| Proj No. | A2219-251 |
| Title | Prediction of next day solar irradiance in Singapore by machine learning techniques. |
| Summary | In order to reduce the electricity consumption by buildings and to enhance air quality, there is a long term goal for new buildings to become net zero. For these buildings, photovoltaic and other renewable energy generation methods are deployed and the building management system will strive to balance the electricity drawn from the grid and the electricity generated by renewable sources in the building. In this project, the student will use machine learning techniques to predict the next day solar irradiance which is the power per unit area from direct and scattered sunlight. The historical dataset for irradiance in Singapore can be obtained from the solar energy research institute of Singapore (SERIS) and the objective is to accurately predict the next day irradiance using the previous day irradiance or other relevant features. The prediction capabilities of different machine learning models will be compared using quantitative metrics. These predictions will enable the building management system to better manage its daily energy budget. |
| Supervisor | A/P Wong Kin Shun, Terence (Loc:S2 > S2 B2C > S2 B2C 103, Ext: +65 67906401) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Clean Energy Research (Loc: S2-B7c-05) |
| Single/Group: | Single |
| Area: | Electrical Power and Energy |
| ISP/RI/SMP/SCP?: |