Design of Load Balancing Method on Secondary Distribution Network Using Artificial Intelligence Based on Fuzzy Logic

Abstract

In order to reduce load imbalance on distribution power transformer, Indonesia Electrical Power Utility (PLN) is using Load Balancing strategy. According to the Circular Letters of the Directors of PT. PLN (Persero) No. 0017E/DIR/2014 regarding Distribution Transformer Maintenance Methods Based on Asset Management Rules on distribution transformers stipulates a good load imbalance, 10%. Based on the load measurements carried out on the distribution transformer NBR 022 with a capacity of 200 kVA supplied by the Matoa feeder, the load imbalance value was 11.25% and 12.74% in 1 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> semester of 2021 and 2019 respectively. The peak load measurement in 2019, 2020, and 1 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> semester of 2021 were employed as the input for load balancing using Fuzzy Logic Algorithm. Fuzzy logic has the advantage in faster data processing than the conventional balanced day-today method that commonly used to perform load balancing. According to simulation, Fuzzy logic can reduce load imbalance from 11.25% to 4.18% in the 1st semester of 2021 and 12.74% to 8.29% in the 1st semester of 2019. These results indicate that Load Balancing using Fuzzy Logic could decrease the load imbalance to the value below 10%. In addition, the percentage of loading in each phase is more evenly distributed after balancing the load using fuzzy logic. So, this proves that the fuzzy logic program can work well for load balancing.