Search

The predispatch price forecast plays a key element in the electricity market. However, such a forecast usually depends on the traditional offline batch-learning technologies, which cannot respond in time to the unexpected changes in the local power system environment. Further, the predispatch local price forecast is often affected by the dynamic price changes from the neighboring regions. This article proposes a novel online learning forecast approach to overcome the above issues to provide a better predispatch price forecast by using the online sequential extreme learning machine (OS-ELM) algorithm. The article proposes a novel data structure in the form of a 2-D orthogonal list and two corresponding OS-ELM modules. One module provides the rolling day-ahead price prediction and prediction intervals using the day-by-day online training update, while the other provides the rolling 30-min prediction using the 2-h-by-2-h online training update. The proposed approach can continuously perceive any unexpected events and any price fluctuations from the neighboring regions in the nonlinear patterns. The proposed approach is validated using simulation studies based on the data from the Australian electricity market, and the simulation results show that the proposed approach can help in improving the forecast accuracy, especially when unexpected changes occur both locally and in the neighboring area. [ABSTRACT FROM AUTHOR]

This paper proposes a coordinated multilayer control strategy for the energy management (EM) of grid-connected ac microgrids. The strategy predicts the customer's load demand and the photovoltaics (PV) power generation for a day-ahead EM. It utilizes the PV power generations and the bidirectional energy transactions from electric vehicles and battery storage to provide a combined response for load support. The system also predicts any uncertainties in customers demand and power generations and implements day-ahead precautionary measures to tackle that uncertainty. Two different prediction strategies are used, autoregressive moving average and artificial neural networks, and their performances for a day-ahead EM are investigated. The reference power from the tertiary layer EM is sent to the local controllers for power regulation at the inverter level. Additionally, the varying power output reference obtained from a day-ahead EM is classified into the slow, medium, and fast variations. The performance of the local controller employed in the interfacing grid-connected three-phase inverter is tested during the above-mentioned power reference variations. The total harmonic distortion incorporating a moving window technique is calculated for the ac output current during each class of power variations over a day. [ABSTRACT FROM AUTHOR]