Abstract
With the widespread adoption of smart meters in buildings, an unprecedented amount of high-resolution energy data is released, which provides opportunities to understand building consumption patterns. Accordingly, research efforts have employed data analytics and machine learning methods to segment customers based on their load profiles, which help utilities and energy providers promote customized/personalized targeting for energy programs. Existing energy consumption segmentation techniques use assumptions that could reduce clusters’ quality in representing their members. Therefore, in this paper, we investigated a two-stage clustering method for capturing more representative load shape temporal patterns and peak demands through a cluster merging approach. In the first stage, load shapes are clustered (using classical clustering algorithms) by allowing a large number of clusters to accurately capture variations in energy use patterns, and cluster centroids are extracted by accounting for limited shape misalignment within the range of Demand Response (DR) timeframes. In the second stage, clusters with similar centroids and power magnitude ranges are merged using Complexity-Invariant Dynamic Time Warping. We used three datasets consisting of ~250 households (~15000 profiles) to demonstrate the efficacy of the framework, compared to baseline methods, and discuss the impact on energy management. The proposed investigated merging-based clustering also increased correlation between cluster centroids and the corresponding members by 3–9% for different datasets.
Highlights
Demand response (DR) mechanisms help electricity providers maintain distribution reliability, reduce generation cost and environmental concerns, and increase utilization of renewable energy
Seeking to evaluate cluster representation, in this paper, we investigated a cluster merging approach for identifying representative electricity load shapes that account for improved compatibility between cluster centroids and their contributing load shapes while capturing both temporal variations and peak values of energy use profiles
We evaluated a cluster merging technique through a two-stage approach to preserve temporal patterns and peak magnitude of load shapes for segmentation and increase the quality of clusters in representing their corresponding members
Summary
Demand response (DR) mechanisms help electricity providers maintain distribution reliability, reduce generation cost and environmental concerns, and increase utilization of renewable energy. Advanced metering infrastructure (AMI) and smart meters have been adopted to provide finegrained (hourly or sub-hourly) energy data for advanced analytics to enhance the efficiency of power network operations. With the wide adoption of smart meters nationwide [6], and the availability of hourly and sub-hourly data, segmentation methods have been used to find similar patterns of electricity consumption behavior of customers. This task can be applied in different capacities to improve power system operations including implementation of DR programs [7], load forecasting [8], tariff determination [9], and renewable integration [10], [11]. The primary objective of the customer segmentation task is to transform a large library of load shapes (i.e., all profiles in a database) into representative daily energy use routines, which altogether define the typical behavioral patterns of the entire customer base
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
