I am posting the following announcement on behalf of Prof. Ishfaq Ahmad in the Computer Science Engineering Department.
Large-scale computer systems and data centers consume substantial amounts of electric energy. Their power and cooling costs are becoming comparable to the cost of their acquisitions. Energy is one of the most valuable and scarce resources available to humanity, a substantial portion of which is now being consumed to power up computers and their accessories. Massive energy consumption is an escalating threat to the environment. The explosive growth in computing is leading to rapidly increasing consumption of precious natural resources such as oil and coal, strengthening the looming danger of an energy shortage. Recent studies have reported that computers consume close to 4% of the total energy produced and this fraction is growing. One can systematically shut down or slow down such systems to save energy, but this can reduce their quality of service and performance.
In the Computer Science and Engineering Department, our group is engaged in research to design intelligent software that will allow computers to become self optimizing by determining their own speed and energy requirements. Incorporating these efficient software techniques in the operating system will allow a computer to determine an optimum balance between energy saving and good performance. The quality of service can be different for different applications. Sometimes the computing tasks may be more urgent and time critical (e.g., health and security applications). Sometimes there are computing jobs that are not so urgent. Similarly, there can be energy shortages or budgetary constraints. We are developing techniques that will enable large-scale computers and data centers to handle such scenarios by finding the required tradeoffs between performance and energy requirements under a given situation. Such software solutions can assist IT organizations to better support their users while reducing energy costs. Hence, our work has tremendous potential for an economic, environmental, and societal impact.
Large-scale computers and data centers are complex systems and consist of several design layers. At the lowest level are the building blocks, such as processors, while a network of computers with disks and other peripheral devices form a high level layer. Efficient control mechanisms are required at all of these levels. We have several projects funded by the National Science Foundation and Semiconductor Research Corporation. One project addresses the problem at the system level while another project is focused at the processor level. We are seeking new research funding that will enable us to develop smart software that will use a holistic approach to enhance energy saving without performance degradation at all levels of a complex computer system.
We also are initiating new courses on related topics and are developing relevant tutorials for conferences and industrial workshops, which will help to create awareness and educate a large audience on a critically important research topic. Green computing is a new research direction in computer science and engineering, creating a fresh area of knowledge. To support such research activities, UT Arlington is a co-sponsor of the First International Green Computing Conference (http://www.green-conf.org/) to be held in Chicago this August. The conference addresses key issues and topics related to energy efficiency in computing and promoting environmentally friendly computer technologies and systems. The conference aims to provide a forum to a wide audience for discussing, sharing and investigating the state-of-the-art for all aspects of green computing, which include energy-efficient use of computers, design of algorithms and systems for environmentally friendly computer technologies, and a wide range of related topics. The conference will publish papers pertaining to hardware and software systems, algorithms, and applications as well as power, energy and temperature related research areas of current importance to researchers, engineers and practitioners. The conference will hold forums and workshops on hot topics related to how the carbon footprint of computing can be reduced and how computers can contribute to the environment and overall well being of the planet.