Forecasting electricity prices and market length for trading stochastic generation in markets with a single-price balancing mechanism

摘要: This paper presents the problem facing stochastic generators who are required to participate in electricity markets with a single-price balancing mechanism. The solution this requires forecasts of multiple processes: weatherdependent generation, and prices, sign system length. By formulating from probabilistic perspective, it is demonstrated that combination well known understood forecasting techniques can support market participants both increasing revenue reducing risk. Probabilistic length produced using logistic regression on data widely available participants, prices forecast ARMAX models automated fitting. Wind power provided by wind farm operator for case study based participating UK market. It shown proposed approach be employed increase revenue, over 10% most extreme case, reduce risk