Efficient detection of electricity theft cyber attacks in AMI networks
- Resource Type
- Conference
- Authors
- Ismail, Muhammad; Shahin, Mostafa; Shaaban, Mostafa F.; Serpedin, Erchin; Qaraqe, Khalid
- Source
- 2018 IEEE Wireless Communications and Networking Conference (WCNC) Wireless Communications and Networking Conference (WCNC), 2018 IEEE. :1-6 Apr, 2018
- Subject
- Communication, Networking and Broadcast Technologies
Detectors
Energy consumption
Cyberattack
Machine learning
Neurons
Computer architecture
Companies
Electricity theft detection
cyber attacks
AMI networks
deep machine learning
- Language
- ISSN
- 1558-2612
Advanced metering infrastructure (AMI) networks are vulnerable against electricity theft cyber attacks. Different from the existing research that exploits shallow machine learning architectures for electricity theft detection, this paper proposes a deep neural network (DNN)-based customer-specific detector that can efficiently thwart such cyber attacks. The proposed DNN-based detector implements a sequential grid search analysis in its learning stage to appropriately fine tune its hyper-parameters, hence, improving the detection performance. Extensive test studies are carried out based on publicly available real energy consumption data of 5000 customers and the detector's performance is investigated against a mixture of different types of electricity theft cyber attacks. Simulation results demonstrate a significant performance improvement compared with state-of-the-art shallow detectors.