MOVE: Matching Game for Partial Offloading in Vehicular Edge Computing
This paper introduces a cooperative offloading scheme using matching-theory, enabling vehicles and RSUs to execute computations with deadline constraints.
Clicking on any of the links below will redirect you to the abstract and details of my contributions.
This paper introduces a cooperative offloading scheme using matching-theory, enabling vehicles and RSUs to execute computations with deadline constraints.
This paper introduces a framework POSCA aimed at meeting the energy requirements of UAM flights.
This work introduces EFraS (Emulated Framework for Dynamic VNE Strategies over SDN) with the goal of aiding the developers and researchers in iterating, testing, and evaluating VNE solutions seamlessly, leveraging a modular design and customized reconfigurability.
This paper proposes a framework LEASE that dynamically schedules resources in serverless functions catering to different microservices and adhering to their deadline constraint.
This paper proposes an offloading solution abstracted as a one-to-many matching game between two sets of entities - tasks and fog nodes (FNs) by considering preferences of both the emtities obtained via AHP.
This work discusses a binary offloading scheme for fog networks using matching theory. The preferences are generated using Analytic Hierarchy Process (AHP) followed by the deferred acceptance algorithm (DAA)-based stable assignment.
This work studies the performance of spot instances via rigorous experimentation over commercial SPs such as Amazon AWS and Microsoft Azure. Real-world evaluations affirm that spot instances perform poorly compared to their on-demand counterpart concerning memory, CPU, disk read, and write operations.
This work presents an efficient scheduling strategy FASE that takes advantage of a finite-sized warm pool to facilitate the instantaneous execution of functions on pre-warmed containers.
Develops a VM migration model called Low Energy Application Workload Migration (LEWAM) aimed at reducing the per-bit migration cost in migrating VMs over Geo-distributed clouds. With a Geo-distributed cloud-connected through multiple ISPs, the work develops an approach to find out the migration path across ISPs leading to the most feasible destination.
Developed a matching theory-based protocol A-DAFTO that generates an offloading plan which distributes the network and computational load at the FNs respecting the application’s deadline.
Developed a topology-aware and efficient virtual network embedding strategy to maximize the revenue-to-cost and embedding ratio.
This paper discusses a framework MatchVNE that is focused on maximizing the revenue-to-cost ratio of virtual networks by considering a blend of system and topological attributes that better capture the inherent dependencies among the virtual machines.
This paper discusses a proposes a relaxed resources sharing model for the service providers called cloud federation-alliance.
Developed a one-to-many matching framework with dynamic preferences to relocate virtual data center requests experiencing fluctuating resource demands over an interconnected substrate network.
Developed a matching theory-based framework with static prefernces to relocate dynamic virtual data center requets over a geo-distributed substrate network.
This work presents an effective strategy to offload computations of resource-constrained IoT devices to nearby fog nodes (FNs) to reduce the total offloading delay and achieve a balanced assignment across FNs using a matching game with minimum quotas.
Proposed a multi-cloud broker model that selects a sub-optimal virtual machine coalition for multi-tier applications from an service provider catering to minimum coalition pricing and maximum quality-of-service for end users.
This paper proposes a student project allocation (SPA) based efficient task offloading strategy that considers multiple parameters of stakeholders and aims to reduce the offloading energy and latency in a complex IoT Fog network.
This work proposes a modified serial migration strategy to schedule multiple virtual machines (VMs) migration based on the pre-copy live migration technique aimed at reducing migration overheads in terms of migration time and downtime.
Discussed a meta-heuristic inspired crow search algorithm-based task scheduling strategy to reduce the makespan for heterogeneous tasks onto virtual machines in cloud environments.
This paper discusses a service matching technique for a multi-cloud marketplace using a revised deferred acceptance algorithm.
In this work, we propose a dynamic resource reconfiguration strategy called that generates an efficient relocation/remapping plan for already assigned virtual links (VLs) facing bandwidth expansion.
This paper discusses an effective IoT offloading strategy for a densely connected IoT-Fog network that aims to reduce the total system energy and number of outages (number of tasks exceeding the deadline) in polynomial time.
This book chapter evolution of cloud networks starting from the traditional virtual machine (VM) based offerings to a more complex model that involves a fruitful interplay between the stratums.
This research presents a complete re-embedding strategy for dynamic virtual data center requests over a geo-distributed infrastructure. The primary goal of the work is to minimize the re-embedding cost and migration overhead.
This work propose an architecture for federated Infrastructure-as-a-service (IaaS) provisioning with the help of a completely decentralized marketplace designed using the blockchain technology.
This paper proposes a virtual machine (VM) migration model to reduce power consumption while migrating a set of VMs over geo-distributed clouds. As a solution strategy, we adopt an Ant Colony Optimization (ACO) inspired solution approach and formulate the overall problem as a bi-objective optimization that strikes a balance between the power consumption and the migration time to make the implementation realistic.
This paper discusses a multi-cloud broker environment to select an optimal VM coalition for multi-tier applications from an SP with minimum coalition pricing and better quality of service. The coalition formation problem is modeled as a bi-objective optimization and is solved using an ant-colony meta-heuristic.
This work discusses a two-tier virtual machine (VM) placement strategy. Firstly, a queueing structure is discussed to process and schedule the VMs. Secondly, a multi-objective VM placement algorithm inspired by crow search to reduce resource wastage and power consumption at the data centers is also presented.
Developed a framework for secure live migration of virtual machines (VMs) in a cloud federation. Costs associated with the migration were analyzed for serial, parallel, and improved serial migration strategies.
This work discusses a cooperative game to estimate the price users would pay for their requested virtual machines (VMs) under a collaborative environment. Shapley value estimates the fraction of capital expenditure included in the VM price. For evaluation, VM configurations and pricing of popular CSPs-Microsoft Azure and Amazon EC2-are considered.