Deep learning-based multistep ahead wind speed and power generation forecasting using direct method

Long-term effective and accurate wind power potential prediction, especially for wind farms, facilitates planning for the sustainable development of renewable energy. Accurate wind speed forecasting enhances wind power generation planning and reduces costs. Wind speed time series has nonlinearity, intermittence, and fluctuation, which makes the prediction difficult. Deep learning techniques can be beneficial when there is no specific structure to data. These techniques can predict wind speed with reasonable accuracy and reliability. In this study, four different algorithms, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolu-tional Neural Network (CNN), and CNN-LSTM, for three different long-term horizons (6 months, 1 year, and 5 years) are successfully developed using the direct method. GRU method showed a higher degree of accuracy compared to other methods. In addition, it is confirmed that using a multivariate data set increases the model's accuracy compared to the univariate model. A computational cost analysis is also conducted to compare the proposed algorithms. Finally, the power production capacity of the wind farm at a given location, Zabol city, is calculated for the next five years, which is indispensable for planning, management, and economic analysis. The reasonable conformance between the real data and predicted ones is shown to confirm the capability of the proposed model to use in long-term wind speed forecasting.

Financial Solace: Malaysian Credit Counselling and Debt Management Agency Responses to COVID-19 Challenges

This study evaluates the measures undertaken by the Credit Counselling and Debt Management Agency (AKPK) to assist those financially distressed due to their inability to meet their financial commitments amidst the COVID-19 pandemic. Adopting secondary analysis of qualitative data, relevant secondary data, including journal articles, annual reports, and newspaper articles, were analyzed. The study finds that measures adopted by AKPK in response to the COVID-19 pandemic include reinforcing the workforce, enhancing IT infrastructures, deploying digital platforms, using various media channels, introducing online apps, online portals, online webinars, online learning modules, and online payment facility for all debt management participants. AKPK is also entrusted with handling small and medium enterprises (SMEs) under the Small Debt Resolution Scheme. A dedicated SME Helpdesk is established to facilitate the process. AKPK's continual support to provide financial aid is reflected in its collaborative effort with the banking industry under the Financial Management and Resilience Program and the Financial Resilience Support Program. However, the government should seriously consider strengthening personal data protection laws because of AKPK's significant reliance on digital platforms. Similarly, appropriate government bodies must take quick action to address the digital divide issue and promote inclusion to reduce disparity in terms of access to online services offered by AKPK. Also, since certain individuals or SMEs with credit facilities with entities not regulated by Bank Negara Malaysia are deprived of this incentive, relevant regulators should undertake actions to provide a similar facility. This study is significant in that it provides lessons to be learned by other credit counseling and debt management agencies in adopting effective measures to enable them to adapt to the new normal. © The Authors.