- Publication number
- CN110570023A CN110570023A CN201910758297.0A CN201910758297A CN110570023A CN 110570023 A CN110570023 A CN 110570023A CN 201910758297 A CN201910758297 A CN 201910758297A CN 110570023 A CN110570023 A CN 110570023A
- Authority
- CN
- China
- Prior art keywords
- prediction
- model
- commercial power
- power load
- svm
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 28
- 241000728173 Sarima Species 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 238000002790 cross-validation Methods 0.000 claims abstract description 7
- 210000002569 neuron Anatomy 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 230000003190 augmentative effect Effects 0.000 claims description 2
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 230000001419 dependent effect Effects 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 238000012886 linear function Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000013277 forecasting method Methods 0.000 claims 5
- 230000000737 periodic effect Effects 0.000 abstract description 5
- 230000001932 seasonal effect Effects 0.000 description 9
- 238000011161 development Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010438 heat treatment 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
- 230000008092 positive effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
-
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Optimization (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Water Supply & Treatment (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
Abstract
The invention relates to a short-term commercial power load prediction method based on SARIMA-GRNN-SVM, which comprises the following steps: analyzing the load curve to obtain the influence factors of commercial power load fluctuation; constructing a single prediction model for commercial power load time series prediction and multi-factor regression prediction; constructing an SVM model, performing parameter optimization and training on the SVM model by using a training sample, and performing parameter optimization on the SVM model by using a grid search and cross validation method; and inputting the predicted values of the prediction days obtained by the SARIMA model and the GRNN model into the trained SVM model to obtain the commercial power load predicted values of the prediction days. The method solves the problem that a prediction result is easy to generate larger errors due to the fact that a single prediction model cannot comprehensively consider the periodic variation and the influence factors of the commercial load, and improves the prediction accuracy and the robustness.
Description
Technical Field
the invention belongs to the technical field of electric vehicle parts, and particularly relates to a short-term commercial power load prediction method based on SARIMA-GRNN-SVM.
background
The short-term power load prediction is the basis for power supply enterprises to make power generation and scheduling plans and ensure stable and reliable operation of a power system. Under the background of rapid development of the electric power spot market, the short-term electric power load prediction can enable power supply enterprises to master the electricity utilization condition in time, formulate reasonable electric power price, flexibly adjust electricity selling strategies and improve the transaction efficiency and economic benefits of the electric power spot market.
in recent years, commercial power loads have a significantly rising trend due to adjustment of industrial structures in China and improvement of living standards of residents. Compared with industrial load and resident load, commercial power load has stronger controllability, and the peak-valley difference is more obvious, thus being suitable for participating in the trade of the electric power spot market. Therefore, the short-term prediction of the commercial power load has important significance for safe and economic operation of a power grid and smooth development of a power spot market. At present, the research on the prediction of the commercial power load is less, the prediction of the medium-term and long-term commercial power load is mostly aimed at, the influence of factors such as weather and temperature on the commercial power load is not considered, and the requirement of the power spot market on the prediction of the short-term commercial power load is difficult to meet.
Therefore, based on the problems, the short-term commercial power load prediction method based on the SARIMA-GRNN-SVM is provided for overcoming the problem that a single prediction model cannot comprehensively consider the periodic variation of the commercial load and influence factors, so that a prediction result is prone to generating a large error, and has important practical significance.
disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a short-term commercial power load prediction method based on the SARIMA-GRNN-SVM, which solves the problem that a single prediction model cannot comprehensively consider periodic variation and influence factors of a commercial load, so that a prediction result is prone to generating a large error.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
A short-term commercial power load prediction method based on a SARIMA-GRNN-SVM comprises the following steps:
S1, collecting recent local commercial power load data, drawing an average load curve in the period of time or/and a load curve in a certain period of time in the period of time, and analyzing the load curve to obtain the influence factors of commercial power load fluctuation;
S2, constructing a single prediction model for commercial power load time series prediction and multi-factor regression prediction;
S201, establishing a SARIMA model to realize prediction of a commercial power load time sequence;
Establishing a SARIMA model, wherein the formula is shown as formula (1):
Wherein:
θ(B)＝1-θ1B-…-θqBq
Φ(Bs)＝1-Φ1BS-…-ΦPBS
Θ(Bs)＝1-Θ1BS-…-ΘQBS
wherein x (t) is a commercial power load time series,Is a differentiated stationary time sequence; b represents a hysteresis operator, and 2 represents a difference operator;is a model of the seasonal autoregressive model,for p-order autoregressionthe polynomial expression is a function of the time domain,non-seasonal autoregressive parameters; phi (B)s) Expressing a seasonal autoregressive polynomial, phi1，Φ2，…ΦPis a P-order seasonal autoregressive parameter; theta (B)S) Theta (B) represents a seasonal moving average model, where theta (B) represents a moving average polynomial of order q, theta (B) represents a moving average polynomial of order theta1，θ2，…θqis a non-seasonal moving average parameter, Θ (B)S) Representing a seasonal moving average polynomial, Θ1，Θ2，…ΘQIs a Q-order seasonal moving average parameter, and epsilon (t) is Gaussian noise;
establishing a SARIMA model, taking a historical load and a time sequence of a continuous time before a prediction day as input, adopting an Augmented dictionary-Fuller test to stabilize an original time sequence and determine a difference order, judging possible model parameters through an autocorrelation coefficient and a partial autocorrelation coefficient graph, screening by using an akage pool information quantity criterion and a Bayesian information criterion, and outputting a prediction value of the prediction day;
S202, carrying out multi-factor regression prediction on commercial power load by adopting GRNN model
constructing a GRNN model, taking the influence factors of the commercial power load fluctuation and the load at the same time of the same date type day determined in the step S1 of predicting a continuous time before the day as input, and utilizing a training method of cyclic cross validation to optimize the output predicted value;
s3, constructing an SVM model, performing parameter optimization and training on the SVM model by using a training sample, and performing parameter optimization on the SVM model by using a grid search and cross validation method; aiming at the working day prediction, selecting a single prediction model prediction value and a load actual value of the previous three working days as training samples; aiming at the forecast of the rest day, selecting a single forecast model forecast value and a load actual value of two days before the forecast day and the same date type day as training samples; wherein, the predicted value of the single prediction model is a predicted value obtained by using the SARIMA model and the GRNN model in the steps S201 and S202;
and S4, inputting the predicted values of the predicted days obtained by the SARIMA model and the GRNN model in the steps S201 and S202 into the SVM model trained in the step S3, and obtaining the predicted values of the commercial power load of the predicted days.
further, in step S3, before training the SVM model, the prediction day in the training sample is determined by the laeyda criterion, and if the prediction result of the prediction day is determined to be an abnormal value, the prediction day is removed, and the training sample is continued forward by one day.
further, the local commercial power load data collected in the step S1 is at least one year in the near future.
further, the GRNN model in step S202 is composed of an input layer, a mode layer, a summation layer, and an output layer; each neuron of the input layer directly transmits input data to the mode layer, the mode layer transmits a sample to the summation layer through a radial transfer function, the summation layer sums through two algorithms and transmits the data to the output layer, and the output layer outputs a result by adopting a linear function.
Further, the radial transfer function of the mode layer is:
In the formula, X is a network input variable; xiLearning samples corresponding to the ith neuron; σ represents a smoothing factor, where the optimal σ is found using a round-robin cross-validation training method.
Further, the summation layer utilizes the following two summation modes: one is to calculate the weighted sum of each neuron output of the mode layer; the other is to calculate the sum of the outputs of each neuron of the mode layer; the two formulas are respectively:
in the formula，j＝1，2，…，m；hijIs the jth element in the dependent variable of the ith training sample.
