Joint optimization of VM placement and request distribution for electricity cost cut in geo-distributed data centers

The rising demand on cloud services has made the electricity cost become the main operational expenditure (OPEX) to data center providers. By exploring the geographical distribution feature of data centers and the electricity price diversity in modern multi-electricity market, data center resizing technique emerges as a promising solution to lowering the electricity cost. Since services are usually provided by leasing virtual machines (VMs) over geo-distributed data centers, the corresponding user requests must be distributed only to these VMs. This motivates us to study the electricity cost minimization problem with the joint consideration of VM placement, user request distribution and data center resizing in geo-distributed data centers with heterogeneous electricity prices. To the best of our knowledge, we are the first to study this optimization problem, which is formulated as a mixed-integer linear programming (MILP) problem and then solved by a computation-efficient heuristic algorithm in large-scale systems. The high efficiency of our proposal is validated by extensive simulation based studies.