Combating energy theft with analytics
Cemig saves US$420,000 a month by identifying commercial losses related to the misuse of power and technical failures
While fraudulent activity in most industries leads to lost revenue or increased risk exposure, energy theft is different. It’s not just about the revenue lost or the drain on the energy grid. Energy theft can be illegal and hazardous. Tampering with equipment – such as meters, pipes and wires – exposes people to the risk of electric shock, explosion, injury or possibly death.
Before using SAS Enterprise Miner, we could find only 35 percent of fraudsters during the inspection. Now we can detect more than 50 percent.
In Brazil, the level of energy theft was a concern for the National Electric Energy Agency (Aneel). It estimates that nontechnical loss has a financial impact of US$1.2 billion a year in the country. If the risk to life and limb won’t thwart thieves, perhaps analytics will.
Utilities provider Cemig (Companhia Energética de Minas Gerais) uses SAS® Analytics to increase accuracy in locating power deviations and technical faults in meters scattered around the metropolitan region of Belo Horizonte, Minas Gerais. Because physical inspection of all energy customers is not practical, analytical prioritization enables Cemig to identify and prioritize candidates.
Since implementing SAS® Enterprise Miner™, Iguatinan Monteiro, Planning Engineer for Cemig, says the company saves about $420,000 a month by detecting energy theft. Cemig uses the technology for statistical modeling, helping analyze data about consumption history, socio-demographic information and geographic potential of each household.
“Before using SAS Enterprise Miner, we could find only 35 percent of fraudsters during the inspection. Now we can find more than 50 percent,” says Monteiro.
After analyzing the data, Cemig uses SAS to generate a score for the household or establishment. The score shows the probability that the location is the site of energy theft.
“When the investigator visits the site, he already knows in advance which installed devices are more likely to have failures and deviations,” explains Monteiro. “We also can identify the consumer units with higher volume offset. These are the ones that cause significant harm to the company and to the end consumer.”
Detect and mitigate financial losses related to electricity theft, billing errors and meter failure.
- Detects more than 50 percent of energy fraud cases.
- Pinpoints energy deviations (nontechnical loss).
- Identifies technical faults in meters (technical loss).
- Savings of about $420,000 per month.
Cemig is a major electric utilities provider in Brazil. Cemig accounts for 96 percent of Minas Gerais’ concession area, with more than 7.5 million consumers in 774 municipalities. The company is also a power generator, operating 70 plants with an installed capacity of 7,295 megawatts.