The one-year Solar Forecasting Model trial was recently completed. It was launched to anticipate solar intermittency and enhance power grid resilience. The project was developed by the Solar Energy Research Institute of Singapore (SERIS) at the National University of Singapore (NUS). It was supported by the Energy Market Authority (EMA) and the Meteorological Service Singapore (MSS) of the National Environment Agency (NEA).
The model completed its trial at EMA’s Power System Control Centre in September. It can forecast island-wide solar irradiance up to one hour ahead, with an average error rate lower than 10%, one of the lowest for solar forecasting in the tropics. According to a statement by EMA, Singapore’s power system operator, the model uses data from real-time irradiance sensors that are installed on rooftops of buildings and electrical substations across the country.
The model involves several dynamic solar forecasting techniques, including satellite imagery and machine learning algorithms. Combining outputs from MSS’ numerical weather prediction system, SINGV, the Solar Forecasting Model collects various types of data to generate solar irradiance forecasts at regular intervals from 5 minutes to 24 hours ahead of schedules.
Solar power generation cannot be moderated according to energy demand, unlike power generation plants. Solar power generation is dependent on Singapore’s tropical weather conditions, which vary due to environmental factors. This can lead to imbalances between electricity demand and supply output from solar photovoltaic (PV) systems.
The model would allow EMA to anticipate the solar power output and take pre-emptive actions to manage solar intermittency and balance the power grid. This is another step towards maintaining grid reliability as the government scales up solar deployment in Singapore, the statement wrote.
The model will also enable the electricity market to procure additional reserves or adjust the output of power generation plants and energy storage systems to increase electricity supply ahead of time to meet demand.
Following the completion of the trial, EMA is upgrading its Energy Management System (EMS) to incorporate solar generation forecasts produced by the Solar Forecasting Model by 2023. These forecasts would also be provided to the Energy Market Company (EMC), Singapore’s wholesale electricity market operator, to be factored into the market clearing process. This will generate more precise dispatch schedules for power generators to meet power system demand.
By 2030, Singapore aims to deploy at least 2 gigawatt-peak (GWp) of solar capacity, under the Singapore Green Plan 2030. A reliable solar forecasting model to predict solar irradiance will enhance the country’s grid resilience and flexibility while supporting the deployment of additional solar capacity.
The Singapore Green Plan 2030 was unveiled in February 2021. As OpenGov Asia reported, the country is keen to make a concerted effort to seek green growth opportunities to create new jobs, transform Singapore’s industries and harness sustainability as a competitive advantage. The plan aims to help more local enterprises restructure to adopt greener technologies and practices, and shift towards greener business activities. Other objectives include planting one million more trees, quadrupling solar energy deployment by 2025, reducing the waste sent to landfill by 30% by 2030, and having at least 20% of schools be carbon neutral by 2030.