Nitul Dutta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nitul Dutta has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
Iti Saha Misra
7 shared publicationsHiren Kumar Deva Sarma
5 shared publications- Zdzislaw Polkowski
Faculty of Social and Technical Sciences, Jan Wyzykowski University Polkowice, Lubin, Poland
5 shared publications Corina Savulescu
Faculty of Elect. Comm. and Computer University of Pitesti, Romania
4 shared publicationsAshish Kr. Srivastava
Computer Engineering Department, MEF Group of Institutions, Rajkot, Gujarat, India
2 shared publications- Emil Pricop
Petroleum-Gas University of Ploiesti
2 shared publications
Latest Publications
- 8 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (3) , 4708-4721
A Strategic Game Based Interest Forwarding in Information Centric Vehicular Network
In an Information Centric Network (ICN), a client acquires data by disseminating an ‘interest’ packet across the network. For ease of accessing, the interest packet carries the name of the desired content. If any intermediate node receives the interest packet and possess the named content, then it serves the client from it's own cache instead of forwarding it to the actual content producer. Hence, if interest packets are efficiently forwarded to the most appropriate content store, then the content retrieval process would be significantly faster. In this paper, a strategic game based interest forwarding techniques is proposed for Information Centric Vehicular Networks (ICVN). The game is played among network entities such as mobile vehicles, road side units (RSUs) and edge servers (ESs). Every such entities keep track of their neighbors' information in a table which assist them in playing the game by identifying the potential neighbors that may hold the searched content. During the game, participants (i.e. the players) earn credits based on their behavior during a deal. It in turn calculated based on some payoff function driven by selected strategy. A network entity (also called node) with higher credits got higher preference in playing the game. Moreover, the payoff is computed as a function of content retrieval cost and the mobility profile of the node. The cost of content retrieval, on the other hand, is dependent on the service probability ($s_{p}$) and the mobility profile ($r_{m}$) of the selected neighbor. The $s_{p}$ is derived from the past service history and $r_{m}$ is derived from the mobility pattern. Proposed protocol is evaluated mathematically followed by comparative study in $ns$-3. Performance of the proposed protocol is compared with three existing approaches and found that the new algorithm performs better in terms of interest success rate, content retrieval time, server hit ratio and network overhead.
- 8 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (3) , 4708-4721
A Strategic Game Based Interest Forwarding in Information Centric Vehicular Network
In an Information Centric Network (ICN), a client acquires data by disseminating an ‘interest’ packet across the network. For ease of accessing, the interest packet carries the name of the desired content. If any intermediate node receives the interest packet and possess the named content, then it serves the client from it's own cache instead of forwarding it to the actual content producer. Hence, if interest packets are efficiently forwarded to the most appropriate content store, then the content retrieval process would be significantly faster. In this paper, a strategic game based interest forwarding techniques is proposed for Information Centric Vehicular Networks (ICVN). The game is played among network entities such as mobile vehicles, road side units (RSUs) and edge servers (ESs). Every such entities keep track of their neighbors' information in a table which assist them in playing the game by identifying the potential neighbors that may hold the searched content. During the game, participants (i.e. the players) earn credits based on their behavior during a deal. It in turn calculated based on some payoff function driven by selected strategy. A network entity (also called node) with higher credits got higher preference in playing the game. Moreover, the payoff is computed as a function of content retrieval cost and the mobility profile of the node. The cost of content retrieval, on the other hand, is dependent on the service probability ($s_{p}$) and the mobility profile ($r_{m}$) of the selected neighbor. The $s_{p}$ is derived from the past service history and $r_{m}$ is derived from the mobility pattern. Proposed protocol is evaluated mathematically followed by comparative study in $ns$-3. Performance of the proposed protocol is compared with three existing approaches and found that the new algorithm performs better in terms of interest success rate, content retrieval time, server hit ratio and network overhead.