The invention has the advantages and positive effects that:
The SARIMA model adopted in the invention can describe the sequence of the periodic characteristic time shown by seasonal variation, and can consider the correlation among data and the interference of random factors when processing the problem of the time sequence, so that the prediction precision is higher; the GRNN model is an improved algorithm of a radial basis network, and has high calculation precision and short required time; the SVM model adopted by the invention utilizes training sample data to construct an optimal hyperplane in a high-dimensional space, has stronger generalization capability and needs few samples; the method solves the problem that a prediction result is easy to generate larger errors due to the fact that a single prediction model cannot comprehensively consider the periodic variation and the influence factors of the commercial load, and improves the prediction accuracy and the robustness.
Drawings
The technical solutions of the present invention will be described in further detail below with reference to the accompanying drawings and examples, but it should be understood that these drawings are designed for illustrative purposes only and thus do not limit the scope of the present invention. Furthermore, unless otherwise indicated, the drawings are intended to be illustrative of the structural configurations described herein and are not necessarily drawn to scale.
fig. 1 is a 2017 average daily load curve of a certain shopping mall provided in embodiment 1 of the present invention;
fig. 2(a) is an average load curve of a shopping mall in 2017 at an entire business hour and a whole hour in 1 month according to embodiment 1 of the present invention;
Fig. 2(b) is an average load curve of a shopping mall in accordance with embodiment 1 of the present invention over the entire business hours of 4 months in 2017;
Fig. 2(c) is an average load curve of a shopping mall in accordance with embodiment 1 of the present invention over 7 months of business hours in 2017;
fig. 2(d) is an average load curve of a shopping mall in accordance with embodiment 1 of the present invention over 10 months of business hours in 2017;
FIG. 3 shows the predicted daily and business hours load actual values and the predicted values of the individual models provided in embodiment 1 of the present invention;
FIG. 4 shows the predicted daily and business hours load actual values and SVM model predicted values provided in embodiment 1 of the present invention;
Detailed Description
it should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
example 1
Fig. 1 is a 2017 average daily load curve of a certain shopping mall provided in embodiment 1 of the present invention; fig. 2(a) is an average load curve of a shopping mall in 2017 at an entire business hour and a whole hour in 1 month according to embodiment 1 of the present invention; fig. 2(b) is an average load curve of a shopping mall in accordance with embodiment 1 of the present invention over the entire business hours of 4 months in 2017; fig. 2(c) is an average load curve of a shopping mall in accordance with embodiment 1 of the present invention over 7 months of business hours in 2017; fig. 2(d) is an average load curve of a shopping mall in accordance with embodiment 1 of the present invention over 10 months of business hours in 2017; FIG. 3 shows the predicted daily and business hours load actual values and the predicted values of the individual models provided in embodiment 1 of the present invention; FIG. 4 shows the predicted daily and business hours load actual values and SVM model predicted values provided in embodiment 1 of the present invention;
Referring to FIGS. 1, 2(a), 2(b), 2(c), and 2 (d): the influence factors of the commercial power load fluctuation are obtained through the analysis of the load curve as follows: weather, highest temperature, lowest temperature, date type;
and (3) carrying out commercial power load prediction on the business hours from 7 months and 5 days to 7 months and 10 days of a large leisure shopping center in Wuqing district in Tianjin City in 2017. The actual value of the commercial power load of the business hours of 28 days before each forecast day, and the weather, the highest temperature, the lowest temperature, the date type and the load at the same time of day of the previous same date type 14 days before the forecast day are respectively used as input, a single forecasting model of SARIMA and GRNN is established, and the forecasting result is shown in figure 3.
As can be seen from fig. 3, the predicted value of each single prediction model is substantially consistent with the actual value of the commercial power load, but the accuracy of the prediction result of the single prediction model fluctuates greatly, which shows that the robustness is poor.
