Home energy management starts with a monitoring system for the user to become aware of how much e... more Home energy management starts with a monitoring system for the user to become aware of how much energy he/she consumes over a period of time and a controlling system that maximizes energy efficiency. There are two methods of load monitoring used in analyzing loads in residential installations and one of them is Intrusive Load Monitoring (ILM). This study was aimed to create an energy management system focusing on individual load monitoring of household appliances through ILM implementation. Wireless network technology was also utilized for data transmission and access, using Raspberry Pi 3B+ and SenseTecnic cloud host. The notification feature of the system, done through a cloud-based communication platform Twilio, is 100% successful in performing its function. Energy consumption behavior model equations for specific types of appliance loads were generated using regression analysis. All equations have relatively good fit, with R squared of 85% 94%, and low standard error, except for...
Home energy management starts with a monitoring system for the user to become aware of how much e... more Home energy management starts with a monitoring system for the user to become aware of how much energy he/she consumes over a period of time and a controlling system that maximizes energy efficiency. There are two methods of load monitoring used in analyzing loads in residential installations and one of them is Intrusive Load Monitoring (ILM). This study was aimed to create an energy management system focusing on individual load monitoring of household appliances through ILM implementation. Wireless network technology was also utilized for data transmission and access, using Raspberry Pi 3B+ and SenseTecnic cloud host. The notification feature of the system, done through a cloud-based communication platform Twilio, is 100% successful in performing its function. Energy consumption behavior model equations for specific types of appliance loads were generated using regression analysis. All equations have relatively good fit, with R squared of 85% 94%, and low standard error, except for...
Uploads
Papers