Multi-objective home appliance scheduling with implicit and interactive user satisfaction modelling

[Display omitted] •A new multi-objective approach for appliance scheduling by minimizing the cost and user dissatisfaction.•Implicit modelling of user satisfaction from the past appliance usage patterns obtained from energy disaggregation.•Modified user satisfaction objective where importance of a d...

Full description

Saved in:
Bibliographic Details
Published in:Applied energy Vol. 267; p. 114690
Main Authors: Pamulapati, Trinadh, Mallipeddi, Rammohan, Lee, Minho
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.06.2020
Subjects:
algorithms
consumer satisfaction
decision making
electric energy consumption
electricity
Electricity cost minimization
energy
Energy disaggregation
Home appliance scheduling
household equipment
humans
Implicit user satisfaction estimation
Interactive scheduling
Multi-objective scheduling
Implicit user satisfaction estimation
Multi-objective scheduling
Home appliance scheduling
Interactive scheduling
Energy disaggregation
Electricity cost minimization
ISSN:0306-2619, 1872-9118
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] •A new multi-objective approach for appliance scheduling by minimizing the cost and user dissatisfaction.•Implicit modelling of user satisfaction from the past appliance usage patterns obtained from energy disaggregation.•Modified user satisfaction objective where importance of a device(s) operation can be incorporated through a priority weight.•Ability to provide customized schedules for different scheduling intervals.•Suggesting representative trade-off schedules (RTS) using trade-off worth (μ) metric and niching. Residential consumers desire to minimize electricity bills while maximizing comfort by appropriate appliance scheduling. The conflicting nature of the objectives facilitates a multi-objective formulation that can provide a set of trade-off schedules enabling better decision making. In literature, user preference or comfort regarding each device at each time instance is obtained explicitly. In addition, scheduling interval of 1-hour is considered because reducing scheduling interval to 1 or 5 min drastically increases – (1) the dimensionality of search space and complicates the search process, and (2) the number of time instances for which the user has to explicitly provide the preference resulting in human fatigue. However, it is essential to schedule the devices at lower scheduling intervals to precisely-estimate the electricity consumption due to the presence of high power devices such as microwave that operate for shorter intervals (<5 min). In this work, we employ an efficient and scalable multi-objective evolutionary algorithm to solve the scheduling problem. In addition, the user preference is implicitly estimated from the past usage patterns obtained using energy disaggregation. And, if the estimated user preference deviates from the user expectation then the user can modify preference using weights referred to as priority weights. The novel implicit user satisfaction modeling and interactive customization through priority weights makes the proposed work a standalone approach suitable for any user. Experimental results and analysis for various user priorities and scheduling intervals (ranging from 1-minute to 1-hour) proves that the proposed framework is able to provide generalized schedules.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0306-2619
1872-9118
DOI:10.1016/j.apenergy.2020.114690