Electricity price forecasting on electricity spot market: a case study based on the Brazilian Difference Settlement Price

Developing predictive models is a complex task since it deals with the uncertainty and stochastic behavior of variables. Specifically concerning commodities, accurately predicting their future prices allows us to minimize risks establish more reliable decision support mechanisms. Although discussion on this question extensive, there academic attention being paid construction nonparametric applied energy markets, as they have presented promising results, what justifies present study. This paper applies classical statistical Dynamic Time Scan Forecasting (DTSF) short-term electricity market prices, in Brazil, from 2006 2019. DTSF consists scanning time series then identifying past patterns (so-called “matches”), similar last available observations. We predict Brazilian spot according most matches, using aggregation functions, such median. Recent research increasing, indicating significance. Our approach exhibited greater accuracy than seminal models. was designed for high frequency series. Its performance remained robust when other both errors (spring), well those are highly accurate (winter). For research, we recommend finely-tune study parameters.