The method of the invention is used for carrying out parameter optimization and training on the SVM: optimizing parameters of the SVM model by a grid search and cross verification method; aiming at the working day prediction, selecting a single prediction model prediction value and a load actual value of the previous three working days as training samples; aiming at the forecast of the rest day, selecting a single forecast model forecast value and a load actual value of two days before the forecast day and the same date type day as training samples; wherein, the predicted value of the single prediction model is a predicted value obtained by utilizing a SARIMA model and a GRNN model;
After parameter optimization and training are carried out on the SVM, the single prediction model prediction result from 7 months and 5 days to 7 months and 10 days in 2017 is input into the SVM to obtain a combined prediction model prediction value, as shown in FIG. 4.
From fig. 4, the combined prediction model provided by the invention better fits the change trend of the commercial power load, the prediction result is similar to the actual value, the difference between the predicted value and the actual value is larger only in 7-month and 6-day, and after the detection of the Larita criterion, the abnormal values are 5, so that the data of 7-month and 6-day is not adopted in the subsequent prediction. Specifically, the error e of each time of three prediction days in the training sample1，e2，…，e36Calculating the average value E and the standard deviation sigma of the standard deviation as a judgment reference; respectively calculating the errors v of different times of the judged day1，v2，…v12difference V from the judgment reference average value En(n-1, 2, … 12); if | VnIf the | is greater than 3 σ, the predicted value at the moment is considered as an abnormal value; if the prediction day outliers exceed 5, then subsequent predictions will not use the day data.
to measure the accuracy and robustness of the prediction model, the present embodiment uses the Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE) as error criteria, which are respectively shown as follows:
in the formula, n is the number of predicted times.
the average absolute percentage error Em and the root mean square error Er of the single model and the combined model from 7 months 5 days to 7 months 10 days in 2017 are obtained by using the formula shown in table 1:
TABLE 1 error comparison of combined predictive model to Single predictive model
As can be seen from table 1, the MAPE and the RMSE of the combined prediction model provided in this embodiment are both smaller than those of the single prediction model, which indicates that the combined prediction model integrates the advantages of the single prediction model, extracts more comprehensive information, and has better prediction accuracy and robustness than the single prediction model.
Example 2
and carrying out business power load prediction on business hours from 1 month 13 days to 1 month 19 days of another business complex in Wuqing district in Tianjin City, 2017. The combined model to single model error ratio is shown in table 2.
TABLE 2 error comparison of combined predictive model to Single predictive model
As can be seen from table 2, since the winter heating load is smaller than the summer cooling load, the volatility of the winter commercial power load is smaller than the summer load, and the prediction accuracy of both the single prediction model and the combined prediction model is better than that of the summer prediction. And the MAPE and RMSE of the combined prediction model provided by the embodiment are smaller than those of each single prediction model, the prediction accuracy and robustness are better than those of the single prediction model, and the short-term prediction accuracy and period requirements of the commercial power load can be met.
The present invention has been described in detail with reference to the above examples, but the description is only for the preferred examples of the present invention and should not be construed as limiting the scope of the present invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.
Claims (6)
1. A short-term commercial power load prediction method based on a SARIMA-GRNN-SVM is characterized by comprising the following steps: the method comprises the following steps:
S1, collecting recent local commercial power load data, drawing an average load curve in the period of time or/and a load curve in a certain period of time in the period of time, and analyzing the load curve to obtain the influence factors of commercial power load fluctuation;
S2, constructing a single prediction model for commercial power load time series prediction and multi-factor regression prediction;
S201, establishing a SARIMA model to realize prediction of a commercial power load time sequence;
Establishing a SARIMA model, taking a historical load and a time sequence of a continuous time before a prediction day as input, adopting an Augmented dictionary-Fuller test to stabilize an original time sequence and determine a difference order, judging possible model parameters through an autocorrelation coefficient and a partial autocorrelation coefficient graph, screening by using an akage pool information quantity criterion and a Bayesian information criterion, and outputting a prediction value of the prediction day;
S202, carrying out multi-factor regression prediction on commercial power load by adopting GRNN model
Constructing a GRNN model, taking the influence factors of the commercial power load fluctuation and the load at the same time of the same date type day determined in the step S1 of predicting a continuous time before the day as input, and utilizing a training method of cyclic cross validation to optimize the output predicted value;
s3, constructing an SVM model, performing parameter optimization and training on the SVM model by using a training sample, and performing parameter optimization on the SVM model by using a grid search and cross validation method; aiming at the working day prediction, selecting a single prediction model prediction value and a load actual value of the previous three working days as training samples; aiming at the forecast of the rest day, selecting a single forecast model forecast value and a load actual value of two days before the forecast day and the same date type day as training samples; wherein, the predicted value of the single prediction model is a predicted value obtained by using the SARIMA model and the GRNN model in the steps S201 and S202;
And S4, inputting the predicted values of the predicted days obtained by the SARIMA model and the GRNN model in the steps S201 and S202 into the SVM model trained in the step S3, and obtaining the predicted values of the commercial power load of the predicted days.
