Difference between revisions of "Short-Term Energy Demand Forecasting"
From ISLAB/CAISR
(Created page with "{{StudentProjectTemplate |Summary=Forecasting the electricity consumption based on historical usage by using smart meter data |Keywords=load forecasting, demand response |Refe...") |
|||
| Line 9: | Line 9: | ||
|Level=Master | |Level=Master | ||
|Status=Open | |Status=Open | ||
| − | }} | + | }} |
The project is about evaluating different forecasting methods for short term electricity usage and implementing them. There are some available methods e.g. time series, frequency analysis, NN, etc. which student should investigate them and discuss about the most suitable forecasting model. | The project is about evaluating different forecasting methods for short term electricity usage and implementing them. There are some available methods e.g. time series, frequency analysis, NN, etc. which student should investigate them and discuss about the most suitable forecasting model. | ||
Latest revision as of 19:12, 24 October 2016
| Title | Short-Term Energy Demand Forecasting |
|---|---|
| Summary | Forecasting the electricity consumption based on historical usage by using smart meter data |
| Keywords | load forecasting, demand response |
| TimeFrame | |
| References | Hong, Wei-Chiang. Intelligent Energy Demand Forecasting. Vol. 10. Springer, 2013.
Ghofrani, M., et al. "Smart meter based short-term load forecasting for residential customers." North American Power Symposium (NAPS), 2011. IEEE, 2011. http://www.sciencedirect.com/science/article/pii/S1877050914011053 |
| Prerequisites | Cooperating Intelligent Systems and Learning Systems courses |
| Author | |
| Supervisor | Anita Sant'Anna, Sławomir Nowaczyk, Hassan Mashad Nemati |
| Level | Master |
| Status | Open |
The project is about evaluating different forecasting methods for short term electricity usage and implementing them. There are some available methods e.g. time series, frequency analysis, NN, etc. which student should investigate them and discuss about the most suitable forecasting model.
