Dr Balaj iNaik
@nitsikkim.ac.in
Assistant Professor Dept of CSE
National Institute of Technology Sikkim
RESEARCH INTERESTS
Cloud Computing, Workflow Scheduling Algorithm and Nature Inspired Algorithms
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Banavath Balaji Naik, Bollu Priyanka, and Md. Sarfaraj Alam Ansari
Springer Science and Business Media LLC
Banavath Balaji Naik, Bollu Priyanka, and Sarfaraj Alam Ansari
Springer Science and Business Media LLC
Most Tahia Subah Ankita, Bipal Khanal, Samvedna Gupta, Manvendra Singh, B. Balaji Naik, and Md. Sarfaraj Alam Ansari
Springer Nature Switzerland
Bollu Priyanka, Banavath Balaji Naik, and Thandava Purandeswar Reddy
Springer Science and Business Media LLC
Anubhav Baranwal, Prince Gaurav, Lohit Reddy, Bhabani Shankar Das, and Balaji Naik
IWA Publishing
ABSTRACT Scouring around a bridge pier involves removing sediment from the riverbed and banks due to water flow. This paper employs eXtreme Gradient Boosting (XGBoost) and support vector machine with particle swarm optimization (SVM-PSO) machine learning (ML) approaches to model the temporal local scour depth around bridge piers under clear water scouring (CWS) conditions. CWS datasets, incorporating bridge pier geometry, flow characteristics, and sediment properties, are collected from existing literature. Five non-dimensional influencing parameters, such as ratio of pier width to flow depth (b/y), ratio of approach mean velocity to critical velocity (V/Vc), ratio of mean sediment size to pier width (d50/b), Froude number (Fr), and standard deviation of sediment (σg), are chosen as input parameters. XGBoost and SVM-PSO ML models demonstrate superior predictive capabilities, achieving coefficient of determination (R2) values exceeding 0.90 and mean absolute percentage error (MAPE) and root mean square error (RMSE) values less than 17.07% and 0.0341, respectively. Comparison with the previous four empirical models based on statistical indices reveals that the proposed XGBoost model outperforms SVM-PSO and empirical models in predicting scour depth, so it is recommended for estimating clear water scour depth under varying temporal conditions within the specified dataset range.
Marlom Bey, Pratyay Kuila, Banavath Balaji Naik, and Santanu Ghosh
Elsevier BV
Marlom Bey, Pratyay Kuila, and Banavath Balaji Naik
IEEE
The rise in Internet of Things (IoT) devices has led to the creation of sophisticated applications that demand various resources in real time to support a wide range of IoT services. Leveraging edge computing (EC) infrastructure, these services can be effectively placed on edge nodes (ENs). However, due to the limited computational resources of ENs, it becomes challenging to manage a large number of services while maintaining the system’s quality of service (QoS) and quality of experience (QoE). This paper introduces a quantum-inspired differential evolution method (QIDE-IoTSP) designed to optimize the placement of IoT services within EC networks. The primary objectives of QIDE-IoTSP are to maximize throughput, ensure optimal load balance, and minimize computation time. A quantum vector (QV) is utilized to develop a robust solution for the optimal deployment of IoT services in EC networks to achieve this. The effectiveness of each solution is evaluated using a formulated fitness function. Simulation results demonstrate that QIDE-IoTSP surpasses other metaheuristic techniques in terms of throughput, computation latency, and load balancing.
Suman Banerjee, Pratyay Kuila, and Banavath Balaji Naik
IEEE
Vehicle-to-everything (V2X) communication is crucial in Intelligent Transportation Systems (ITSs) for enhancing road safety, traffic efficiency, and convenience. To address the need for trust in V2X communications, a trust management system for Vehicular Ad Hoc Networks (VANETs) using blockchain technology has been proposed. This system calculates dynamic trust scores for vehicles based on direct communication, recommendations from other vehicles, and proximity to roadside units (RSUs). The trust scores are stored in a transparent and tamperproof blockchain, ensuring the immutability and transparency of trust scores. Simulations demonstrate that this blockchain-based trust management system significantly improves the security and reliability of V2X communications. This system is essential for the widespread acceptance of VANETs by fostering a trusted communication environment.
Marlom Bey, Pratyay Kuila, and Banavath Balaji Naik
Institute of Electrical and Electronics Engineers (IEEE)
B. Balaji Naik, T. Jaya Venkata Rama Reddy, K. Rohith Venkata karthik, and Pratyay Kuila
Springer Science and Business Media LLC
Deepak Dhingan, Santanu Ghosh, Banavath Balaji Naik, and Pratyay Kuila
IEEE
The research describes a technique that enables an Unmanned Aerial Vehicle (UAV) to delegate a part of a task to mobile devices. By outsourcing the computationally costly sections of a work to the more capable UAV and using the mobile devices for tasks that can be completed locally, the system makes good use of the capabilities of both the UAV and mobile devices. In this paper, Differential Evolution (DE) based algorithm is proposed for energy and delay efficient partial offloading in UAV-assisted MEC system. An extensive Simulations have been done to measure the performance of the proposed algorithm. The results reveal a considerable reduction in latency. Overall, our method shows how partial task offloading may be used to enhance the performance of UAV-assisted systems.