2. The method of claim 1, wherein the short-term commercial power load forecasting method based on SARIMA-GRNN-SVM comprises: in step S3, before training the SVM model, the prediction day in the training samples is determined by using the ralda criterion, and if the prediction result of the prediction day is determined to be an abnormal value, the prediction day is removed, and the training samples are continued forward by one day.
3. The method of claim 1, wherein the short-term commercial power load forecasting method based on SARIMA-GRNN-SVM comprises: the local commercial power load data collected in said step S1 is at least one year recent.
4. The method of claim 1, wherein the short-term commercial power load forecasting method based on SARIMA-GRNN-SVM comprises: the GRNN model in step S202 is composed of an input layer, a mode layer, a summation layer, and an output layer; each neuron of the input layer directly transmits input data to the mode layer, the mode layer transmits a sample to the summation layer through a radial transfer function, the summation layer sums through two algorithms and transmits the data to the output layer, and the output layer outputs a result by adopting a linear function.
5. The method of claim 4, wherein the short-term commercial power load forecasting method based on SARIMA-GRNN-SVM comprises: the radial transfer function of the mode layer is:
In the formula, X is a network input variable; xiLearning samples corresponding to the ith neuron; σ represents a smoothing factor, where the optimal σ is found using a round-robin cross-validation training method.
6. The method of claim 5, wherein the short-term commercial power load forecasting method based on SARIMA-GRNN-SVM comprises: the summation layer utilizes the following two summation modes: one is to calculate the weighted sum of each neuron output of the mode layer; the other is to calculate the sum of the outputs of each neuron of the mode layer; the two formulas are respectively:
Wherein j is 1, 2, …, m; h isijis the jth element in the dependent variable of the ith training sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910758297.0A CN110570023B (en) | 2019-08-16 | 2019-08-16 | Short-term commercial power load prediction method based on SARIMA-GRNN-SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910758297.0A CN110570023B (en) | 2019-08-16 | 2019-08-16 | Short-term commercial power load prediction method based on SARIMA-GRNN-SVM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110570023A true CN110570023A (en) | 2019-12-13 |
| CN110570023B CN110570023B (en) | 2023-05-16 |
Family
ID=68775658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910758297.0A Active CN110570023B (en) | 2019-08-16 | 2019-08-16 | Short-term commercial power load prediction method based on SARIMA-GRNN-SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110570023B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382906A (en) * | 2020-03-06 | 2020-07-07 | 南京工程学院 | Power load prediction method, system, equipment and computer readable storage medium |
| CN111815051A (en) * | 2020-07-06 | 2020-10-23 | 安徽建筑大学 | GRNN photovoltaic power generation prediction method considering weather influence factors |
| CN112116144A (en) * | 2020-09-15 | 2020-12-22 | 山东科技大学 | Regional power distribution network short-term load prediction method |
| CN112465250A (en) * | 2020-12-08 | 2021-03-09 | 深圳供电局有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN117272121A (en) * | 2023-11-21 | 2023-12-22 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030182250A1 (en) * | 2002-03-19 | 2003-09-25 | Mohammad Shihidehpour | Technique for forecasting market pricing of electricity |
| WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
| CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学（保定） | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
| CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
| CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
-
2019
- 2019-08-16 CN CN201910758297.0A patent/CN110570023B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030182250A1 (en) * | 2002-03-19 | 2003-09-25 | Mohammad Shihidehpour | Technique for forecasting market pricing of electricity |
| WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
| CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学（保定） | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
| CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
| CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382906A (en) * | 2020-03-06 | 2020-07-07 | 南京工程学院 | Power load prediction method, system, equipment and computer readable storage medium |
| CN111382906B (en) * | 2020-03-06 | 2024-02-27 | 南京工程学院 | Power load prediction method, system, equipment and computer readable storage medium |
| CN111815051A (en) * | 2020-07-06 | 2020-10-23 | 安徽建筑大学 | GRNN photovoltaic power generation prediction method considering weather influence factors |
| CN112116144A (en) * | 2020-09-15 | 2020-12-22 | 山东科技大学 | Regional power distribution network short-term load prediction method |
| CN112465250A (en) * | 2020-12-08 | 2021-03-09 | 深圳供电局有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN117272121A (en) * | 2023-11-21 | 2023-12-22 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
| CN117272121B (en) * | 2023-11-21 | 2024-03-12 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110570023B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570023A (en) | short-term commercial power load prediction method based on SARIMA-GRNN-SVM | |
| Deihimi et al. | Application of echo state networks in short-term electric load forecasting | |
| Chen et al. | Online 24-h solar power forecasting based on weather type classification using artificial neural network | |
| CN111260136A (en) | Building short-term load prediction method based on ARIMA-LSTM combined model | |
| CN104598985B (en) | Methods of electric load forecasting | |
| He | Deep neural network based load forecast | |
| Dong et al. | Applying the ensemble artificial neural network-based hybrid data-driven model to daily total load forecasting | |
| Hu et al. | New hybrid approach for short-term wind speed predictions based on preprocessing algorithm and optimization theory | |
| Ghasvarian Jahromi et al. | A novel method for day-ahead solar power prediction based on hidden Markov model and cosine similarity | |
| CN112418526A (en) | Comprehensive energy load control method and device based on improved deep belief network | |
| Zheng et al. | A simple method of residential electricity load forecasting by improved Bayesian neural networks | |
| CN111222700A (en) | Day-ahead electricity price probability prediction method based on dynamic network quantile model | |
| CN113869616A (en) | Self-adaptive residential user load prediction method | |
| Wang et al. | Multi-criteria comprehensive study on predictive algorithm of heating energy consumption of district heating station based on timeseries processing | |
| Liu et al. | A multi-task learning model for building electrical load prediction | |
| Souhe et al. | A hybrid model for forecasting the consumption of electrical energy in a smart grid | |
| Bhandari et al. | Short term electric load forecasting of kathmandu valley of nepal using artificial neural network | |
| Chen et al. | Short term load forecasting based on SBiGRU and CEEMDAN-SBiGRU combined model | |
| Sinha et al. | Forecasting electricity load with hybrid scalable model based on stacked non linear residual approach | |
| Silva et al. | Optimization of narx neural models using particle swarm optimization and genetic algorithms applied to identification of photovoltaic systems | |
| Putri et al. | Short-term forecasting of electricity consumption revenue on Java-Bali electricity system using Jordan recurrent neural network | |
| Yan et al. | An improved feature-time Transformer encoder-Bi-LSTM for short-term forecasting of user-level integrated energy loads | |
| Qureshi et al. | Short-term forecasting of wind power generation using artificial intelligence | |
| Fatema et al. | Analysing and forecasting electricity demand and price using deep learning model during the COVID-19 pandemic | |
| Safari et al. | Multi-Term Electrical Load Forecasting of Smart Cities Using a New Hybrid Highly Accurate Neural Network-Based Predictive Model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |