Towards a Self-managing Tool for Optimizing Energy Usage in Buildings Naveed Arshad, Fahad Javed and Muhammad Dawood Liaqat Abstract Smart grid is the next generation of electricity generation, transmission and distribution technology. A major component of smart grid is an overlay commu- nication network for two-way communication between the power providers and the customers. With this feature smart grid provides exciting new ways of energy man- agement and conservation. One of ways to conserve energy using a smart grid is to control and optimize energy usage in buildings. Buildings consume more than one third of the energy produced in the world. Therefore, conserving energy in buildings is cited as the “most important fuel” in energy generation. To this end, we have de- veloped a self-managing approach to optimize energy usage in buildings. We have evaluated our approach using a software tool called Power Conservation Analysis Tool (PCAT). Our initial results using PCAT show upto 38% savings in the energy bills of customers that could directly translates into reduction in energy production costs for power producers. Key words: optimization, energy usage, self-managing tool 1 Introduction With global warming and impending scarcity of fossil fuel, cleaner sources and bet- ter utilization of energy has been considered as a major goal for future technology advancements and research. Energy conservation has been cited as the ’most impor- tant fuel’ in energy generation [1], [10]. Correspondingly, the smart grid provides a number of ways to conserve energy. One of the ways in which a smart grid provides energy savings is through Advanced Metering Infrastructure (AMI). Through an AMI the energy usage in buildings is monitored through smart meters that are capa- ble of communicating with the smart grid in real time. Electric devices in buildings are connected through a home area network (HAN) using standards such as Zig- bee [18], wi-fi, radio or other communication protocols, thus making it possible for Naveed Arshad, Fahad Javed and Muhammad Dawood Liaqat Department of Computer Science, LUMS School of Science and Engineering, Lahore, Pakistan, e-mail: naveedarshad, fahadjaved, dawoodliaqat at lums.edu.pk 1