Short term electrical load forecasting for an urban 11 KV feeder using machine learning techniques

Journal Title: Journal of Multidisciplinary Sciences - Year 2019, Vol 1, Issue 1

Abstract

Accurate electricity load estimation is an important issue for the operation of the power system and it is one of the essential works of future power planning for large cities. Every power prediction model has its own benefits and drawbacks and has its particular application range. Researchers categorized the load energy forecasting as Short-Term Load Forecasting (STLF), Medium-Term Load Forecasting (MTLF) and Long-Term Load Forecasting (LTLF), which entirely depends on time in which estimation is scheduled. As electricity load forecasting can be seen as a machine learning problem, so a number of automated methodologies and models are included in the literature review. In this work, we aim to explore and implement state of art machine learning techniques like Polynomial Regression, Support Vector Regression (SVR) and Artificial Neural Networks (ANN) in order to predict the short term and medium-term load consumption for the historical data accurately. For this study, hourly load data of an Urban 11 KV Feeder was collected from the 220 KV grid station. Weather parameters like temperature, pressure and humidity data for the particular region were taken from Lahore Meteorological Department. Data were divided into several datasets (daily, weekly and monthly) to achieve short term and medium-term electrical load prediction using aforementioned techniques. Input parameters used in this study were temperature (both dry and wet), humidity and pressure while predicted hourly load demand was used as output. Final results tables show that the performance of the SVR predictor is much better than other techniques both in short term and medium load forecasting.

Authors and Affiliations

Abdul Khaliq, Ikramullah Khosa, Muhammad Muneeb

Keywords

Related Articles

Aspergillus creber and A. keveii, two new records as endophytes from wild medicinal plants in Egypt

In the present research and during surveys of mycobiota inhabiting leaves and roots of some wild and medicinal plants in El-Kharga Oasis, New Valley Governorate, Egypt, two significant isolates were isolated for the firs...

Present scenario of knowledge management effectuation in the national library of Bangladesh: A study

The primary goal of this paper includes finding out systems used in National Library of Bangladesh (NLB) to confine the created knowledge and investigate the library officers’ views of knowledge management (KM). Survey m...

Biological characterization of two bacteriophages infecting Klebsiella pneumoniae

Klebsiella became an increasingly important source of community-acquired and nosocomial infections. Extensive broad-spectrum utilization of antibiotics in hospitalized patients has contributed to both increased carriages...

Performance of eighteen advanced wheat lines grown under irrigated optimum and late sown conditions in different regions of Bangladesh

Eighteen advanced wheat lines were evaluated for irrigated optimum and late sown conditions in different environmental regions of Bangladesh. The experiments were conducted at Bangladesh Wheat and Maize Research Institut...

Biocontrol of pepper wilt disease by antagonistic fungi and their modes of action for the biocontrol

Thirty species of fungi related to 16 genera were isolated from the rhizosphere soils of healthy pepper plantations in different localities in Assiut (13 localities), Behera (2 localities) and Sohag Governorates (2 local...

Download PDF file
  • EP ID EP683685
  • DOI https://doi.org/10.33888/jms.2019.114
  • Views 287
  • Downloads 0

How To Cite

Abdul Khaliq, Ikramullah Khosa, Muhammad Muneeb (2019). Short term electrical load forecasting for an urban 11 KV feeder using machine learning techniques. Journal of Multidisciplinary Sciences, 1(1), -. https://europub.co.uk/articles/-A-683685