Intelligent Information System as a Tool to Reach Unaproachable Goals for Inspectors - High-Performance Data Analysis for Reduction of Non-Technical Losses on Smart Grids

Abstract

The Non-Technical Losses (NTLs) represent the non-billed energy due to faults or illegal manipulations in customer facilities. The objective of the Midas project is the detection of NTL through the application of computational intelligence over the information stored in utility company databases. This project has several research lines. Some of them are pattern recognition, expert systems, big data and High Performance Computing (HPC). This paper proposes module which use statistical techniques to make patterns of correct consumption. This module is integrated with a rule based expert system with other modules as: text mining module and data warehousing module. The correct consumption patterns are generated using rules which will be used in rule based expert system. Two implementations are proposed. Both implementations provided an Intelligent Information System (IIS) to reach unapproachable goals for inspectors.