Energy Theft Detection in Multi-Tenant Data Centers with Digital Protective Relay Deployment

Abstract

High performance data centers serve as the backbone of the prevailing cloud computing paradigm. Among data centers with different operational structures, multi-tenant data centers (MTDCs) are increasingly popular among various internet service providers for the ease of deployment. Despite the offered benefits, MTDCs are vulnerable to various cyberattacks. An important cyberattack is energy theft which can be launched by malicious tenants to reduce monetary cost of the electricity consumption. It can be achieved through attacking a smart meter in the data center to undercount its energy usage. By alleviating the financial burden of the cloud service providers in MTDCs, energy theft discourages frugality in terms of energy consumption, which is highly undesirable in the era of sustainable computing. Despite fruitful research results on MTDCs, none of them address energy theft. When energy theft occurs, it might be necessary for the data center operator to examine smart meter of all tenants to find the compromised ones which could induce excessive labor cost. Localization of energy theft detection is an effective way to limit the labor cost in detecting energy thefts in MTDCs. It can be facilitated through deploying Digital Protective Relays (DPR) in the data center where a DPR is a microprocessor based device for fault detection and event logging in the power system. In this paper, we propose an anomaly rate range based dynamic programming algorithm for inserting DPRs into the data center while minimizing the deployment cost. Our algorithm optimizes the DPR deployment through exploring an innovative aggregated anomaly rate range which accounts for the long term effect of energy theft in an MTDC. In addition, given the historical records of energy usage for all tenants, we calculate the anomaly rate range for each tenant, leveraging the Minimum Covariance Determinant (MCD) based anomaly identification algorithm. To the best of our knowledge, this is the first work addressing the energy theft issue in multi-tenant data centers. The simulation results demonstrate that our algorithm inserts 18:9% less DPRs into the data center compared to a natural baseline algorithm. Meanwhile, in an attempt to identify all energy theft cases, our DPR insertion solution requires 14:7% less tenants to be checked compared with a natural heuristic baseline algorithm.

Existing System

Proposed System

Architecture