Balancing Generation from Renewable Energy Sources: Profitability of an Energy Trader

Abstract

Motivated by a practical problem faced by an energy trading company in Poland, we investigate the profitability of balancing intermittent generation from renewable energy sources (RES). We consider a company that buys electricity generated by a pool of wind farms and pays their owners the day-ahead system price minus a commission, then sells the actually generated volume in the day-ahead and balancing markets. We evaluate the profitability (measured by the Sharpe ratio) and market risk faced by the energy trader as a function of the commission charged and the adopted trading strategy. We show that publicly available, country-wide RES generation forecasts can be significantly improved using a relatively simple regression model and that trading on this information yields significantly higher profits for the company. Moreover, we address the issue of contract design as a key performance driver. We argue that by offering tolerance range contracts, which transfer some of the risk to wind farm owners, both parties can bilaterally agree on a suitable framework that meets individual risk appetite and profitability expectations.

Energy Forecasting: A Review and Outlook

“…It is thus important to tie the evaluation measures to the users' characteristics and define alternative metrics that better capture the strengths and weaknesses of competing price forecasting models. Attempts at tackling this issue include proposing simple bidding strategies based on a comparison of the actual prices and their forecasts [114], [115] or using measures popular in financial portfolio analysis, like the Sharpe ratio [116], [117]. A recent study demonstrated that during volatile market periods, and for micro-grid energy management, a moving horizon deterministic model with point price forecasts led to significantly lower operation costs, compared to more complex stochastic and robust models [118].…”

Influence of Photovoltaic Development on Decarbonization of Power Generation—Example of Poland

“…The lack of these incentives will certainly hinder the transition to renewable energy. Studies indicate that the society is slowly opening up to renewable energy [41,[57][58][59][60][61][62][63]. However, in Poland, a big barrier is the attachment to coal [64,65].…”

Forecasting Electricity Prices: Autoregressive Hybrid Nearest Neighbors (ARHNN) Method

“…Given the high level of price volatility and the limitations in storing electricity, the selection of a wrong strategy, based on price misinformation, may lead to economic losses or even bankruptcy. On the contrary, utilizing accurate forecasts may increase profits or reduce the risk of economic losses [9,14].…”