Intelligent Decision Support System for Lowering the Costs of Service Calls for Smart Meters

The operations and maintenance (O&M) of the electric smart meter (ESM) systems constitute the most expensive systems engineering lifecycle phase, where resources drive costs up. Customer service calls activities are one of the cost items that are directly linked to the success of smart meter operations. As the number of field visits required to customer sites increases and the quality of meter reading decreases, the effect on volume of calls to customer care center will increase and overall customer satisfaction will most likely decrease.;This research focuses on introducing an intelligent decision-support system (iDSS) for lowering the costs of service calls for ESM systems. The iDSS is a novel approach that leverages advanced analytics of ESM network communication-quality data, to improve predictions for smart meter field operations, and provides actionable decision recommendations regarding whether to send a technician to a customer location to resolve an ESM issue. The predictive model is empirically evaluated using datasets from a commercial ESM network. The efficiency and accuracy of the approach are demonstrated using various machine learning classifiers. The research results will demonstrate, that this approach generates statistically noteworthy estimations, and improves the cost efficiency of ESM network O&M, implying significant contributions to the fields of systems engineering O&M cost optimization, and the applications of ESM machine learning and advanced analytics.