This article presents a novel approach to detecting emergency events, such as power outages, that utilizes social media users as “social sensors” for virtual detection of such events. The proposed new method is based on the analysis of the Twitter data that leads to the detection of Twitter discussions about these emergency events. The method described in the article was implemented and deployed by one of the vendors in the context of detecting power outages as a part of their comprehensive social engagement platform. It was also field tested on Twitter users in an industrial setting and performed well during these tests.

Power outages (PO) constitute a serious problem around the world that disrupts our lives in the most unexpected ways. There were 3, 634 power outages reported in 2014, affecting 14.2 million people [3], and over the period of 2008-2014 the US has averaged 2, 987 outages affecting 21.6 million people per year, leading to estimated losses in excess of $150 billion annually [3]. To address this problem, there have been extensive resources dedicated to detecting and reporting power outages with new technologies, such as smart sensors, meters and distribution devices [11]. Utilities’ Outage Management Systems (OMS) vary in their composition of outage detection technologies. These systems typically include both traditional and, so-called, “smart” grid elements as means of power outage detection in the utilities’ coverage regions. Unfortunately, these smart grid technologies are extremely costly, with the total cost being estimated at $338 to $476 billion, and the system will be fully implemented by only 2030 [3]. To address this important problem in the near term and with respect to budgetary constraints, it is necessary to develop alternative approaches to power outage detection. The ubiquity of smart phones and social networks has given rise to an entirely new class of sensor: the human “social sensor” [6]: any individual with a networked device and a social media account can become a “social sensor node” capable of a wide range of functions, including producing data about spontaneous events in real-time functioning either independently or as a collective network. The Electrical Utility industry is uniquely positioned to benefit from incorporating this new class of sensors into their existing Outage Management Systems via existing social networks such as Facebook or Twitter. The data produced by social sensor nodes can be analyzed, modeled, and used to construct a virtual outage detection network for power outage events that could function either independently of or in parallel with utilities’

In this paper we describe a novel approach to detecting power outages that utilizes social media platform users as “social sensors” for virtual detection of power outages. We present the underlying methodology based on analyzing Twitter and other social media data that detects bursts in tweets related to the power outages. The proposed methodology was implemented and deployed by a major company in the area of enterprise solutions for social media aggregation for the electrical utility industry as a part of their comprehensive social engagement platform. It was also field tested on the Twitter users in an industrial setting and performed well during these tests.