- Open Access
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 110913-110925
Graph Based Cooperative Forwarding in Information Centric Vehicular Networks
The rise of data intensive applications reveal the limitations of IP-based networking, particularly in dynamic vehicular environment. Transitioning to Information Centric Network (ICN) addresses these limitations by focusing on content retrieval from any suitable location rather than completely relying on content server or host-to-host communication. The content based communication uses an interest packet to seek named data. The interest packets are forwarded through the network to locate and retrieve content. In general the ICN uses Forwarding Information Base (FIB) tables for efficient forwarding of interest. However, in wireless environment like Vehicular Network (V-Net), use of FIB is expensive due to high bandwidth demand for maintenance. Hence, interest forwarding approach without FIB is much popular. In this paper, an interest forwarding technique for Information Centric Vehicular Networks (ICVNs) is proposed without the use of FIB. The prime objective of the algorithm is to reduce content retrieval time and optimize network overhead and throughput. For that purpose the network is modeled as a graph and partitioned into groups where each group is managed by a group leader. The group members cooperate with leader and share local information. The leaders, on the other hand cooperate with other group leaders and share information in the global level. Interest packets are forwarded by leaders on behalf of a group there by accelerating the content retrieval process. The proposed algorithm is named as GCF (Graph based Cooperative Forwarding) and is simulated in ndnSim-2.0. The performance of GCF is compared with the other two contemporary protocols, and observation shows better performance of the new approach, specifically in a densely populated scenario, compared to other benchmark algorithms. Various parameters used in the comparison are end-to-end latency, interest loss rate, network overhead, throughput, and server hit ratio. Quantitatively, the proposed protocol shows nearly 10% improvement in latency, 40% improvement in interest packet loss, and 60% improvement in network overhead.
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 110913-110925
Open AccessGraph Based Cooperative Forwarding in Information Centric Vehicular Networks
The rise of data intensive applications reveal the limitations of IP-based networking, particularly in dynamic vehicular environment. Transitioning to Information Centric Network (ICN) addresses these limitations by focusing on content retrieval from any suitable location rather than completely relying on content server or host-to-host communication. The content based communication uses an interest packet to seek named data. The interest packets are forwarded through the network to locate and retrieve content. In general the ICN uses Forwarding Information Base (FIB) tables for efficient forwarding of interest. However, in wireless environment like Vehicular Network (V-Net), use of FIB is expensive due to high bandwidth demand for maintenance. Hence, interest forwarding approach without FIB is much popular. In this paper, an interest forwarding technique for Information Centric Vehicular Networks (ICVNs) is proposed without the use of FIB. The prime objective of the algorithm is to reduce content retrieval time and optimize network overhead and throughput. For that purpose the network is modeled as a graph and partitioned into groups where each group is managed by a group leader. The group members cooperate with leader and share local information. The leaders, on the other hand cooperate with other group leaders and share information in the global level. Interest packets are forwarded by leaders on behalf of a group there by accelerating the content retrieval process. The proposed algorithm is named as GCF (Graph based Cooperative Forwarding) and is simulated in ndnSim-2.0. The performance of GCF is compared with the other two contemporary protocols, and observation shows better performance of the new approach, specifically in a densely populated scenario, compared to other benchmark algorithms. Various parameters used in the comparison are end-to-end latency, interest loss rate, network overhead, throughput, and server hit ratio. Quantitatively, the proposed protocol shows nearly 10% improvement in latency, 40% improvement in interest packet loss, and 60% improvement in network overhead.
- 20 April 2025
- Published by Wiley in International Journal of Communication Systems
- Vol. 38 (8)
Genetic Algorithm‐Based Interest Forwarding for Information Centric Vehicular Networks
The information centric vehicular network (ICVN) is envisioned as an alternative to IP‐based vehicular network in order to extend the content oriented retrieval in to vehicular communication. In such network, named contents are retrieved through circulation of interest packets. Hence, there is a need of efficient interest forwarding techniques for timely retrieval of data. So far, the flooding of interest is the most intuitive forwarding approach in ICVN. But it suffers from broadcast storm and generates extensive signaling overhead which is not affordable in bandwidth constrained ICVN. In this article, a guided genetic algorithm (GA)‐based interest forwarding (GABIF) technique is proposed for ICVN. The algorithm selects a set of neighbors to forward interest packets rather than flooding an interest to all its neighbors. To select the set of neighbors, the content seeker (a vehicle) performs a GA‐based analysis on the list of neighbors and finds the optimized set of vehicles that have maximum possibility of holding the searched content. Every vehicle in the topology maintains a table of its neighbors along with the content availability probability and the cost of acquiring content from those sources. These parameters are later used to generate the optimized solution by applying GA. The proposed approach is simulated in ‐3‐based ‐2.0 and compared with other three exiting approaches. Observation shows a better performance of GABIF in many aspects including interest success rate, content retrieval time, protocol overhead, and server hit ratio.
