Multiple context based service scheduling for balancing cost and benefits of mobile users and cloud datacenter supplier in mobile cloud

Load-Balancing for Edge QoE-Based VNF Placement for OTT Video Streaming

“…Throughput and other resource-based strategies also show good performance especially for scenarios where the systems are optimized for prioritized user schemes. The scaling algorithms that proposed by Kesevaraja et al [23] & Chunlin et al [24] show similar performance as network oriented throughput-based algorithms, however, they lack to meet the demand of a QoE related degradation.…”

“…Cooling down strategy of an online video delivery system is as important as the warming up because this is one of the main parameters that the success rate of this implementation defines the budget estimation. In terms of cooling down, random-access shows the worst performance along with Chunlin et al [24] and QoE based scaling, as shown in Figure 3. That occurs due to the fact that average number of users that are connected to an instance can not be zero while the VMs are instantiated.…”

“…Kesevaraja et al have modeled [23] single VM instance taking into account the success rate of a physical node, current utilization of the processor, the maximum capacity of the processor,, current utilization of primary memory, maximum available capacity of primary memory, the data bits transferred among time interval and the network bandwidth. Chunlin et al have proposed multiple contextbased service-scheduling models [24] that adopt network utility maximization framework to maximize total system utility. When the mobile device application's job is accepted by the cloud system, it is scheduled and assigned to the cloud resource.…”

“…In terms of costs, although Kesevaraja et al [23] & Chunlin et al [24] show good performance along with throughput and resource-based scaling strategies while cooling down, still, a conspicuous QoE degradation takes place during some of the VM termination incidents.…”

Cost-aware scheduling for ensuring software performance and reliability under heterogeneous workloads of hybrid cloud

“…Many researchers have studied the scheduling problems in hybrid clouds, some of which are designed to meet deadlines and cost constraints (Zuo et al 2017;Clemente-Castelló et al 2017;Chopra and Singh 2013;Abdi et al 2017;Zhang et al 2016;Genez et al 2013;Qiu et al 2015;Shao et al 2019;Chunlin et al 2017). The comparison of the cost in existing research about hybrid cloud scheduling is shown in Table 1.…”