Abstract:
|
Understanding electrical demand at the consumer level plays an important role in planning the distribution of electrical networks and evaluating the need for construction of new power plants, but monitoring individual consumption loads is still expensive. The proposed methodology separates substation aggregated loads into estimated mean consumption curves, called typical curves, one for each supplied customer type. The proposed approach assumes that each customer load curve follows a Gaussian process with a mean given by the typical curve, which can be modeled in terms of explanatory scalar and functional covariates. In addition, a model-based clustering approach for substations is proposed based on the similarity of their consumers’ typical curves and covariance structures. To assess model performance, the methodology is tested in a series of experiments under eight simulated scenarios and applied to a real substation load monitoring dataset from the United Kingdom.
|