Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Machine Learning Powered Autoscaling for Blockchain-Based Fog Environments(Springer Science and Business Media Deutschland GmbH, 2022) Martin, J.P.; Joseph, C.T.; Chandrasekaran, K.; Kandasamy, A.Internet-of-Things devices generate huge amount of data which further need to be processed. Fog computing provides a decentralized infrastructure for processing these huge volumes of data. Fog computing environments provide low latency and location-aware alternative to conventional cloud computing by placing the processing nodes closer to the end devices. Co-ordination among end devices can become cumbersome and complex with the increasing amount of IoT devices. Some of the major challenges faced while executing services in the fog environment is the resource provisioning for the user services, service placement among the fog devices and scaling of fog devices based on the current load on the network. Being a decentralized infrastructure, fog computing is vulnerable to external threats such as data thefts. This work presents a blockchain based fog framework for making autoscaling decisions with the use of machine learning techniques. Evaluation is done by performing a series of experiments that show how the services are handled by the fog framework and how the autoscaling decisions are made. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Adaptive Workload Management for Enhanced Function Performance in Serverless Computing(Association for Computing Machinery, Inc, 2025) Birajdar, P.A.; Harsha, V.; Satpathy, A.; Addya, S.K.Serverless computing streamlines application deployment by removing the need for infrastructure management, but fluctuating workloads make resource allocation challenging. To solve this, we propose an adaptive workload manager that intelligently balances workloads, optimizes resource use, and adapts to changes with auto-scaling, ensuring efficient and reliable serverless performance. Preliminary experiments demonstrate an ≈ 0.6X% and 2X% improvement in execution time and resource utilization compared to the First-Come-First-Serve (FCFS) scheduling algorithm. © 2025 Copyright held by the owner/author(s).Item ARIMA-PID: container auto scaling based on predictive analysis and control theory(Springer, 2024) Joshi, N.S.; Raghuwanshi, R.; Agarwal, Y.M.; Annappa, B.; Sachin, D.N.Containerization has become a widely popular virtualization mechanism alongside Virtual Machines (VMs) to deploy applications and services in the cloud. Containers form the backbone of the modern architectures around microservices and provide a lightweight virtualization mechanism for IoT and Edge systems. Elasticity is one of the key requirements of modern applications with various constraints ranging from Service Level Agreements (SLA) to optimization of resource utilization, cost management, etc. Auto Scaling is a technique used to attain elasticity by scaling the number of containers or resources. This work introduces a novel mechanism for auto-scaling containers in cloud environments, addressing the key elasticity requirement in modern applications. The proposed mechanism combines predictive analysis using the Auto-Regressive Integrated Moving Average (ARIMA) model and control theory utilizing the Proportional-Integral-Derivative (PID) controller. The major contributions of this work include the development of the ARIMA-PID algorithm for forecasting resource utilization and maintaining desired levels, comparing ARIMA-PID with existing threshold mechanisms, and demonstrating its superior performance in terms of CPU utilization and average response times. Experimental results showcase improvements of approximately 10% in CPU utilization and 30%. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.