Review On Optimal Mathematical Workload Allocation Models In Energy Consumption Using Fog-Cloud Networks

This paper provides information regarding different approaches in terms of energy consumption and delay in transmission which helps in finding out the optimized solution over fog-cloud networks. As we are very much familiar about the concept of cloud and fog computing which holds huge amount of data via different routing protocol and many other sources. Also, there is increase in need of localized services of mobile users. For such cases, we have insufficient in cloud resources which motivates the access of fog based computing these days. It provides the resources locally to the users which pre-stores data used in cloud and then distributes to the end users with fast-rate. Generally, routing of data consumes lots of energy or power because it follows the concept of packet forwarding through various intermediate networking nodes in a systematic manner. There are several factors and metrics which helps in optimizing power consumption for routing activity as provided minimum of the power and delay. The paper includes introduction of basic concept of minimization of energy consumption and margin in fog- cloud networks and discuss about some more optimized techniques to simplify the results. Also, we developed a problem based on workload allocation which suggests the best way to allocate workload in between the fog-cloud networks by considering minimum energy consumption with the specific constrained service delay. For better simulation, the mentioned problem can be divided in to three sub problems relative to subsystems. Each sub problem can be solved individually by considering some networking constraints and after that we combine three subsystems and get the minimized results in terms of energy consumption and delay in transmission. We use primal problem using approximation method in this case. Finally, we propose some more modified techniques by considering previous simulations and numerical results so that we can get more accuracy in results. This helps in saving of communication bandwidth, improvement in performance of fog and cloud computing.