- 20 April 2025
- Published by Wiley in International Journal of Communication Systems
- Vol. 38 (8)
Genetic Algorithm‐Based Interest Forwarding for Information Centric Vehicular Networks
The information centric vehicular network (ICVN) is envisioned as an alternative to IP‐based vehicular network in order to extend the content oriented retrieval in to vehicular communication. In such network, named contents are retrieved through circulation of interest packets. Hence, there is a need of efficient interest forwarding techniques for timely retrieval of data. So far, the flooding of interest is the most intuitive forwarding approach in ICVN. But it suffers from broadcast storm and generates extensive signaling overhead which is not affordable in bandwidth constrained ICVN. In this article, a guided genetic algorithm (GA)‐based interest forwarding (GABIF) technique is proposed for ICVN. The algorithm selects a set of neighbors to forward interest packets rather than flooding an interest to all its neighbors. To select the set of neighbors, the content seeker (a vehicle) performs a GA‐based analysis on the list of neighbors and finds the optimized set of vehicles that have maximum possibility of holding the searched content. Every vehicle in the topology maintains a table of its neighbors along with the content availability probability and the cost of acquiring content from those sources. These parameters are later used to generate the optimized solution by applying GA. The proposed approach is simulated in ‐3‐based ‐2.0 and compared with other three exiting approaches. Observation shows a better performance of GABIF in many aspects including interest success rate, content retrieval time, protocol overhead, and server hit ratio.
- Open Access
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 5, 1680-1691
Efficient Modeling of Interest Forwarding in Information Centric Vehicular Networks
Vehicular networks (V-Nets) of the current era is widely used for information sharing and entertainment. Considering the popularity and demand for faster data communications, V-Nets are evolving towards an information-centric approach, namely the Information Centric Vehicular Networks (ICVN). In ICVN, nodes such as vehicles, roadside units, pedestrian devices, and sensors, generate interest packets and forward them to appropriate cache stores to retrieve desired data. Hence, an efficient interest forwarding algorithm in ICVN considerably enhances the content retrieval performance and make supports road safety, traffic management, environmental monitoring in real-vehicular environment. However, designing such efficient scheme is critical due to the involvement of various communication scenarios like vehicle-to-vehicle (V2V), vehicle-to-roadside unit (V2R), vehicle-to-in-vehicle sensors (V2S), vehicle-to-mobile infrastructure (V2I), and vehicle-to-personal device (V2P) and it demands a comprehensive and connected vehicular network. In this paper, we propose an interest forwarding scheme for ICVN with the above said realistic scenario. The interest forwarding process is governed by the Secretary Selection Problem (SSP) which guides a vehicular node to select the next level forwarder for locating the desired content. The goal is to select the best neighboring vehicle as the next forwarder thereby maximizing the chances of obtaining the requested data. The proposed scheme, named as Selection Based Interest Forwarding (SBIF) which uses Secretary Selection Problem (SSP) for governing the forward process to select the next level forwarder for locating the desired content. This scheme is analyzed mathematically and implemented in $ndn$ simulator. Performance is compared with existing state of the art schemes and observation shows that SBIF outperforms existing approaches considered for comparison.
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 5, 1680-1691
Open AccessEfficient Modeling of Interest Forwarding in Information Centric Vehicular Networks
Vehicular networks (V-Nets) of the current era is widely used for information sharing and entertainment. Considering the popularity and demand for faster data communications, V-Nets are evolving towards an information-centric approach, namely the Information Centric Vehicular Networks (ICVN). In ICVN, nodes such as vehicles, roadside units, pedestrian devices, and sensors, generate interest packets and forward them to appropriate cache stores to retrieve desired data. Hence, an efficient interest forwarding algorithm in ICVN considerably enhances the content retrieval performance and make supports road safety, traffic management, environmental monitoring in real-vehicular environment. However, designing such efficient scheme is critical due to the involvement of various communication scenarios like vehicle-to-vehicle (V2V), vehicle-to-roadside unit (V2R), vehicle-to-in-vehicle sensors (V2S), vehicle-to-mobile infrastructure (V2I), and vehicle-to-personal device (V2P) and it demands a comprehensive and connected vehicular network. In this paper, we propose an interest forwarding scheme for ICVN with the above said realistic scenario. The interest forwarding process is governed by the Secretary Selection Problem (SSP) which guides a vehicular node to select the next level forwarder for locating the desired content. The goal is to select the best neighboring vehicle as the next forwarder thereby maximizing the chances of obtaining the requested data. The proposed scheme, named as Selection Based Interest Forwarding (SBIF) which uses Secretary Selection Problem (SSP) for governing the forward process to select the next level forwarder for locating the desired content. This scheme is analyzed mathematically and implemented in $ndn$ simulator. Performance is compared with existing state of the art schemes and observation shows that SBIF outperforms existing approaches considered for comparison.
