PurposePower management in households has become the periodic issue for electric suppliers and household occupants. The number of electronic appliances is increasing day by day in every home with upcoming technology. So, it is becoming difficult for the energy suppliers to predict the power consumption for households at the appliance level. Power consumption in households depends on various factors such as building types, demographics, weather conditions and behavioral aspect. An uncertainty related to the usage of appliances in homes makes the prediction of power difficult. Hence, there is a need to study the usage patterns of the households appliances for predicting the power effectively.Design/methodology/approachPrincipal component analysis was performed for dimensionality reduction and for finding the hidden patterns to provide data in clusters. Then, these clusters were further being integrated with climate variables such as temperature, visibility and humidity. Finally, power has been predicted according to climate using regression-based machine learning models.FindingsPower prediction was done based on different climatic conditions for electronic appliances in the residential sector. Different machine learning algorithms were implemented, and the result was compared with the existing work.Social implicationsThis will benefit the society as a whole as it will help to reduce the power consumption and the electricity bills of the house. It will also be helpful in the reduction of the greenhouse gas emission.Originality/valueThe proposed work has been compared with the existing work to validate the current work. The work will be useful to energy suppliers as it will help them to predict the next day power supply to the households. It will be useful for the occupants of the households to complete their daily activities without any hindrance.
International Journal of Energy Sector Management – Emerald Publishing
Published: Sep 2, 2019
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.
Read from thousands of the leading scholarly journals from SpringerNature, Wiley-Blackwell, Oxford University Press and more.
All the latest content is available, no embargo periods.
“Hi guys, I cannot tell you how much I love this resource. Incredible. I really believe you've hit the nail on the head with this site in regards to solving the research-purchase issue.”Daniel C.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud
“I must say, @deepdyve is a fabulous solution to the independent researcher's problem of #access to #information.”@deepthiw
“My last article couldn't be possible without the platform @deepdyve that makes journal papers cheaper.”@JoseServera