Extraction of Energy Information From Analog Meters Using Image Processing

There has been an ongoing effort to increase the number of advanced metering infrastructure (AMI) devices to improve system observability. When deployed across distribution secondary networks, AMI provides building-level load and consumption information, which can be used to improve grid management strategies. A barrier to implementation is the significant upgrade costs associated with retrofitting existing meters with network-capable sensing. One economic way is to use imageprocessing methods to extract usage information from images of the existing meters.

This paper presents a solution that uses online data exchange of power consumption information to a cloud server without modifying the existing electromechanical analog meters. In this framework, a systematic approach to extract energy data from images is applied to replace the manual reading process. A case study is presented where the digital imaging approach is compared to the averages determined by visual readings over a one-month period.