Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item LitE: Load Balanced Virtual Data Center Embedding for Energy Efficiency in Data Centers(Association for Computing Machinery, Inc, 2025) Preetham, N.; Addya, S.K.; Keerthan Kumar, K.K.; Hegde, S.Network virtualization (NV) enables efficient management of physical network (PN) resources by partitioning them into virtual data center requests (VDCRs), consisting of interconnected virtual machines (VMs) and virtual links (VLs). A key challenge in NV is virtual data center embedding (VDCE), which allocates PN resources to VMs and VLs and is -hard problem. Existing VDCE strategies often fail to balance energy efficiency and resource distribution, leading to sub-optimal solutions with higher energy consumption in data centers (DCs). This work presents LitE, a load-balanced VDCE strategy focused on minimizing energy consumption in single-domain PN. LitE uses a resource management strategy that considers server utilization, overloading probability, and energy consumption to select suitable servers for VM embedding. It then applies Dijkstra's shortest path algorithm for VL embedding to optimize energy use. Experiments show LitE improves energy efficiency by compared to baseline methods through better resource utilization. © 2025 Copyright held by the owner/author(s).Item EFraS: Emulated framework to develop and analyze dynamic Virtual Network Embedding strategies over SDN infrastructure(Elsevier B.V., 2024) Keerthan Kumar, K.K.; Tomar, S.; Addya, S.K.; Satpathy, A.; Koolagudi, S.G.The integration of Software-Defined Networking (SDN) into Network Virtualization (NV) significantly enhances network management, isolation, and troubleshooting capabilities. However, it brings forth the intricate challenge of allocating Substrate Network (SN) resources for various Virtual Network Requests (VNRs), a process known as Virtual Network Embedding (VNE). It encompasses solving two intractable sub-problems: embedding Virtual Machines (VMs) and embedding Virtual Links (VLs). While the research community has focused on formulating embedding strategies, there has been less emphasis on practical implementation at a laboratory scale, which is crucial for comprehensive design, development, testing, and validation policies for large-scale systems. However, conducting tests using commercial providers presents challenges due to the scale of the problem and associated costs. Moreover, current simulators lack accuracy in representing the complexities of communication patterns, resource allocation, and support for SDN-specific features. These limitations result in inefficient implementations and reduced adaptability, hindering seamless integration with commercial cloud providers. To address this gap, this work introduces EFraS (Emulated Framework for Dynamic VNE Strategies over SDN). The goal is to aid developers and researchers in iterating, testing, and evaluating VNE solutions seamlessly, leveraging a modular design and customized reconfigurability. EFraS offers various functionalities, including generating real-world SN topologies and VNRs. Additionally, it integrates with a diverse set of evaluation metrics to streamline the testing and validation process. EFraS leverages Mininet, Ryu controller, and OpenFlow switches to closely emulate real-time setups. Moreover, we integrate EFraS with various state-of-the-art VNE schemes, ensuring the effective validation of embedding algorithms. © 2024 Elsevier B.V.Item DBNLP: detecting bias in natural language processing system for India-centric languages(Springer Science and Business Media B.V., 2025) Keerthan Kumar, K.K.; Mendke, S.; Parihar, R.; Mayya, S.; Venkatesh, S.; Koolagudi, S.G.Natural language processing (NLP) is gaining widespread interest and seeing advancements rapidly due to its attractive and exhilarating applications. NLP models are being developed in search engines for real-world scenarios such as language translation, sentiment analysis, chat-bots such as ChatGPT, and auto-completion. These models are trained on a vast corpus of online data, exposing them to harmful biases and stereotypes towards various communities. The models learn these biases, making harmful and undesirable predictions about particular genders, religions, races, and professions. Biases in NLP systems can perpetuate societal biases and discrimination, leading to unfair and unequal treatment of individuals or groups. It is crucial to identify these biases, which will help mitigate them. Most of the literary works in this area have been primarily Western-centric, focusing on the English language, making it tough to use them for Indian models and languages. In this work, we propose a model called Detecting Bias in Natural Language Processing System for India-Centric Languages (DBNLP), which aims to identify the biases relevant to the Indian context present in the text-based language models, particularly for the English and Hindi languages. The DBNLP presents three techniques for bias identification based on (1) a Context Association Test (CAT), (2) a template-based perturbation technique for various co-domain associations, and (3) a co-occurrence count-based corpus analysis technique. Further, this work showcases how India-centric models such as IndicBERT, MuRIL, and datasets such as IndicCorp are biased toward various demographic categories. Detecting bias in natural language processing systems for India-centric languages is essential to creating fair, diverse, and inclusive models that benefit society. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.Item TReB: Task dependency aware-Resource allocation for Internet of Things using Binary offloading(Elsevier B.V., 2025) Soni, P.; Hajare, A.G.; Keerthan Kumar, K.K.; Addya, S.K.The rapid growth of Internet of Things (IoT) applications in domains such as healthcare, smart homes, and autonomous vehicles has led to an exponential increase in data generated by compute intensive tasks. Efficiently offloading these tasks to nearby computational resources in fog environments remains a significant challenge due to the inherent heterogeneity and constrained resources of Fog Nodes (FNs). Most of the existing approaches fail to address the trade-offs between latency, energy, and resource utilization, particularly when managing dependent and independent task workloads. Moreover, establishing an offloading strategy within a densely interconnected IoT network is known to be NP-hard. To overcome these limitations, in this work, we propose a Task dependency-Aware Resource allocation for IoT using Binary offloading (TReB) framework by considering both independent and dependent tasks of IoT applications. The TReB utilizes the Analytic Hierarchy Process (AHP) technique to generate the preferences of FNs and tasks by considering diverse attributes. With preferences established, a binary offloading is handled through a one-to-many matching procedure, utilizing a Deferred Acceptance Algorithm (DAA). It allows TReB to jointly minimize system energy consumption, latency, and the number of outages in an IoT network. We evaluated the effectiveness of TReB through simulation experiments, and results show that the proposed approach achieves a 49.1%, 62.4%, and 41.7% minimization in overall system latency, energy, and outages compared to the existing baselines. © 2025 Elsevier B.V.