A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Smart meter technology presents an opportunity to gain better insights into consumer appliance usage and consumption behaviour. Load monitoring can provide valuable data on appliance specific energy consumption statistics which in turn will be useful for the consumer to evolve an optimum energy utilization strategy. In the utility point of view, the data acquired in this manner could be used to evolve better target demand side management programs, including demand response and energy efficiency. Non-intrusive load monitoring (NILM) is a consumer energy disaggregation technique that segregates individual appliance energy consumption from the total energy measured at the mains. Unlike intrusive load monitoring, it does not require separate meters to measure individual device consumption. This field has garnered lot of research interest recently, owing to emergence of smart grid technologies and advances in smart metering. Machine learning algorithms are predominantly used to solve NILM problems. In view of concerns regarding customer privacy and economics, low frequency smart meters are preferred. There are many challenges involved in using low granularity data for NILM algorithms. This work summarizes the current state of the art of NILM methods for low rate smart meter data. The limitations of the present methods and scope for future work are also presented.
Smart meter technology presents an opportunity to gain better insights into consumer appliance usage and consumption behaviour. Load monitoring can provide valuable data on appliance specific energy consumption statistics which in turn will be useful for the consumer to evolve an optimum energy utilization strategy. In the utility point of view, the data acquired in this manner could be used to evolve better target demand side management programs, including demand response and energy efficiency. Non-intrusive load monitoring (NILM) is a consumer energy disaggregation technique that segregates individual appliance energy consumption from the total energy measured at the mains. Unlike intrusive load monitoring, it does not require separate meters to measure individual device consumption. This field has garnered lot of research interest recently, owing to emergence of smart grid technologies and advances in smart metering. Machine learning algorithms are predominantly used to solve NILM problems. In view of concerns regarding customer privacy and economics, low frequency smart meters are preferred. There are many challenges involved in using low granularity data for NILM algorithms. This work summarizes the current state of the art of NILM methods for low rate smart meter data. The limitations of the present methods and scope for future work are also presented.
NON-INTRUSIVE LOAD DISAGGREGATION METHODS FOR LOW-RATE SMART METER DATA
Divya M. (author)
2021-11-10
International Engineering Journal For Research & Development; Vol. 6 No. ICRRTNB (2021): International Conference on “Role of Recent Technology in Nation – Building"; 12 ; 2349-0721
Article (Journal)
Electronic Resource
English
DDC:
690
Disaggregation of household solar energy generation using censored smart meter data
| BASE | 2021
Non-Intrusive Load Disaggregation of Industrial Cooling Demand with LSTM Neural Network
| BASE | 2022