Shape-based clustering for demand response potential evaluation: A perspective of comprehensive evaluation metrics

With the wide deployment of smart meter and advanced communication technology, customers in demand side have large potential to participate in demand response (DR). Therefore, suitable DR potential evaluation methods are needed to select customers for proper DR programs. In this work, an evaluation procedure based on multiple metrics is proposed. First, a bi-level clustering method is proposed to group load profiles into clusters based on the similarity in shape. Adaptive k-Shape clustering is proposed to automatically generate clusters based on the defined threshold. To evaluate the variability of the load profiles in each cluster, adaptive piecewise aggregate approximation (APAA) method is proposed to divide time series into segments based on load features. Then, onestep Markov chain is utilized to model the dynamics of load profiles. And the multiple evaluation metrics is calculated which can reflect variability, sensitivity, and quantity of electricity consumption to generate potential evaluation criterion. A numerical case study based on Low Carbon London dataset is conducted. The results show that the proposed method is feasible in terms of cluster division, metric calculation, and customer selection.