Development of Short-term Electric Load Forecasting System Based on Statistical Learning Method and Bayesian Estimation
| Project/Area Number |
15K06113
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Measurement engineering
|
|---|
| Research Institution | Kagoshima University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2017: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2016: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
|---|
| Keywords | 計測工学 / 制御工学 / システム工学 |
|---|
| Outline of Final Research Achievements |
This research presents a method of short-term electric load forecasting based on the statistical learning method and Bayesian estimation. The proposed forecasting system can yield not only the predicted electric load demands but also their confidence measures. The Gaussian process models are trained by the particle swarm optimization, cuckoo search, and so forth. The results of electric load forecasting for Kyushu district are shown to demonstrate the effectiveness of this forecasting system.
|
Report
(4 results)
Research Products
(6 results)
