Direct and indirect short-term aggregated turbine- and farm-level wind power forecasts integrating several NWP sources.

The wind power sector is experiencing rapid growth, which creates new challenges for its electricity grid integration. Accurate wind power forecasting (WPF) is crucial for trading, balancing, and dispatching wind energy. In this paper, we examine the use of aggregated turbine- and farm-level WPFs in the Nordic energy market. The turbine-level WPFs were retrieved from a previous study, while the farm-level WPFs were developed using the same methodology, incorporating inputs from three different numerical weather predictions (NWPs) and implementing both direct and indirect forecasting approaches. In the indirect WPF approach, we explore the impact of using wind direction as an input for the wind farm-level power performance model. The different WPFs are combined into one using weights related to up-to-date forecast errors. An automated and optimized machine-learning pipeline using data from a Norwegian wind farm is used to implement the proposed forecasting methods. The indirect approach, that uses the wind-downscaling model, improves the wind speed forecast accuracy compared to raw forecasts from the relevant NWPs. Additionally, we observed that the farm-level downscaling model exhibited lower error than those developed at the turbine level. The combined use of multiple NWP sources reduced forecasting errors by 8 %-30 % for direct and indirect WPFs, respectively. Direct and indirect forecasting methods present similar performance. Finally, the aggregated turbine-level improved WPF accuracy by 10 % and 15 % for RMSE and MAE, respectively, compared to farm-level WPF.

Sustainable energy towards air pollution and climate change mitigation.

This is an evidence from a high-income economy in Southeast Asia and a support for scientific planning of the energy sector in ensuring air pollution and climate change mitigation. A comparative analysis of the energy options for electricity generation in the nation was made considering availability, cost and greenhouse gases emission - CO2, N2O and CH4, using a two-stage method comprising multi-objective optimization and TOPSIS. The renewable (RE) and non-renewable energy (NRE) options available were assessed through the lifecycle approach to determine the lifecycle greenhouse gas emission (LCGHG) and levelized cost of energy (LCOE) per MWh of electricity. Considering historical electricity consumption, annual GDP and population growth from 1965, energy consumption for the year 2035 was forecasted using support vector machine regressor in Weka. Future plans in energy diversification pathways were examined through various scenario multi-objective optimizations with a constraint on resource availability and energy target using genetic algorithm in MATLAB. The outputs were ranked using TOPSIS method. Results showed that greenhouse gases emission could be reduced by 10.3 percent compared to business as usual scenario while the energy mix could attain 10 percent renewable energy in the grid at a relatively lower generation cost.