- Open Access
- 8 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 421-426
Federated learning framework for prediction based load distribution in 5G network slicing
The 5G technology brings transformative changes across sectors like healthcare, automotive, and entertainment by integrating massive IoT networks and supporting dense device connectivity. Network slicing in 5G further ignites the capability by allowing tailored virtual networks for specific applications, enhancing operational efficiency and user experience across diverse scenarios. In this paper we propose a framework to use Federated Learning (FL) in 5G network slicing to support service assignment. The aim is to optimize the network traffic allocation among various slices. It first predicts the load on each network slice and then the incoming traffic is allocated to a slice which is most suitable and not heavily loaded. The DeepSlice dataset on 5G slicing is horizontally splited into multiple segments to train a federated CNN model which are deployed across multiple clients. The model is analyzed with varying number of clients and parameters such as accuracy and loss are observed. The performance of federated approach is compared with centralized approach of prediction keeping essential hyper parameters unchanged. Outcomes in terms of training and testing is presented for better interpretation of the proposed framework. Observation shows that the federated learning outperform the centralized technique in accuracy as well as loss.
- 8 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 421-426
Open AccessFederated learning framework for prediction based load distribution in 5G network slicing
The 5G technology brings transformative changes across sectors like healthcare, automotive, and entertainment by integrating massive IoT networks and supporting dense device connectivity. Network slicing in 5G further ignites the capability by allowing tailored virtual networks for specific applications, enhancing operational efficiency and user experience across diverse scenarios. In this paper we propose a framework to use Federated Learning (FL) in 5G network slicing to support service assignment. The aim is to optimize the network traffic allocation among various slices. It first predicts the load on each network slice and then the incoming traffic is allocated to a slice which is most suitable and not heavily loaded. The DeepSlice dataset on 5G slicing is horizontally splited into multiple segments to train a federated CNN model which are deployed across multiple clients. The model is analyzed with varying number of clients and parameters such as accuracy and loss are observed. The performance of federated approach is compared with centralized approach of prediction keeping essential hyper parameters unchanged. Outcomes in terms of training and testing is presented for better interpretation of the proposed framework. Observation shows that the federated learning outperform the centralized technique in accuracy as well as loss.
- 25 April 2024
- Published by Elsevier in Vehicular Communications
- Vol. 47
Evolutionary game based interest forwarding in information centric vehicular networks
- 25 April 2024
- Published by Elsevier in Vehicular Communications
- Vol. 47
Evolutionary game based interest forwarding in information centric vehicular networks
- Open Access
- 7 February 2023
- Published by Springer Nature in Research Square
Optimized interest forwarding in information centric vehicular networks using general secretary problem
Vehicular networks of current era is not limited only to road safety and traffic management. It is been widely accepted as a network for information sharing, social networking and entertainment. With the advent of smart vehicles, the demand of vehicular network centric applications are getting popular. In one way, these applications demand faster data access and on the other hand, the underlying challenges of vehicular networks such as intermittent connectivity, low bandwidth and unpredictable vehicle movements impose considerable hindrance on communications. That is why, the vehicular communication is moving towards information centric approach so that the benefits of Information Centric Network (ICN) can be utilized. However, inherent challenges of vehicular communication and the lack of adequate protocols to implement content centric approach makes the extension of ICN into vehicular communications difficult. In ICN, a node generates interest packets to find a content. The interest is forwarded to an appropriate cache store to get the data. Hence, efficient forwarding of interest packets can considerably improve the content retrieval delay and can reduce network load. The interest forwarding techniques designed for wired ICN are not suitable for vehicular network due to computational complexity and bandwidth crisis. Hence, Information Centric Vehicular Network (ICVN) demands a new design for interest forwarding. Influenced by the need of the current time in vehicular communication, this research is aimed at developing an efficient interest forwarding mechanism for ICVN. The proposed algorithm models the interest forwarding task as a general secretary problem and finds the best node (or set of nodes) in the network to forward the interest packet. The protocol performance is examined in a simulation testbed designed in ndnSim-2.0 and compared with existing forwarding approaches. Observation demonstrates a better performance of the said vehicle with respect to content retrieval latency and network overhead.
