Artificial intelligence and Internet of Things in a smart home contextنوشته شده توسط شیدا بهلولی
- نام نویسندگان: Lynggaard, Per
Artificial intelligence and Internet of Things in a smart home context
Artificial intelligence , Internet of Things , smart home , Building Automation System , Personal Area Network , Radio-frequency identification , Wireless Sensor Network , The history of smart homes has its source and roots in building and home automation. Today (2013), the home automation area offers remote and timer control of systems and embedded devices such as light, heating, ventilation, ntertainment systems, appliances, etc., to improve comfort, convenience, energy efficiency, and ecurity. However, the element of autonomous behavior is lacking, this is where the smart homes come into play. The smart homes era builds on the progressing maturity of these areas and the Internet of Things evolution, adding artificial intelligence to the home automation field. Smart homes will be based on distributed multi-agent architectures to overcome technological challenges such as immature home intelligence, huge network and central server processing load; and embedded resource usage. At resent, smart homes are still in their infancy, and they only exist in the form of laboratory experiments such as living labs.
To pave the way for future smart homes, more research on distributed system architecture, smart objects, and distributed artificial intelligence frameworks in a smart home context is needed. State-of-the-art research projects have so far only shown a centralized approach. This work contributes to the field by developing a new distributed framework for smart homes, which comprises a real-time istributed system with autonomous behavior, parallel processing, context awareness, and node communication. The proposed solution takes into account significant technological challenges such as real-time learning, detection probability, battery lifetime, network communication, and embedded processing power. In particular, it introduces a novel approach to adapt and distribute the artificial intelligence to match the distributed system architecture in the smart home. A multi-agent smart object model is provided to support the artificial intelligence framework with a new distributed architecture. This model focuses on the embedded resources, the sensor frameworks, and the employed algorithms and leads to considerable savings in battery power consumption, processing resources and network load. It is part of the developed hierarchical distributed smart home system architecture which consists of a Low-Level and a High-Level Smart Home System (LL-SHS and HJ-SHS). The layout structure and architecture of this model are derived and part of it is simulated. The methodology used in this work is based on a combination of established theories, i.e., the ―hybrid imagination‖, the ―truthiness‖, and the theory of induction and deduction. These theories are combined with an iterative process model, which is used to support the research process. This research process uses: technical and mathematical analysis based on library and online searches; objects oriented process modeling; model and code implementation; and test by using empiric dataset from other independent researchers. The research results are presented in a ―research view‖ and a ―presentation view‖ which covers the research process. The proposed framework features a simplified implementation, high flexibility, learning and prediction on the fly, advanced temporal prediction, standalone capability, limited processing
resources, and easy integration with the smart objects. Significant parts of the framework are simulated to validate their performance, and it is shown that the performance is comparable to state-of-the-art smart home technologies. In a larger perspective, the proposed framework supports and facilitates the coming era of Internet of Things. The distributed approach and elements of the framework can be applied in many related areas, such as ambient-assisted living, e.g., assisting elderly people to stay longer at home, intelligent transportation systems, and many other sustainable solutions based on ICT.
- سال انتشار: جمعه, 20 دی 1392
- دانشگاه: Aalborg University
- مقطع: PhD student