Design of a Prototype Neural Network for Smart Homes and Energy Efficiency

As a part of smart homes, a subsystem consisting of three components including a neural network is designed to provide personalized services. Unique factor combinations of building specifics, user profiles and external influences lead to the necessity of self-adaptive systems for personal comfort. The system supports room temperature control in order to heat rooms energy-efficiently at a set time. Smart home systems require a software architecture that allows services to be deployed on virtual and hardware devices. The design of automated processes is the first step of later programming and implementation into smart home systems that will automatically supervise and re-train its components and will also allow live feedback. (C) 2014 The Authors. Published by Elsevier Ltd.