Power system state forecasting using fuzzy-Viterbi Algorithm

This paper proposes a a new method for 1-hour state forecasting in electrical power systems with high intermittent wind energy penetration. The proposed method has the potential to be utilized as an auxiliary function in Energy Management System (EMS). The method utilizes Markov Models (MM), the Viterbi Algorithm (VA) and fuzzy logic. The proposed auxiliary function creates a predictive database for the power system states using the historical states as well as wind and load forecasts. The predictive database can be utilized to provide pseudo measurements to a static linear state estimator in the case of loss of observability, loss of power system communication network or cyber-attacks. Simulations for the IEEE 14-bus system using available load and wind data from the Bonneville Power Administration (BPA) websites show good correlation between the predictions and the actual data.