Commercial buildings have a significant impact on energy and the environment, being responsible for more than 18% of the annual primary energy consumption in the United States. Analyzing their electrical demand profiles is necessary for the assessment of supply-demand interactions and potential; of particular importance are supply- or demand-side energy storage assets and the value they bring to various stakeholders in the smart grid context. This research developed and applied unsupervised classification of commercial buildings according to their electrical demand profile. A Department of Energy (DOE) database was employed, containing electrical demand profiles representing the United States commercial building stock as detailed in the 2003 Commercial Buildings Consumption Survey (CBECS) and as modeled in the EnergyPlus building energy simulation tool. The essence of the approach was: (1) discrete wavelet transformation of the electrical demand profiles, (2) energy and entropy feature extraction (absolute and relative) from the wavelet levels at definitive time frames, and (3) Bayesian probabilistic hierarchical clustering of the features to classify the buildings in terms of similar patterns of electrical demand. The process yielded a categorized and more manageable set of representative electrical demand profiles, inference of the characteristics influencing supply-demand interactions, and a test bed for quantifying the impact of applying energy storage technologies.