Multivariate EMD-based Portfolio Value at Risk Estimate for Electricity Markets

With the electricity market reform in recent years, the electricity price is seeing higher level of volatility and risk. Based on the Multivaraite EMD algorithm, this paper proposes a novel risk measurement approach for studying the risk trends and estimating Value at Risk (VaR) in the electricity market. The Multivariate EMD algorithm is introduced to analyze the multi-scale and the volatility behaviors of the correlation among different electricity markets. The heterogeneous data is decomposed in the proposed Multivariate EMD based VaR estimation algorithm. The decomposed time series will be calculate with the DCC-GARCH model. Empirical studies in the representative Australian electricity markets suggest that the proposed algorithm outperforms the benchmark Exponential Weighted Moving Average (EWMA) and DCC-GARCH model, in terms of conventional performance evaluation criteria for the model reliability.