Comparative Analysis of Load Forecasting Models for Varying Time Horizons and Load Aggregation Levels

Power system operators are confronted with a multitude of new forecasting tasks to ensure constant supply security despite the decreasing number fully controllable energy producers. With this paper, we aim facilitate selection suitable approaches for load problem. First, provide classification cases in two dimensions: temporal and hierarchical. Then, identify typical features models compare their applicability structured manner depending on six previously defined cases. These compared against real data terms computational effort accuracy during development testing. From comparative analysis, derive generic guide best prediction per case.