COmparison Of Modified K-means and hierarchical algorithms in customers load curves clustering for designing suitable tariffs in electricity market

In the electricity market, it is highly desirable for suppliers to know the electrical behavior of their customers, in order to provide them with satisfactory services at the least cost. One of the most important objectives in such case is designing tariff for customers. Electricity providers have been given new degrees of freedom in defining tariff structures and rates under regulatory-imposed revenue caps. This requires a suitable grouping of the electricity consumers into customer classes. Therefore, investigation of optimum clustering algorithm is of great practical concept. In this paper a modified K-means algorithm is adopted for customer clustering. This method is then compared with other clustering algorithms including classical K-means and hierarchical methods.