Penalization of electricity thefts in smart utility networks by a cost estimation-based forced corrective measure

Electricity theft menace has attracted various research efforts with most proposed detection algorithms relying on analysing customers' consumption profile to determine fraudulent electricity consumers (FEC). This necessitates the need for on-site inspections before penalties are sanctioned despite the manpower, cost, energy, time, and stress associated with such tedious routine. Moreover, the penalty-imposed fines are bogusly determined and uncoordinated, and losses in revenue are burdened on the honest consumers. Fortunately, the advent of advanced metering infrastructure offers a flexible and efficient platform which can be leveraged to provide additional functionality of curbing these complicated procedures. In this work, a cost estimation-based model deploying a forced corrective measure for a real-time enforcement of penalties on FEC in a smart utility network is proposed. It relies on the results of commonly applied intelligent algorithms for electricity theft detection to obtain the amount and cost of energy consumed by reported FEC while also providing efficient monitoring till imposed fines are cleared. The results of the developed model give proportionate sanctions and enhances the functions of the system manager's monitoring of the operational status to ensure compliance and is suitable for deployment in a smart utility network