Real-Time Power Outage Detection System using Social Sensing and Neural Networks

With the omnipresence of big data, social sensing has become a valuable technique for information retrieval and event detection. In recent years, extensive research has been conducted on using social sensing as a platform to detect critical events and emergency situations such as natural disasters, criminal activities, and power outages. In this paper, we focus on detecting real-time power outages using social sensing by investigating different predictive models, preprocessing techniques and feature extraction methods. The investigation shows that multi-layer perception neural network outperforms other popular predictive models. The paper proposes a real-time situational-awareness mechanism to detect the ongoing power outages and extract useful information for power outage management. In the proposed framework, for temporal analysis, a modified approach of Kleinberg’s burst detection algorithm is proposed to ensure the prompt detection of power outages. This study paves the way for future investigation and innovation in efficient real-time event detection using social sensing.