Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation
Short-term load forecast (STLF) plays an important role in power system operations. This paper proposes a spline bases-assisted Recurrent Neural Network (RNN) for STLF with a semi-parametric model being adopted to determine the suitable spline bases for constructing the RNN model. To reduce the expo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/13/5930 |
| _version_ | 1797528709466423296 |
|---|---|
| author | Tzu-Lun Yuan Dian-Sheng Jiang Shih-Yun Huang Yuan-Yu Hsu Hung-Chih Yeh Mong-Na Lo Huang Chan-Nan Lu |
| author_facet | Tzu-Lun Yuan Dian-Sheng Jiang Shih-Yun Huang Yuan-Yu Hsu Hung-Chih Yeh Mong-Na Lo Huang Chan-Nan Lu |
| author_sort | Tzu-Lun Yuan |
| collection | DOAJ |
| description | Short-term load forecast (STLF) plays an important role in power system operations. This paper proposes a spline bases-assisted Recurrent Neural Network (RNN) for STLF with a semi-parametric model being adopted to determine the suitable spline bases for constructing the RNN model. To reduce the exposure to real-time uncertainties, interpolation is achieved by an adapted mean adjustment and exponentially weighted moving average (EWMA) scheme for finer time interval forecast adjustment. To circumvent the effects of forecasted apparent temperature bias, the forecasted temperatures issued by the weather bureau are adjusted using the average of the forecast errors over the preceding 28 days. The proposed RNN model is trained using 15-min interval load data from the Taiwan Power Company (TPC) and has been used by system operators since 2019. Forecast results show that the spline bases-assisted RNN-STLF method accurately predicts the short-term variations in power demand over the studied time period. The proposed real-time short-term load calibration scheme can help accommodate unexpected changes in load patterns and shows great potential for real-time applications. |
| first_indexed | 2024-03-10T10:02:15Z |
| format | Article |
| id | doaj.art-08253cb1a55b430491412944a6fe1e76 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T10:02:15Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-08253cb1a55b430491412944a6fe1e762023-11-22T01:47:04ZengMDPI AGApplied Sciences2076-34172021-06-011113593010.3390/app11135930Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time AdaptationTzu-Lun Yuan0Dian-Sheng Jiang1Shih-Yun Huang2Yuan-Yu Hsu3Hung-Chih Yeh4Mong-Na Lo Huang5Chan-Nan Lu6Department of Applied Mathematics, National Sun Yat-sen University, Kaohsiung 804, TaiwanDepartment of Applied Mathematics, National Sun Yat-sen University, Kaohsiung 804, TaiwanDepartment of Applied Mathematics, National Sun Yat-sen University, Kaohsiung 804, TaiwanDepartment of Electrical Engineering, National Sun Yat-sen University, Kaohsiung 804, TaiwanSystem Operations Department, Taiwan Power Company, Taipei 100, TaiwanDepartment of Applied Mathematics, National Sun Yat-sen University, Kaohsiung 804, TaiwanDepartment of Electrical Engineering, National Sun Yat-sen University, Kaohsiung 804, TaiwanShort-term load forecast (STLF) plays an important role in power system operations. This paper proposes a spline bases-assisted Recurrent Neural Network (RNN) for STLF with a semi-parametric model being adopted to determine the suitable spline bases for constructing the RNN model. To reduce the exposure to real-time uncertainties, interpolation is achieved by an adapted mean adjustment and exponentially weighted moving average (EWMA) scheme for finer time interval forecast adjustment. To circumvent the effects of forecasted apparent temperature bias, the forecasted temperatures issued by the weather bureau are adjusted using the average of the forecast errors over the preceding 28 days. The proposed RNN model is trained using 15-min interval load data from the Taiwan Power Company (TPC) and has been used by system operators since 2019. Forecast results show that the spline bases-assisted RNN-STLF method accurately predicts the short-term variations in power demand over the studied time period. The proposed real-time short-term load calibration scheme can help accommodate unexpected changes in load patterns and shows great potential for real-time applications.https://www.mdpi.com/2076-3417/11/13/5930exponentially weighted moving averageLASSO model selectionsemi-parametric modelshort term load forecastspline bases |
| spellingShingle | Tzu-Lun Yuan Dian-Sheng Jiang Shih-Yun Huang Yuan-Yu Hsu Hung-Chih Yeh Mong-Na Lo Huang Chan-Nan Lu Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation Applied Sciences exponentially weighted moving average LASSO model selection semi-parametric model short term load forecast spline bases |
| title | Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation |
| title_full | Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation |
| title_fullStr | Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation |
| title_full_unstemmed | Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation |
| title_short | Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation |
| title_sort | recurrent neural network based short term load forecast with spline bases and real time adaptation |
| topic | exponentially weighted moving average LASSO model selection semi-parametric model short term load forecast spline bases |
| url | https://www.mdpi.com/2076-3417/11/13/5930 |
| work_keys_str_mv | AT tzulunyuan recurrentneuralnetworkbasedshorttermloadforecastwithsplinebasesandrealtimeadaptation AT dianshengjiang recurrentneuralnetworkbasedshorttermloadforecastwithsplinebasesandrealtimeadaptation AT shihyunhuang recurrentneuralnetworkbasedshorttermloadforecastwithsplinebasesandrealtimeadaptation AT yuanyuhsu recurrentneuralnetworkbasedshorttermloadforecastwithsplinebasesandrealtimeadaptation AT hungchihyeh recurrentneuralnetworkbasedshorttermloadforecastwithsplinebasesandrealtimeadaptation AT mongnalohuang recurrentneuralnetworkbasedshorttermloadforecastwithsplinebasesandrealtimeadaptation AT channanlu recurrentneuralnetworkbasedshorttermloadforecastwithsplinebasesandrealtimeadaptation |