With the increasing expansion of cloud data centers and the demand for cloud services, one of the major problems facing these data centers is the “increasing growth in energy consumption ". In this paper, we propose a method to balance the burden of virtual machine resources in order to reduce energy consumption. The proposed technique is based on a four-adaptive threshold model to reduce energy consumption in physical servers and minimize SLA violation in cloud data centers. Based on the proposed technique, hosts will be grouped into five clusters: hosts with low load, hosts with a light load, hosts with a middle load, hosts with high load and finally, hosts with a heavy load. Virtual machines are transferred from the host with high load and heavy load to the hosts with light load. Also, the VMs on low hosts will be migrated to the hosts with middle load, while the host with a light load and hosts with middle load remain unchanged. The values of the thresholds are obtained on the basis of the mathematical modeling approach and the 𝐾-Means Clustering Algorithm is used for clustering of hosts. Experimental results show that applying the proposed technique will improve the load balancing and reduce the number of VM migration and reduce energy consumption.

Accelerated multi-armed bandit (MAB) model in Reinforcement-Learning for on-line sequential selection problems is presented. This iterative model utilizes an automatic step size calculation that improves the performance of MAB algorithm under different conditions such as, variable variance of reward and larger set of usable actions. As result of these modifications, number of optimal selections will be maximized and stability of the algorithm under mentioned conditions may be amplified. This adaptive model with automatic step size computation may attractive for on-line applications in which,  variance of observations vary with time and re-tuning their step size are unavoidable where, this re-tuning is not a simple task. The proposed model governed by upper confidence bound (UCB) approach in iterative form with automatic step size computation. It called adaptive UCB (AUCB) that may use in industrial robotics, autonomous control and intelligent selection or prediction tasks in the economical engineering applications under lack of information.

Current algorithms for solving multi-armed bandit (MAB) problem in stationary observations often perform well. Although this performance may be acceptable with accurate parameter settings, most of them degrade under non stationary observations. We setup an incremental ε-greedy model with stochastic mean equation as its action-value function which is more applicable to real-world problems. Unlike the iterative algorithms suffering from step size dependency, we propose an adaptive step-size model (ASM) to introduce adaptive MAB algorithm. The proposed model employs ε-greedy approach as action selection policy. In addition, a dynamic exploration parameter ε is introduced to be ineffective by increasing decision maker's intelligence. The proposed model is empirically evaluated and compared with existing algorithms including the standard ε-greedy, Softmax, ε-decreasing and UCB-Tuned models under stationary as well as non stationary situations. ASM not only addresses concerns in parameter dependency problem but also performs either comparable or better than mentioned algorithms. Applying these enhancements to the standard ε-greedy reduce the learning time which is more attractive to the wide range of on-line sequential selection-based applications such as autonomous agents, adaptive control, industrial robots and forecasting trend problems in management and economics domains.