Unsupervised Clustering for Regional Demand Response Potential to Support Renewable Integration and Decarbonisation

Accurately estimating demand response (DR) potential is challenging in regions without historical DR programs. This paper presents an unsupervised, clustering-based framework that infers regional DR potential directly from smart-meter load data. The pipeline includes (i) data cleansing and normalization; (ii) customer segmentation using DRL-DBSCAN and RW-Clustering to uncover consumption regularities and latent flexibility; and (iii) aggregation of segment-level flexibility to form regional DR potential indices. A case study on the Low Carbon London (LCL) smart-meter trial uses half-hourly load measurements from 487 residential customers to quantify the performance of the proposed method. Compared with a conventional k-means baseline, the proposed DRL-DBSCAN plus RW-Clustering pipeline improves the Davies–Bouldin index from 4.9545 to 2.1642 and the Xie–Beni index from 10.7438 to 6.6637, yielding more compact and better-separated typical daily load profiles and more reliable DR potential estimates. The resulting probability distributions of upward and downward DR potential across 48 half-hourly time steps provide a quantitative basis for targeting flexible customer segments and prioritizing DR deployment. The proposed method supports distribution-level planning and local grid operation—especially in areas where DR infrastructure is nascent—and offers a scalable tool for integrating demand-side flexibility into renewable-rich power systems.