Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item A Time Series Forecasting Approach to Minimize Cold Start Time in Cloud-Serverless Platform(Institute of Electrical and Electronics Engineers Inc., 2022) Jegannathan, A.P.; Saha, R.; Addya, S.K.Serverless computing is a buzzword that is being used commonly in the world of technology and among developers and businesses. Using the Function-As-A-Service (FaaS) model of serverless, one can easily deploy their applications to the cloud and go live in a matter of days, it facilitates the developers to focus on their core business logic and the backend process such as managing the infrastructure, scaling of the application, updation of software and other dependencies is handled by the Cloud Service Provider. One of the features of serverless computing is ability to scale the containers to zero, which results in a problem called cold start. The challenging part is to reduce the cold start latency without the consumption of extra resources. In this paper, we use SARIMA (Seasonal Auto Regressive Integrated Moving Average), one of the classical time series forecasting models to predict the time at which the incoming request comes, and accordingly increase or decrease the amount of required containers to minimize the resource wastage, thus reducing the function launching time. Finally, we implement PBA (Prediction Based Autoscaler) and compare it with the default HPA (Horizontal Pod Autoscaler), which comes inbuilt with kubernetes. The results showed that PBA performs fairly better than the default HPA, while reducing the wastage of resources. © 2022 IEEE.Item Shipping code towards data in an inter-region serverless environment to leverage latency(Springer, 2023) Sethi, B.; Addya, S.K.; Bhutada, J.; Ghosh, S.K.Serverless computing emerges as a new standard to build cloud applications, where developers write compact functions that respond to events in the cloud infrastructure. Several cloud service industries started adopting serverless for deploying their applications. But one key limitation in serverless computing is that it disregards the significance of data. In the age of big data, when applications run around a huge volume, to transfer data from the data side to the computation side to co-allocate the data and code, leads to high latency. All existing serverless architectures are based on the data shipping architecture. In this paper, we present an inter-region code shipping architecture for serverless, that enables the code to flow from computation side to the data side where the size of the code is negligible compared to the data size. We tested our proposed architecture over a real-time cloud platform Amazon Web Services with the integration of the Fission serverless tool. The evaluation of the proposed code shipping architecture shows for a data file size of 64 MB, the latency in the proposed code shipping architecture is 8.36 ms and in existing data shipped architecture is found to be 16.8 ms. Hence, the proposed architecture achieves a speedup of 2x on the round latency for high data sizes in a serverless environment. We define round latency to be the duration to read and write back the data in the storage. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item ESMA: Towards elevating system happiness in a decentralized serverless edge computing framework(Academic Press Inc., 2024) Datta, S.; Addya, S.K.; Ghosh, S.K.Due to the rapid growth in the adoption of numerous technologies, such as smartphones and the Internet of Things (IoT), edge and serverless computing have started gaining momentum in today's computing infrastructure. It has led to the production of huge amounts of data and has also resulted in increased network traffic, which if not managed well can cause network congestion. To address this and maintain the quality of service (QoS), in this work, a novel dispatch (destination selection) algorithm called Egalitarian Stable Matching Algorithm (ESMA) for faster data processing has been developed while also considering the best use of server resources in a decentralized Serverless-Edge environment. This will allow us to effectively utilize the enormous volumes of data that are generated. The proposed algorithm has been able to achieve lower overall dissatisfaction scores for the entire system. Individually, the client's happiness as well as the server's happiness have improved over the baseline. Moreover, there has been a drop of 25.7% in the total execution time and the total network resources consumed are lower as compared to the baseline algorithm as well as random-allocation algorithm. © 2023 Elsevier Inc.Item FASE: fast deployment for dependent applications in serverless environments(Springer, 2024) Saha, R.; Satpathy, A.; Addya, S.K.Function-as-a-service has reduced the user burden by allowing cloud service providers to overtake operational activities such as resource allocation, service deployment, auto-scaling, and load-balancing, to name a few. The users are only responsible for developing the business logic through event-triggered functions catering to an application. Although FaaS brings about multiple user benefits, a typical challenge in this context is the time incurred in the environmental setup of the containers on which the functions execute, often referred to as the cold-start time leading to delayed execution and quality-of-service violations. This paper presents an efficient scheduling strategy FASE that uses a finite-sized warm pool to facilitate the instantaneous execution of functions on pre-warmed containers. Test-bed evaluations over AWS Lambda confirm that FASE achieves a 40% reduction in the average cold-start time and 1.29× speedup compared to the baselines. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.Item RUSH: Rule-Based Scheduling for Low-Latency Serverless Computing(Institute of Electrical and Electronics Engineers Inc., 2025) Birajdar, P.A.; Anchalia, K.; Satpathy, A.; Addya, S.K.Serverless computing abstracts server management, enabling developers to focus on application logic while benefiting from automatic scaling and pay-per-use pricing. However, dynamic workloads pose challenges in resource allocation and response time optimization. Response time is a critical performance metric in serverless environments, especially for latency-sensitive applications, where inefficient scheduling can degrade user experience and system efficiency. This paper proposes RUSH (Rule-based Scheduling for Low-Latency Serverless Computing), a lightweight and adaptive scheduling framework designed to reduce cold starts and execution delays. RUSH employs a set of predefined rules that consider system state, resource availability, and timeout thresholds to make proactive, latency-Aware scheduling decisions. We implement and evaluate RUSH on a real-world serverless application that generates emoji meanings. Experimental results demonstrate that RUSH consistently outperforms First-Come-First-Served (FCFS), Random Scheduling, and Profaastinate, achieving ? 33% reduction in average execution time. © IEEE. 2019 IEEE.Item DCRDA: deadline-constrained function scheduling in serverless-cloud platform(Springer, 2025) Birajdar, P.A.; Meena, D.; Satpathy, A.; Addya, S.K.The serverless computing model frees developers from operational and management tasks, allowing them to focus solely on business logic. This paper addresses the computationally challenging function-container-virtual machine (VM) scheduling problem, especially under stringent deadline constraints. We propose a two-stage holistic scheduling framework called DCRDA targeting deadline-constrained function scheduling. In the first stage, the function-to-container scheduling is modeled as a one-to-one matching game and solved using the classical Deferred Acceptance Algorithm (DAA). The second stage addresses the container-to-VM assignment, modeled as a many-to-one matching problem, and solved using a variant of the DAA, the Revised-Deferred Acceptance Algorithm (RDA), to account for heterogeneous resource demands. Since matching-based strategies require agent preferences, a Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) ranking mechanism is employed to prioritize alternatives based on execution time, deadlines, and resource demands. The primary goal of DCRDA is to maximize the success ratio (SR), defined as the ratio of functions executed within the deadline to the total functions. Extensive test-bed validations over commercial providers such as Amazon EC2 show that the proposed framework significantly improves the success ratio compared to baseline approaches. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.