- 7 February 2023
- Published by Springer Nature in Research Square
Open AccessOptimized interest forwarding in information centric vehicular networks using general secretary problem
Vehicular networks of current era is not limited only to road safety and traffic management. It is been widely accepted as a network for information sharing, social networking and entertainment. With the advent of smart vehicles, the demand of vehicular network centric applications are getting popular. In one way, these applications demand faster data access and on the other hand, the underlying challenges of vehicular networks such as intermittent connectivity, low bandwidth and unpredictable vehicle movements impose considerable hindrance on communications. That is why, the vehicular communication is moving towards information centric approach so that the benefits of Information Centric Network (ICN) can be utilized. However, inherent challenges of vehicular communication and the lack of adequate protocols to implement content centric approach makes the extension of ICN into vehicular communications difficult. In ICN, a node generates interest packets to find a content. The interest is forwarded to an appropriate cache store to get the data. Hence, efficient forwarding of interest packets can considerably improve the content retrieval delay and can reduce network load. The interest forwarding techniques designed for wired ICN are not suitable for vehicular network due to computational complexity and bandwidth crisis. Hence, Information Centric Vehicular Network (ICVN) demands a new design for interest forwarding. Influenced by the need of the current time in vehicular communication, this research is aimed at developing an efficient interest forwarding mechanism for ICVN. The proposed algorithm models the interest forwarding task as a general secretary problem and finds the best node (or set of nodes) in the network to forward the interest packet. The protocol performance is examined in a simulation testbed designed in ndnSim-2.0 and compared with existing forwarding approaches. Observation demonstrates a better performance of the said vehicle with respect to content retrieval latency and network overhead.
- 10 January 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 130, 269-278
An approach for FIB construction and Interest packet forwarding in information centric network
- 10 January 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 130, 269-278
An approach for FIB construction and Interest packet forwarding in information centric network
- Open Access
- 31 December 2021
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
SVM-based Analysis for Predicting Success Rate of Interest Packets in Information Centric Networks
A consumer in Information Centric Network (ICN) generates an Interest packet by specifying the name of the required content. As the network emphasizes on content retrieval without much bothering about who serves it (a cache location or actual producer), every Content Router (CR) either provides the requested content back to the requester (if exists in its cache) or forwards the Interest packet to the nearest CR. While forwarding an Interest packet, the ICN routing by default does not provide any mechanism to predict the probable location of the content searched. However, having a predictive model before forwarding may significantly improve content retrieval performance. In this paper, a machine learning (ML) algorithm, particularly a Support Vector Machine (SVM) is used to forecast the success of the Interest packet. A CR can then send an Interest packet in the outgoing interface which is forecasted successful. The objective is to maximize the success rate which in turn minimizes content search time and maximizes throughput. The dataset used in is generated from a simulation topology designed in ndnSim comprising 10 K data points having 10 features. The linear, RBF and the polynomial kernel (with degree 3) are used to analyze the dataset. The polynomial kernel shows the best behavior with 98% accuracy. A comparative retrieval time with and without ML demonstrates around 10% improvement with SVM enable forwarding compared to normal ICN forwarding.
- 31 December 2021
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
Open AccessSVM-based Analysis for Predicting Success Rate of Interest Packets in Information Centric Networks
A consumer in Information Centric Network (ICN) generates an Interest packet by specifying the name of the required content. As the network emphasizes on content retrieval without much bothering about who serves it (a cache location or actual producer), every Content Router (CR) either provides the requested content back to the requester (if exists in its cache) or forwards the Interest packet to the nearest CR. While forwarding an Interest packet, the ICN routing by default does not provide any mechanism to predict the probable location of the content searched. However, having a predictive model before forwarding may significantly improve content retrieval performance. In this paper, a machine learning (ML) algorithm, particularly a Support Vector Machine (SVM) is used to forecast the success of the Interest packet. A CR can then send an Interest packet in the outgoing interface which is forecasted successful. The objective is to maximize the success rate which in turn minimizes content search time and maximizes throughput. The dataset used in is generated from a simulation topology designed in ndnSim comprising 10 K data points having 10 features. The linear, RBF and the polynomial kernel (with degree 3) are used to analyze the dataset. The polynomial kernel shows the best behavior with 98% accuracy. A comparative retrieval time with and without ML demonstrates around 10% improvement with SVM enable forwarding compared to normal ICN forwarding.
- 6 November 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 123 (3) , 1-26
A Scalable Mobility Management Scheme for PMIPv6 with Multiple Control and Data Plane
- 6 November 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 123 (3) , 1-26
A Scalable Mobility Management Scheme for PMIPv6 with Multiple Control and Data Plane