| Abstrakt: |
Fog computing (FC) is the technology which is placed in-between cloud server and the end user. It is a virtualization technology that processes Internet of Things (IoT) applications at the network's edge. It pretends to share the storage and computing resources. Recently, usage of IoT application from people side is increased. The advantage of this applications is access from anywhere at any time. And the number of request from end user is expanded. However, Fog computing has been faced many challenges as energy constraints, latency and adaption to failure. Plethora of load balancing strategies was proposed in cloud computing, but they are still not works effectively. In this paper load balancing and offloading strategy (LBS-AO) using resource allocation method based on deep learning with adam optimizer algorithm is proposed. LBS-AO is collects the information about the traffic which is occurs in network. The proposed system is manage the work flow from the collected information about load of server's incoming request and distributes the load over the heterogeneous fog server that is fog –to-fog distribution to balance the server load. Hence, it improves the performance when conjunction occurs. According to the system LBS-AO, is efficient in real-time applications like Health care system, Call centers and IOT-fog based applications. The proposed systems focused on three layers named cloud layer, fog layer and end user layer (IoT). Finally, the proposed system carried out the results as effective quality-of-service (QoS) in virtual environment in terms of improving resource allocation and reduces energy constraints upto 35% than the older techniques. Comparing the existing technology with proposed system, LBS-AO is the effective load balancing strategy. Hence, LBS-AO is the best strategy for load balancing in virtualization environment. [ABSTRACT FROM AUTHOR] |
