Modeling and Recognition of Smart Grid Faults by a Combined Approach of Dissimilarity Measures and One-Class Classification (original) (raw)

Detecting faults in electrical power grids is of paramount importance, either from the electricity operator and consumer viewpoints. Modern electric power grids (smart grids) are equipped with smart sensors that allow to gather real-time information regarding the physical status of all the component elements belonging to the whole infrastructure (e.g., cables and related insulation, transformers, breakers and so on). In real-world smart grid systems, usually, additional information that are related to the operational status of the grid itself are collected such as meteorological information. Designing a suitable recognition (discrimination) model of faults in a real-world smart grid system is hence a challenging task. This follows from the heterogeneity of the information that actually determine a typical fault condition. The second point is that, for synthesizing a recognition model, in practice only the conditions of observed faults are usually meaningful. Therefore, a suitable recognition model should be synthesized by making use of the observed fault conditions only. In this paper, we deal with the problem of modeling and recognizing faults in a real-world smart grid system, which supplies the entire city of Rome, Italy. Recognition of faults is addressed by following a combined approach of multiple dissimilarity measures customization and one-class classification techniques. We provide here an in-depth study related to the available data and to the models synthesized by the proposed one-class classifier. We offer also a comprehensive analysis of the fault recognition results by exploiting a fuzzy set based reliability decision rule. control, communication, and self-healing technologies in order to (i) facilitate the connection and operation of generators of all sizes and technologies; (ii) allow consumers to play an active role in optimizing the operation of the system; (iii) significantly reduce the environmental impact of the whole electricity supply system; (iv) preserve or improve the level of system reliability, quality of service, and security. SGs can be considered as an "evolution" rather than a "revolution" of the existing energy networks . The evolution is leaded by the symbiotic exchange between power grid technologies and the Information and Communication Technologies (ICT). ICT provide instruments, such as Smart Sensors (SS), to monitor the network status, wired and wireless communication network to collect and transport data, and powerful computational architectures for data processing. A SG can be framed as a complex non-linear and time-varying system , where heterogeneous elements, including exogenous factors, are extremely interconnected through the exchange of both energy and information. Computational Intelligence (CI) techniques offer sound modeling and algorithmic solutions in the SG context . Well-known CI techniques adopted in the SG context include approximate dynamic programming [10], neural networks and fuzzy inference systems for prediction and control , and swarm intelligence and evolutionary computation for optimization problems ].