"Nobody understands the cloud," shouts a character in a recent comedy about a couple trying to remove a private video from the Internet. 

In reality, the cloud is completely understandable, and it's one of few areas in climate where the emissions costs are also. And because it is quantifiable it can benefit from combinatorial optimization. the famous rucksack problem where a traveler has to try and fit everything in without leaving anything behind.

Cloud computing involves using remote servers for data storage and processing. It can provide users with more storage space and computing power and  they can access it from anywhere in the world. But environmental critics are part of the 'nobody understands the cloud' masses and worry that distributed servers running continuously, where an individual user's laptop might be shut down when it is not in use, could be harming the atmosphere.

Obviously businesses care about that too - electricity costs money as well. IT people are here to help. A group has created an algorithm to control the virtual machines running on computers in a cloud environment so that energy use of the core central processing units (CPUs) and memory capacity (RAM as opposed to hard disk storage space) can be reduced as far as possible with affecting performance overall. 

Writing in the International Journal of Information Technology, Communications and Convergence, researchers at the University of Oran in Algeria, have investigated how cloud computing systems might be optimized for energy use and to reduce their carbon footprint. 

"Energy consumption is considered as a major problem in computing systems containing servers, data centers and clouds," write Jouhra Dad and Ghalem Belalem from the Department of Computer Science at Oran. "These resources continue to consume a large amount of energy and produce carbon dioxide emissions."

The team's study reveals that virtualization of processes and live migration of VMs within the cloud service using their algorithm of selection and allocation allows different tools and applications to be consolidated to use less CPU and memory capacity. This in turn reduces energy demands on the servers by allowing several virtual machines to be run on a single remote compute accessible to the users without compromising performance. 

To optimize the energy consumption of data centers, the proposed approach is divided into two phases. The first one is the selection of VMs using the modified minimization of migration algorithm which takes in consideration the CPU utilization and RAM capacity. The solution is based on upper and lower physical resources thresholds.

The second phase is the allocation of the migrated VMs which uses the modified multidimensional knapsack problem. This algorithm must pack in as many items as possible into a bag without exceeding a weight limit and without being forced to leave behind essential items when traveling.