PROJECT TITLE :

Development of Low Voltage Network Templates—Part II: Peak Load Estimation by Clusterwise Regression

ABSTRACT:

This paper proposes a unique contribution factor (CF) approach to predict diversified daily peak load of low voltage (LV) substations. The CF for every LV template developed in half I of the paper is set by a novel method-clusterwise weighted constrained regression (CWCR). It takes into account the contribution from different client categories to substation peaks, respecting the natural distinction in time and magnitude between LV substation peaks and also the variance within the templates. In CWCR, intercept and coefficients are constrained to ensure that the resultant coefficients do not cause reverse load flow and can respect zero-load substations. Cross validation is developed to validate the soundness of the proposed method and prevent over fitting. The proposed method shows vital improvement within the accuracy of peak estimation over this status quo across 800 substations of different mixes of domestic, industrial and industrial (I&C) customers. The work in the 2 components of the paper is significantly useful for understanding the capabilities of LV networks to accommodate the increasing penetration of low carbon technologies while not massive-scale monitoring.