Underground Cable Fault Location via Random Forest Algorithm

In recent years, Metropolitan Electricity Authority (MEA) has increasingly replaced the overhead lines with underground cables in Bangkok Metropolitan Area. This is to improve the efficiency and reliability of the distribution system, and also the esthetic quality of the landscape. However, the processes of locating and repairing underground cable faults are generally more difficult and time-consuming than those for overhead lines. This article proposed the use of Random Forest algorithm to locate faults for medium voltage underground cables. When tested on the MEA's open-loop underground cable system, this algorithm was capable of finding the fault locations with high accuracy, and can serve system operators and crew staff as a guideline for an efficient system service restoration.