Open AccessData Analytics for Substation Overloading Assessment of Solar Integrated Distribution System
Author(s) -
Juhi Sharma
Publication year - 2020
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.f9577.038620
Subject(s) - adaptive neuro fuzzy inference system , reliability engineering , computer science , photovoltaic system , transformer , electric power system , tap changer , engineering , simulation , voltage , power (physics) , fuzzy logic , electrical engineering , fuzzy control system , physics , quantum mechanics , artificial intelligence
It is an important concern to supply uninterrupted power to consumer under competitive environment. Therefore, available reserve margin of substation transformer is utmost concerns for power utilities due to its direct effects on power quality, reliability and revenue loss. This research work focus on data analytics application to predict substation overloading assessment for integrated distribution system. This paper has developed three adaptive neural fuzzy interface system (ANFIS) to predict the available substation reserve margin by considering base case and different solar integration scenarios. The ANFIS models were trained and tested using stochastic data obtained from load flow computation for a modified IEEE 37 feeder. To train ANFIS models, input variables are taken as “voltage unbalance factor, feeder power loss to load ratio, maximum branch loading, voltage deviation, and minimum power factor”, while target variable is taken as substation reserve margin”. All predications of ANFIS models are compared with those values obtained from load flow computation. It was found that predicated results have good agreement with load flow computational data and R-squared value fall in the range of 0.9182 to 0.9173. The proposed research work is useful to predict operational performance of integrated solar distribution system in smart grid environment.