Understanding customers’ energy consumption at the individual appliances level is crucial for the planning and implementation of demand response (DR) programs. The appliances’ usage profiles can be disaggregated from whole-house energy consumption data using non-intrusive load monitoring (NILM) methods. The appliance load patterns of each customer are considerably different, which make it challenging to train a model with strong generalization ability. In this paper, a novel methodology using transfer knowledge between domains for NILM is proposed. A temporal convolutional network is developed to learn the dynamic features of individual appliance load. A domain adaption loss is used to quantify the domain distribution discrepancy between source and target domain representation. By jointly optimizing domain adaptation and energy disaggregation, an invariant representation across domains for the individual appliance states can be learned. Data experiments on ground truth data validate the accuracy and the robustness of the proposed model, and demonstrate its superior transferability and application potential under those scenarios of data shortage.

Battery energy storage (BES) and demand response (DR) are two important resources to increase the operational flexibility of a virtual power plant (VPP) and thus reduce the economic risks that VPP faces in the short-term electricity market. This article develops a data-driven approach for VPP resource planning (VRP), in which BES sizing and DR customer selection are optimized synergistically to maximize VPP's profit in the electricity market. Heterogeneity in DR potential across individual customers is considered in the planning framework by utilizing the knowledge learnt from smart meter data. The overall VRP problem is formulated by a risk-managed, multistage stochastic programming framework to address the uncertainties from the intermittent renewable energy sources, load demands, market prices, and DR resources. Case studies compare the VRP results under two market imbalance settlement settings, namely, penalty-charged and penalty-free markets. The results demonstrate that jointly optimizing BES and DR customer selection leveraging the smart meter data can improve the VPP's expected profit under both market settings.

Targeting the right customers for energy efficiency (EE) programs is crucial for the power distribution or retail companies to enhance the efficiency of marketing budget allocation and the yield of energy savings. This work presents a scalable methodology for targeting residential customers for EE programs that focus on reducing unnecessary domestic energy consumption and replacing low efficient refrigerator-freezers by using smart meter data and daily temperature data. A novel method is proposed to detect baseload (i.e. power constantly consumed by some appliances that are never turned off) segments from daily load profiles. Test on ground truth data shows the high accuracy performance of the proposed method and its adaptiveness to the heterogeneity in energy consumptions across customers. Then we discuss how the proposed method can be utilized to identify customers with high baseload energy saving potentials and low efficient refrigerator-freezers. Case studies validate that the proposed targeting strategy far outperforms random selection.

For demand response (DR) programs that focus on the energy consumption of heating, ventilation, and air conditioning (HVAC), the knowledge on HVAC usage of individual customers is of great value for DR program implementation. This paper presents a novel methodology to extract space cooling usage from smart meter data. A multisequence, non-homogeneous Factorial Hidden Markov Model (MN-FHMM) is proposed to disaggregate the whole-house energy consumption into an HVAC component and a baseload (i.e., the sum of non-temperature-sensitive loads) component. Rather than holding a constant transition probability over the whole process, a time-varying transition probability model is developed to characterize the dynamic nature of the evolution of users energy consumption. We also discuss how to use the disaggregation results to estimate the HVAC related DR potential for individual customers, which can further inform DR programs to target customers more cost-effectively. Data experiments on ground truth data validate both the accuracy and the robustness of the proposed model as well as the effectiveness of the targeting strategy based on the disaggregation results.

Load shape dictionary (LSD) is a useful tool for utilizing the enormous amount of smart meter data to understand customers’ electricity consumption behaviors. To tackle the big data challenge as well as to better capture the load shape features, this paper develops a bilevel LSD generation framework to cluster and index the residential load profiles into a neat local LSD and a global LSD based on the Derivative Dynamic Time Warping (DDTW) elastic dissimilarity measure. Different from the classic Dynamic Time Warping (DTW), DDTW works on the derivative of the raw data to avoid DTW’s problem of pathological alignments. To reduce the computational cost, a fast DDTW (FDDTW) is proposed to speed up the DDTW calculation. Based on the generated bilevel LSD, analytic approaches are proposed to extract features from the data indexed by the LSD to reveal useful information of customers’ electricity consumption behaviors. Numerical experiments on real premise data verify the effectiveness of the proposed methodology in terms of clustering performance and computational efficiency. Our analysis suggests that the proposed methodology can be applied to improve load forecasting, tariff design and DR customer targeting.

Smart meter data provides rich information on customers’ energy consumption behaviors, which can be a valuable resource for evaluating customers’ demand response (DR) potential and thus can inform the distribution system expansion planning (DSEP). This paper presents a novel DSEP framework incorporating a data-driven model for a particular type of incentive-based DR called the thermostatically-controlled-load DR. The heterogeneity in individual customers’ DR potential is considered in the DSEP by leveraging the healing, ventilation, and air conditioning (HVAC) load information extracted from smart meter data. The relationship between the DR incentive and the customer participation rate is also considered so that incentives can be optimally designed for customers with different DR potentials in a differentiated way. The overall DSEP problem is formulated into a robust optimization framework to address the uncertainties from the load demands, renewable energy generations, and DR resources. Case studies show that the proposed DSEP model can substantially reduce the total expansion cost over conventional planning paradigms, demonstrating the positive role of the proposed data-driven DR model in DSEP.