Download | - View final version: Forecasting temperature in a smart home with segmented linear regression (PDF, 458 KiB)
|
---|
DOI | Resolve DOI: https://doi.org/10.1016/j.procs.2019.08.071 |
---|
Author | Search for: Spencer, Bruce1; Search for: Alfandi, Omar; Search for: Al-Obeidat, Feras |
---|
Affiliation | - National Research Council of Canada. Digital Technologies
|
---|
Format | Text, Article |
---|
Conference | The 9th International Conference on Sustainable Energy Information Technology (SEIT), August 19-21, 2019, Halifax, Nova Scotia, Canada |
---|
Subject | home sensor network; temperature forecasting; LASSO regression; feature selection; model predictive control; energy efficiency; internet of things |
---|
Abstract | The efficiency of heating, ventilation and cooling operations in a home are improved when they are controlled by a system that takes into account an accurate forecast of temperature in the house. Temperature forecasts are informed by data from sensors that report on activities and conditions in and around the home. Using publicly available data, we apply linear models based on LASSO regression and our recently developled MIDFEL LASSO regression. These models take into account the past 24 hours of the sensors’ data. We have previously identified the most influential sensors in a forecast over the next 48 hours. In this paper, we compute 48 separate one-hour forecast and for each hour we identify the sensors that are most influential. This improves forecast accuracy and reveals which sensors are most valuable to install. |
---|
Publication date | 2019-09-13 |
---|
Publisher | Elsevier B.V. |
---|
Licence | |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Identifier | S1877050919309858 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | a75586a5-3883-4335-b1a9-64dfe606af09 |
---|
Record created | 2020-11-27 |
---|
Record modified | 2021-03-08 |
---|