Banavath Balaji Naik, Dhananjay Singh, and Arun Barun Samaddar
Springer Science and Business Media LLC
In cloud computing, more often times cloud assets are underutilized because of poor allocation of task in virtual machine (VM). There exist inconsistent factors affecting the scheduling tasks to VMs. In this paper, an effective scheduling with multi-objective VM selection in cloud data centers is proposed. The proposed multi-objective VM selection and optimized scheduling is described as follows. Initially the input tasks are gathered in a task queue and tasks computational time and trust parameters are measured in the task manager. Then the tasks are prioritized based on the computed measures. Finally, the tasks are scheduled to the VMs in host manager. Here, multi-objectives are considered for VM selection. The objectives such as power usage, load volume, and resource wastage are evaluated for the VMs and the entropy is calculated for the measured objectives and based on the entropy value krill herd optimization algorithm prioritized tasks are scheduled to the VMs. The experimental results prove that the proposed entropy based krill herd optimization scheduling outperforms the existing general krill herd optimization, cuckoo search optimization, cloud list scheduling, minimum completion cloud, cloud task partitioning scheduling and round robin techniques.
Banavath Balaji Naik, Dhananjay Singh, and Arun Barun Samaddar
Wiley
Banavath Balaji Naik, Dhananjay Singh, and Arun B. Samaddar
Institution of Engineering and Technology (IET)
Cloud computing and virtualisation are recent approaches to develop minimum energy usage in virtualised cloud data centre (DC) for resource management. One of the major problems faced by cloud DCs is energy consumption which increases the cost of cloud user and environmental influence. Therefore, virtual machine (VM) consolidation is properly proposed in many approaches which reallocate the VMs by VM migration with the objective of minimum energy consumption. Here, VM consolidation based on the Fruit fly Hybridised Cuckoo Search (FHCS) algorithm is proposed to obtain the optimal solution with the help of two objective functions in cloud DC. This FHCS approach efficiently minimises the energy usage and resource depletion in cloud DC. The proposed work comparison is done with Ant Colony System (ACS), Particle Swarm Optimisation (PSO) algorithm and Genetic Algorithm (GA). The simulation conclusion reveals the advantage of the FHCS and VM migration method over existing procedures such as GA, PSO and ACS in terms of energy consumption and resource utilisation. The proposed method achieves 68 Kwh less energy and 72% less resources than existing methods. Simulation results have shown that energy consumption of the proposed method is reduced with less number of active PMs than other conventional approaches.
Syed Mohd Faraaz, B. Balaji Naik, and Dhananjay Singh
Springer Singapore
The advancement in technology has enabled us to transform from manually controlled devices to automatically controlled devices and smartphones find extensive applications in such a transformed system. Smartphones have become an important part of our lives. The number of smartphone users have increased rapidly as nowadays smartphones not only provide the basic processes such as dialling and receiving calls or sending text messages but they also interact and control a variety of devices such as computers, televisions, locks, cars, etc. In this paper we design and implementation of a remote lock system using wireless Bluetooth communications. The remote lock system is controlled by a dedicated android application which interacts with the hardware installed in the car and locks/unlocks the car without providing any manual inputs through the android app.
B Balaji Naik, Dhananjay Singh, A.B. Samaddar, and Sangsu Jung
IEEE
The virtual machine (VM) placement problem is a major issue in optimizing resource utilization of cloud data center. With rapid development of cloud computing, efficient algorithms are needed to reduce the power consumption and save energy in the cloud data center. Many researchers have investigated Meta heuristics algorithms to solve this problem based on the NP-Hard problem. In this paper, we consider a novel multi-objective Hybrid Fruit-fly Algorithm for virtual machine consideration in the cloud data center. The proposed algorithm is based on the works based on the VM Migration, which are mainly used to minimize over provisioning of physical machine by consolidating VMs on under-utilized physical machine (PM). The experimental results show that the proposed multi objective hybridized Fruitfly optimization technique which is based on the modified cuckoo search algorithm enhances the convergence rate and its optimization accuracy is comparable to other existing multi objective algorithms. The proposed algorithm results show that a significant reduction of unnecessary VM migration, avoids unstable host selection and also improves the application performance and efficiencies of power usage.
B Balaji Naik, Dhananjay Singh, A. B. Samaddar, and Hoon-Jae Lee
IEEE
The Information Centric Networking (ICN) is a novel concept of a large scale ecosystem of wireless actuators and computing technologies. ICN technologies are getting popular in the development of various applications to bring day-to-day comfort and ease in human life. The e-healthcare monitoring services is a subset of ICN services which has been utilized to monitor patient's health condition in a smart and ubiquitous way. However, there are several challenges and attacks on ICN. In this paper we have discussed ICN attacks and ICN based healthcare scenario. We have proposed a novel ICN stack for healthcare scenario for securing biomedical data communication instead of communication networks. However, the biomedical data communication between patient and Doctor requires reliable and secure networks for the global access.