IEEE Talks Big Data: Cicek Cavdar & Burak Kantarci
Dr. Cicek Cavdar and Dr. Burak Kantarci are both active in the IEEE Green ICT Initiative, which is driven, in part, by the advent of big data. Cavdar was coordinator of the project 5GrEEn: Towards Green 5G Mobile Network, now Swedish cluster coordinator of the project SooGREEN – Service Oriented Optimization of Green Mobile Networks, and a senior researcher in the Communications Systems Department at the School of ICT at KTH, the Royal Institute of Technology, Sweden. Kantarci is a senior member of IEEE and an assistant professor in the Department of Electrical and Computer Engineering at the Wallace H. Coulter School of Engineering, Clarkson University, New York. In the following Q&A they discuss drivers, implications and the future of Green ICT.
Question: What forces or developments are driving the need to develop Green ICT?
Cicek Cavdar: The growth in computing and the resulting Big Data, in general, demand it. And that growth is being accelerated by the advent of increasing data exchanges between billions of “things” rather than people. Device-to-device and machine-to-machine communications in the smart grid, in smart cities, in the Internet of Things will drive an urgent need for Green ICT.
Question: What are the implications for society and for people who are directly involved in developing Green ICT?
Cavdar: These developments create both opportunities and challenges. The opportunity to analyze Big Data for myriad insights could make data analytics the “oil of the 21st century.” The biggest challenge is to design sustainable and affordable data networks to accommodate those data flows. Sustainability is quite important. The biggest challenge, in my view, is that we need 1,000 times more network capacity in the coming 10 years, but with the same energy consumption as today. The opportunity is that ICT is being applied for greater energy efficiency in all things, and the challenge is how to make the growing ICT infrastructure more energy efficient. On the one hand, ICT will help our industries – for instance, in transportation or production – become more efficient. At the same time, ICT itself must become more energy efficient as we deploy more ICT capacity. And these ICT networks must be affordable, otherwise the mobile telecom network operators’ business models might collapse. They need to make profit while deploying higher-capacity networks. There’s also the environmental dimension. Energy consumption, in general, contributes to greenhouse gas emissions. So the carbon footprints of the networks must be reduced.
Question: The Green ICT effort, based on fundamental needs such as energy efficiency and network capacity, really affects a broad swath of modern life, doesn’t it?
Cavdar: Yes. Green ICT really presents a lot of parallel research problems that need solving. Researchers must now look more and more to the big picture. The whole topic is becoming more multi-disciplinary. We cannot solve the sustainability challenge in ICT or Big Data without considering them together. Greening ICT is one topic, but energy efficiency across industries is another topic and the two must be considered together. For instance, my own work involves the efficiency of next-generation mobile networks, but I must include energy delivery systems and smart grid in my thinking. That’s one of the objectives of the IEEE Green ICT Initiative: to be a connection point for bringing together different technical domains within IEEE, both in terms of raising awareness of the challenges in other domains and in making connections between individuals in each domain.
Question: Your research has addressed, among other topics, managed versus unmanaged systems and the implications for Green ICT and sustainable networks. Would you comment on this topic?
Cavdar: Certainly. As we move towards a system of systems, a network of networks, the distributed nature of this new paradigm makes it more unmanaged. Such a system is controlled by different entities, in different domains. We have smart power networks, smart cities, communication systems, transportation, manufacturing. These domains are all continuously growing and contributing to energy consumption. So to design a sustainable system of systems, we really need to take a holistic view across these fundamental industry verticals. Handling an unmanaged system of systems and making it sustainable is a serious and urgent challenge. Standardization will be very important but, unfortunately, multi-system standardization that leads to sustainability and energy efficiency is in its infancy, though initiatives in this area are underway.
Question: Burak, your work focuses in part on how the cloud impacts Green ICT. Would you comment on whether the cloud aids or impedes sustainability?
Kantarci: It’s a bit of both. The cloud offers a shared pool of resources to clients, which means offloading computing and storage resources to remote locations such as data centers. Data centers today are mostly run in a sustainable manner, according to current best practices, including the use of renewable energy, when available. On the other hand, offloading such services to remote locations also magnifies network traffic in the backbone, which challenges its energy efficiency. We’re re-engineering the backbone to gain more energy efficiency. New paradigms to achieve this goal include software-defined networks or network virtualization that can separate the control plane from the data transport plane. The cloud increases the affordability of its services, which drives further uptake, which increases the challenge of making the cloud more sustainable.
Question: Are there currently under-appreciated and possibly disruptive forces that could help or hurt Green ICT efforts?
Kantarci: I am working with my colleague, Dr. Silvana Andreescu, at Clarkson University in the chemistry and bio-molecular sciences department and they have developed some paper-based portable sensors that don’t consume energy. They are reusable, they last more than six months, and just based on the change in behavior of those sensors, they can detect changes in their environment. They can be interconnected via a mobile backbone, and they might be able to replace the conventional sensors used in environmental and other types of monitoring. I’m sure there are many other under-appreciated advancements that may impact Green ICT, but I’m sure the one I just mentioned will have such an impact in the future.
Question: In a sense, the Green ICT effort is a race against time. What needs to happen in the short-term, mid-term and long-term to meet the challenges to Green ICT?
Cavdar: Today’s systems were not designed with energy efficiency in mind. Performance was our target. We wanted to maximize system performance, but now sustainability has become paramount. In the short-term, we want to increase the number of functions that can go into “sleep” or “hibernation” mode. This involves modifying existing systems to make them sleep more and work more efficiently. In the long-term we want to redesign the system of systems to be intelligent, adaptive and optimized based on both performance and sustainability. The effects of this long-term strategy may vary between developed and developing countries. In industrialized nations, it’s not easy to redesign everything from scratch. But in green fields, in developing nations, it might be possible to leap-frog ahead. For instance, mobile payment systems in Sweden haven’t taken hold because the banks insist on the use of credit cards. Yet mobile payment systems took hold in Africa with unexpected swiftness.
Kantarci: I agree. Short-term goals will include energy-saving schemes in, say, data acquisition and in communications. Mid-term goals will include energy harvesting, which currently we do not do very efficiently. Long-term I think we’ll need to move towards no-power, battery-less devices. That’s my goal. Because if we succeed in connecting those no-power materials or nano/bio-sensors, that would be truly transformative in terms of its impact on Green ICT.
|Dr. Cicek Cavdar was coordinator of the project 5GrEEn: Towards Green 5G Mobile Network, now Swedish cluster coordinator of the project SooGREEN – Service Oriented Optimization of Green Mobile Networks, and a senior researcher in the Communications Systems Department at the School of ICT at KTH, the Royal Institute of Technology, Sweden.|
|Dr. Burak Kantarci is a senior member of IEEE and an assistant professor in the Department of Electrical and Computer Engineering at the Wallace H. Coulter School of Engineering, Clarkson University, New York.|