The recent international tension warrants a rethink of the electricity market design. In this study, we take the German electricity market as an example to investigate how international tension affects market outcomes, particularly electricity prices. While the shortage in natural gas and fossil fuel inevitably increases electricity prices, we focus on a different perspective, the predictability of the electricity prices. It is commonly believed that when the prices are highly volatile and unpredictable, the corresponding market is more vulnerable to manipulation and many market loopholes for arbitrage exist. In this study, we use a Long Short-term Memory (LSTM) network to predict the electricity prices in Germany and quantity the uncertainty (i.e., predictability) of the fluctuating electricity prices. Our numerical studies reveal that though the prices are rising, the recent international tension makes the electricity market less vulnerable than before from the perspective of electricity price volatility. That is, we find that the recent international tension increases the unpredictability of electricity prices.
[1]
Rui Liu,et al.
Effective long short-term memory with differential evolution algorithm for electricity price prediction
,
2018,
Energy.
[2]
Qing Cao,et al.
Forecasting wind speed with recurrent neural networks
,
2012,
Eur. J. Oper. Res..
[3]
N. Amjady,et al.
Day-Ahead Price Forecasting of Electricity Markets by Mutual Information Technique and Cascaded Neuro-Evolutionary Algorithm
,
2009,
IEEE Transactions on Power Systems.
[4]
Michael Negnevitsky,et al.
An Effort to Optimize Similar Days Parameters for ANN-Based Electricity Price Forecasting
,
2008,
IEEE Transactions on Industry Applications.
[5]
Shu Fan,et al.
Next-day electricity-price forecasting using a hybrid network
,
2007
.
[6]
J. Contreras,et al.
Forecasting Next-Day Electricity Prices by Time Series Models
,
2002,
IEEE Power Engineering Review.
[7]
S. Hochreiter,et al.
Long Short-Term Memory
,
1997,
Neural Computation.