No abstract

No abstract

Energy-saving offices require autonomous and optimised control of integrated devices and appliances with the objective of saving energy while the occupant comfort and productivity are preserved. We propose an approach that analyses and controls an office space and accounts for the objectives of energy-saving offices. The approach considers ontology-based occupant activity recognition using simple sensors to process the context information, and employs Artificial Intelligence planning to control appliances. The approach is evaluated in a semisimulated setting. The activity recognition strategy is tested in an actual living lab and shows recognising accuracy of about 80%. The planning technique is able to cope efficiently under a simulated and increasing number of offices and recognised activities. The overall solution shows intriguing potential for energy saving in the order of 70%, given mostly sunny days and a provisional set of devices for experimentation.

The goal of ubiquitous computing is to create ambience in which one’s experiences and quality of life are improved by monitoring and assisting people using ubiquitous technologies and computation in coherence. The continuous advancements of involved technologies, such as wireless communications, mobile devices, and sensors, imply fast evolution of ubiquitous computing environments too. The complexity of these environments is reaching a point where traditional solutions simply no longer work. The environments are in need of computational techniques that can deal with the evolution and uncertainty of ubiquitous computing environments dynamically and automatically. Artificial Intelligence (AI) can contribute towards satisfying this future scenario in many ways, while numerous approaches inspired by work in the AI planning community have already been designed for ubiquitous computing. We devote this study to investigate the current progress of AI planning for ubiquitous computing by analysing those approaches. We rigorously search for and select relevant literature out of which we extract qualitative information. Using the extracted qualities, we derive a generic framework that consists of aspects important to planning for ubiquitous computing. The framework’s main purpose is to facilitate the understanding of those aspects, and classify the literature according to them. We then analyse the literature in a consolidated way, and identify future challenges of planning for ubiquitous computing.

No abstract