Description: Residential buildings account for a significant proportion of overall energy consumption across the world. Decentralized room level Air Conditioners (ACs) are commonplace in developing countries such as India, contributing a significant share (34% in India) of the total residential energy consumption. Option to independently control each AC presents a prime opportunity for an energy saving system. Thus, we propose PACMAN to non-intrusively (using only the temperature information) predict AC energy consumption prior to usage and estimate energy consumption post-usage.
We discuss various possible applications and use cases of such feedback for the occupants. To empirically validate the performance of PACMAN, we conducted an in-situ study across seven homes in Delhi (India). We collected around 2200 hours of usage data from different ACs, room types, and thermostat temperatures. We achieved an average accuracy of 85.3% and 83.7% with the best accuracy of 97.0% and 93.3% for the estimation and prediction of AC energy consumption respectively, across all homes. Towards the end, we discuss various outlier scenarios, opening up multiple directions for further research in this domain. The code is available on my GitHub account. For more details about the approach, feel free to read the blog post.
Technologies Used: Python
Teammates: Dr. Amarjeet Singh, Dr. Vikas Chandan
Publications:
Milan Jain, Amarjeet Singh, Vikas Chandan; “Non-Intrusive Estimation and Prediction of Residential AC Energy Consumption”, Proceedings of the IEEE International Conference on Pervasive Computing and Communications (PerCom 2016) held in Sydney, Australia. [IEEE][Preprint][Slides]
Milan Jain, “PACMAN: Predicting AC Consumption Minimizing Aggregate eNergy consumption”, Master’s Thesis, Department of Computer Science, IIIT-Delhi (2014). [IIITD][Preprint][Slides]
Published by Milan Jain
"Technology is nothing. What's important is that you have faith in people, that they're basically good and smart, and if you give them tools, they will do wonderful things with them" - Steve Jobs. We are here to design technology that assists people, not to replace them. Today, we are surrounded by the sensors which are generating an enormous amount of information. While this giant pool of data can learn a lot about human behavior, with the right intent, data and technology together can genuinely benefit the people. If data can identify that a person is under stress, technology should provide a way to reduce that stress. I am a data science researcher and primarily works at the intersection of data science and smart homes. Being a researcher, I keep exploring novel and innovative ways to make homes energy efficient, comfortable, and sustainable.
View all posts by Milan Jain
