Search

Fog computing has the capability to provide computing resources to end-to-end devices like Internet-of-Things (IoT), thereby reducing the burden on the cloud. However, due to the growth of IoT devices and an increase in resource consumption, load balancing in fog computing has turned into a challenging task, since improper load allocation may result in underutilization and overutilization while transferring the tasks from one node to another. In order to solve these challenges, we presented an Energy-efficient load balancing algorithm named Hybrid Priority Assigned Laxity (HPAL) algorithm that allocates the tasks to a suitable Virtual Machine (VM) and completes the task within the minimum time. After the task allocation, the load balancing is handled by calculating the fog optimal time and minimum execution time. Response Time (RT), Processing Time (PT), Delay Time (DT), Execution Time (ET) and Energy Consumption (EC) are the five factors considered in this work to design an energy-efficient load balancing in Fog Nodes (FNs). The proposed algorithm carries two phases, among which in the first phase the task is allocated to each VM according to priority within the fog optimal time and in the second phase, the reallocation of tasks is executed within the minimum execution time considering the energy factor. Therefore, the task migration between the FNs is handled in an energy-efficient manner without affecting the lifetime of the FNs. [ABSTRACT FROM AUTHOR]

This research work presents an exploratory study to find answers for managing traffic and payloads in edge/fog zone of the networks. Initial deployments have shown that edge computing has helped in fine grain customization of services and have produced better experiences for the users. However, at the same time, it also invites challenges such as overload, underload and imbalance in utilization of resources such as bandwidth, time responses, throughput etc. The main reason is highly constrained environment and restricted hardware capabilities of fog devices. The conventional algorithms, that work on finding the best routing paths for distributing and processing tasks, do not suffice with respect to Quality of Service (QoS) parameters of fog zone as their computations become unstable. An alternative approach is considered by adding software defined components, that can help in load balancing and managing the payloads using link analysis at the inter-nodes of cloud and fog zone. In this research work, a fuzzy load balancer is devised using different levels of design and tuning of fuzzy controls. This fuzzy logic based algorithm has been implemented for conducting link analysis as interconnects for managing traffic. The analysis shows that 3-level design is energy efficient for load balancing in fog zone due to reduced number of intervals in fuzzy design, reduced overhead in provisioning and improved responsiveness. Higher levels (5-level and 7-level) lead to creation of redundant fuzzy rules and wastage of resources. [ABSTRACT FROM AUTHOR]