Browsing by Author "Mallik, A."

Now showing 1 - 4 of 4

A novel proposal to effectively combine multipath data forwarding for data center networks with congestion control and load balancing using Software-Defined Networking Approach
(Institute of Electrical and Electronics Engineers Inc., 2014) Mallik, A.; Hegde, S.
Modern data center networks (DCNs) often use multi-rooted topologies, which offer multipath capability, for increased bandwidth and fault tolerance. However, traditional routing algorithms for the Internet have no or limited support for multipath routing, and cannot fully utilize available bandwidth in such DCNs. As a result, they route all the traffic through a single path, and thus form congestion. Multipath (MP) routing might be a good alternative, but is not sufficient alone to handle congestion that comes from the contention of end stations. Dynamic load balancing, on the other hand, protects the network from sudden congestions which could be caused by load spikes or link failures. However, little work has been done to incorporate all these features in a single and comprehensive solution for Data Center Ethernet (DCE). In this paper, we propose a novel method that attempts to integrate dynamic load balancing, multi-path scheme with congestion control (CC), with the use of pure Software-Defined-Networking (SDN) approach. SDN decouples control plane from the data forwarding plane, which reduces the overheads of the network switches. The major objectives that our solution attempts to achieve are, efficient utilization of network resources, high throughput and minimal frame loss. Â© 2014 IEEE.
A Survey ofÂ Hyperparameter Selection Methods forÂ Weather Forecasting Using State-of-the-Art Machine Learning Algorithms
(Springer Science and Business Media Deutschland GmbH, 2025) Sen, A.; Sen, U.; Paul, M.; Sutradhar, A.; Vankala, T.N.; Mallick, C.; Mallik, A.; Roy, A.; Sai, S.; Roy, S.
Weather forecasting is an important aspect across various sectors, but the intricate dynamics of weather systems pose a challenge for conventional statistical models to forecast accurately. Besides auto-regressive time forecasting models like ARIMA, deep learning architectures like ANNs, LSTMs, and GRU networks have been shown to enhance the accuracy of forecasts by considering temporal dependencies. This paper studies various machine learning models like XGBoost, SVR, KNN Regressor, Random Forest Regressor and the application of metaheuristic algorithms, like Genetic Algorithm (GA), Differential Evolution (DE), and Particle Swarm Optimization (PSO), on some deep learning model architectures like ANNs, LSTMs and GRUs, to automate the process of finding the best hyperparameters for the models. Furthermore, this paper explores the Quantum LSTM (QLSTM) network and novel QLSTM Ensemble models. We conduct a comparative study of these model structures, evaluating their effectiveness in weather prediction using measures such as Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The findings underscore the capabilities of metaheuristic algorithms and innovative quantum methods in enhancing the precision of weather forecasts. Â© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
A novel proposal to effectively combine multipath data forwarding for data center networks with congestion control and load balancing using Software-Defined Networking Approach
(2014) Mallik, A.; Hegde, S.
Modern data center networks (DCNs) often use multi-rooted topologies, which offer multipath capability, for increased bandwidth and fault tolerance. However, traditional routing algorithms for the Internet have no or limited support for multipath routing, and cannot fully utilize available bandwidth in such DCNs. As a result, they route all the traffic through a single path, and thus form congestion. Multipath (MP) routing might be a good alternative, but is not sufficient alone to handle congestion that comes from the contention of end stations. Dynamic load balancing, on the other hand, protects the network from sudden congestions which could be caused by load spikes or link failures. However, little work has been done to incorporate all these features in a single and comprehensive solution for Data Center Ethernet (DCE). In this paper, we propose a novel method that attempts to integrate dynamic load balancing, multi-path scheme with congestion control (CC), with the use of pure Software-Defined-Networking (SDN) approach. SDN decouples control plane from the data forwarding plane, which reduces the overheads of the network switches. The major objectives that our solution attempts to achieve are, efficient utilization of network resources, high throughput and minimal frame loss. � 2014 IEEE.
QGAPHnet : Quantum Genetic Algorithm Based Hybrid QLSTM Model for Soil Moisture Estimation
(Institute of Electrical and Electronics Engineers Inc., 2024) Sai, S.; Sen, A.; Mallick, C.; Mallik, A.; Sen, U.; Paul, M.; Sutradhar, A.; Roy, S.
Soil moisture, pH, soil temperature, humidity among other factors play a pivotal role in affecting the agricultural productivity of a region, influencing factors such as crop yield, organic carbon estimation, and crop growth analysis. This paper introduces a comprehensive investigation into soil moisture and temperature dynamics, employing a dynamic soil moisture dataset. Utilising Quantum Long Short Term Memory (QLSTM), we apply Quantum Genetic Algorithm (QGA) and Particle Swarm Optimisation (PSO) to study and predict patterns within the dataset. Our approach not only enhances the precision of soil moisture estimations but also provides a novel perspective on environmental factors. The findings from this study hold significant implications for understanding and managing soil moisture in diverse contexts, spanning agriculture, hydrology, and ecosystem studies. Â© 2024 IEEE.