Search

This work aims to detect the impact of fundamentals and regulatory reforms on the Greek Wholesale Electricity Market, applying SARMAX/GARCH models. The System Marginal Price (SMP) is considered a stochastic, nonlinear process, reflecting not only the effects of endogenous/fundamental market factors but also the effects of exogenous variables including regulatory reforms, which also affect the market dynamics. To capture the dynamics of the conditional mean and volatility of SMP, a number of SARMAX/GARCH models have been estimated using as regressors an extensive set of fundamental factors in the Greek Electricity Market (GEM), as well as dummy variables that mimic the history of Regulator's interventions. The best-found model captures adequately the dependency of the spot price to the regulatory reforms. The findings reassure the typical sign and the magnitude of the effect of fundamentals, and detects successfully the impacts of the reforms. The most interesting finding is that the GEM does not exhibit asymmetries or leverage effect, in the volatility of its wholesale price, as the most European markets do. The outcome of this paper can be useful to a wide variety of GEM's participants and specifically to the decision makers in GEM.

This paper presents an integrated model for risk management of electricity traders. It integrates the Unit Commitment (UC) problem, which provides the power generation units' dispatch and the electricity price forecasting of a power system, with artificial neural network (ANN) models, which provide electricity price forecasting of a neighbouring power system by incorporating a clustering algorithm. The integrated model is further extended to estimate the traders' profitability and risk, incorporating risk provisions. The integrated model is applied in bi-directional trading between the Italian and Greek day-ahead electricity markets. The UC and neural network models provide forecasts of the wholesale electricity price in Greece and Italy respectively. The model attributes a confidence level of the price forecasts, depending on the data clustering and the forecasting performance of each model. The integrated model identifies periods with high price margins for trading for each power flow, aligned with a forecasting confidence and a risk level. The integrated model can provide price signals on the profitability of traders and useful insights into the risk of traders.

Accurate forecasts of natural gas demand can be essential for utilities, energy traders, regulatory authorities, decision makers and others. The aim of this paper is to test the robustness of a novel hybrid computational intelligence model in day-ahead natural gas demand predictions. The proposed model combines the Wavelet Transform (WT), Genetic Algorithm (GA), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Feed-Forward Neural Network (FFNN). The WT is used to decompose the original signal in a set of subseries and then a GA optimized ANFIS is employed to provide the forecast for each subseries. ANFIS output is fed into a FFNN to refine the initial forecast and upgrade the overall forecasting accuracy. The model is applied to all distribution points that compose the natural gas grid of a country, in contradiction to the majority of the literature that focuses on a limited number of distribution points. This approach enables the comparison of the model performance on different consumption patterns, providing also insights on the characteristics of large urban centers, small towns, industrial areas, power generation units, public transport filling stations and others.