Power generation mix in Colombia including wind power: Markowitz portfolio efficient frontier analysis with machine learning

Abstract

The Colombian power market is hydro-dominated since 67 % of the power produced comes from hydro-power sources. In addition, it has thermal power from natural gas and coal, and in the last years, alternative energy sources such as wind and solar have been introduced, although so far their share is not significant. Due to this condition, the Colombian power market is very volatile and depends on weather conditions. Usually, in rainy seasons prices are low and power is available, while in dry seasons, prices are high and power can be scarce. One of the main advantages of the new energy sources is that they are complementary to hydro-power, in the case of wind regimes, they are higher during dry seasons and lower during rainy seasons. We propose a complementarity analysis in the energy mix using Markowitz Portfolio analysis to determine if the efficient frontier is improved by introducing wind power to the system and the traditional port-folio analysis is improved by introducing Machine Learning (ML) into calculations. Results show that wind power improves the return while minimizing risk. Therefore, wind power would significantly reduce prices in Colombia's power mix while reducing volatility. This work follows the Open Innovation (OI) paradigm, the intersection of Machine Learning, portfolio optimization, and renewable energy presents a promising landscape for research and practical applications. Continued interdisciplinary collaboration and innovation are essential for harnessing the full potential of these technologies for a sustainable energy future.

Keywords

• Volatility
• Wind power
• Hydro-power
• Portfolio theory
• Machine learning