#EndEnergyPoverty
Syndicate content

Law and Regulation

Machine Learning Helps Power Down Electricity Theft in Jamaica

Anna Lerner's picture
  • In Jamaica, about a quarter of electricity produced is stolen or “lost” through non-paying customers and/or accounting errors. Manual detection has failed to make a difference in reducing this theft.
  • ESMAP’s technical assistance team implemented a machine learning model to help Jamaican utility JPS identify and decrease incidents of theft.
  • The machine learning model is based on an open source code, and is available for free to any utility.
About a quarter of the electricity produced by Jamaica’s energy utility, Jamaica Public Service (JPS) is stolen. When traditional, labor-intensive methods failed to produce lasting results, Jamaica tried a different approach: machine learning.
 
Globally, billions of dollars are lost every year due to electricity theft, wherein electricity is distributed to customers but is never paid for. In 2014 alone, Jamaica’s total power transmission and distribution system reported 27% of losses (due to technical and non-technical reasons), close to double the regional average. While the utility company absorbs a portion of the cost, it also passes some of that cost onto consumers. Both actors therefore have an incentive to want to change this.
 
To combat this, JPS would spend more than $10 million (USD) on anti-theft measures every year, only to see theft numbers temporarily dip before climbing back up again. The problem was, these measures relied primarily on human-intensive, manual detection, and customers stealing electricity used more and more sophisticated ways to go around regularly metered use. JPS employees would use their institutional knowledge of serial offenders and would spend hours poring over metering data to uncover irregular patterns in electricity usage to identify shady accounts. But it wasn’t enough to effectively quash incidents of theft.

Policy shifts to strengthen China’s power sector reform

Yao Zhao's picture
Over the past few years, China saw more investment and installation in renewable energy than any other country in the world. In fact, in the period between 2010 and 2015, investment in the sector reached $377 billion, more than the next two countries - the United States and Germany – combined. China has 150 GW wind power and 77 GW solar photovoltaic power capacity compared to the U.S., for example, which has 80 GW in wind and 35 GW solar PV.

China has performed well above the global average, shined as the regional leader in East Asia, matched, if not outperformed, OCED countries in many dimensions, many countries with much lower investments and capacity have scored higher on renewable energy indicators.

Why the discrepancy?

The World Bank's Regulatory Indicators for Sustainable Energy (RISE) could shed some light on the issue. Launched in February 2017, RISE is a policy scorecard of unprecendented breadth and depth covering energy access, energy efficiency and renewable energy in 111 countries. It focuses on regulatory frameworks in these countries and measures that are within the direct responsibility of policy-makers. The result is based on data made available to the team at the end of 2015 and thoroughly validated.
 
 

Mining Contracts – Five Tips for Governments and the Rest of Us

Michael Jarvis's picture

Mining is a high stakes industry. For the growing list of countries looking to translate underground assets into tangible benefits above the ground, the ability to negotiate and implement a good deal is critical.  However, capacities to do so are often weak. A handy resource is now available to help countries. And it’s free!