Henry Nunoo-Mensah | Kwame Nkrumah University of Science and Technology (original) (raw)
Papers by Henry Nunoo-Mensah
EURASIP Journal on Wireless Communications and Networking, 2022
The integration of Internet of Things devices onto the Blockchain implies an increase in the tran... more The integration of Internet of Things devices onto the Blockchain implies an increase in the transactions that occur on the Blockchain, thus increasing the storage requirements. A solution approach is to leverage cloud resources for storing blocks within the chain. The paper, therefore, proposes two solutions to this problem. The first being an improved hybrid architecture design which uses containerization to create a side chain on a fog node for the devices connected to it and an Advanced Time-variant Multi-objective Particle Swarm Optimization Algorithm (AT-MOPSO) for determining the optimal number of blocks that should be transferred to the cloud for storage. This algorithm uses time-variant weights for the velocity of the particle swarm optimization and the non-dominated sorting and mutation schemes from NSGA-III. The proposed algorithm was compared with results from the original MOPSO algorithm, the Strength Pareto Evolutionary Algorithm (SPEA-II), and the Pareto Envelope-base...
Proceedings on Engineering Sciences, 2022
Technologies, 2022
The move towards intelligent systems has led to the evolution of IoT. This technological leap has... more The move towards intelligent systems has led to the evolution of IoT. This technological leap has over the past few years introduced significant improvements to various aspects of the human environment, such as health, commerce, transport, etc. IoT is data-centric; hence, it is required that the underlying protocols are scalable and sufficient to support the vast D2D communication. Several application layer protocols are being used for M2M communication protocols such as CoAP, MQTT, etc. Even though these messaging protocols have been designed for M2M communication, they are still not optimal for communications where message size and overhead are of much concern. This research paper presents a Lightweight Messaging Protocol (LiMP), which is a minified version of CoAP. We present a detailed protocol stack of the proposed messaging protocol and also perform a benchmark analysis of the protocol on some IoT devices. The proposed minified protocol achieves minimal overhead (a header size...
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 2022
Social Internet of Things (SIoT) involves integrating social networking concepts in the Internet ... more Social Internet of Things (SIoT) involves integrating social networking concepts in the Internet of Things (IoT) to enhance social interactions among IoT objects and users. SIoT is envisaged to provide adequate service selection and discovery. Trust is an essential factor whenever social concepts are discussed in communication networks. Trust usually leads to a mutual relationship between two parties (i.e., the trustor and trustee) where they both enjoy mutual benefits. For secure social relationships, Trust management (TM) is a crucial feature of SIoT. The primary aim of this work is to provide a comprehensive review of trust management proposals/schemes available for SIoT. Four main trust calculation algorithms for trust management were selected for this review, and they were examined in detail. The IEEE Xplore, Scopus, ResearchGate, and Google Scholar databases were searched for articles containing the terms "Trust aggregation approaches in IoT", and "Trust computa...
Engineering Reports, 2020
Emotion detection (ED) is a branch of sentiment analysis that deals with the extraction and analy... more Emotion detection (ED) is a branch of sentiment analysis that deals with the extraction and analysis of emotions. The evolution of Web 2.0 has put text mining and analysis at the frontiers of organizational success. It helps service providers provide tailor-made services to their customers. Numerous studies are being carried out in the area of text mining and analysis due to the ease in sourcing for data and the vast benefits its deliverable offers. This article surveys the concept of ED from texts and highlights the main approaches adopted by researchers in the design of text-based ED systems. The article further discusses some recent state-of-the-art proposals in the field. The proposals are discussed in relation to their major contributions, approaches employed, datasets used, results obtained, strengths, and their weaknesses. Also, emotion-labelled data sources are presented to provide neophytes with eligible text datasets for ED. Finally, the article presents some open issues and future research direction for text-based ED.
International Journal of Computer Applications, 2018
International Journal of Communication Systems, 2017
The security of a wireless sensor network is greatly increased with increasing levels of trustwor... more The security of a wireless sensor network is greatly increased with increasing levels of trustworthiness of nodes on the network. There are a number of trust models proposed that employ various trust evaluation methods. The paper categorises trust evaluation methods for wireless sensor networks into socio-inspired, bio-inspired and analytical methods. Biologically inspired methods and socio constructs are rarely employed in the design of trust schemes as opposed to analytical methods (probability, agent based, fuzzy, etcetera). The paper discusses existing bio-inspired and socio-inspired based trust schemes implemented for wireless sensor networks, viz. Quality-based Distance Vector (QDV) protocol, Enhanced Bio-inspired Trust and Reputation Model for Wireless Sensor Network (EBTRM-WSN), Bio-inspired Trust Routing Protocol (B-iTRP), Machine Learning based Bio-inspired Trust and Reputation Model (MLBTRM), Socio-psychological Trust and Reputation Model, and finally Reputation Framework for Sensor Network (RFSN). A summary of recent trust models (analytical, biological and socio inspired) have been discussed based on their contributions, trust evaluation method, and their limitations was conducted. The pros and cons of analytical, socio and biologically inspired algorithms for computing are outlined in order to easily ascertain the relevance of adopting either biological or socio-inspired approaches for solving trust related problems in wireless sensor networks.
International Journal of Mobile Network Communications & Telematics, 2014
ABSTRACT The widespread nature of wireless computing and communications offers the promise of man... more ABSTRACT The widespread nature of wireless computing and communications offers the promise of many societal and individual benefits. Consumer devices such as cell phones, PDAs and laptops have received a lot of attention over the years, even though the impact of wireless technology is much broader, e.g., through sensor networks for safety applications and home automation, smart grid control, medical wearable and embedded wireless devices, and entertainment systems. These applications have been supported by the rapid developments in wireless technology and standards. One of these wireless technologies is the Worldwide Interoperability for Microwave Access (WiMAX) technology. The WiMAX technology with its growing interest in the West African Sub-Region offers an immerse opportunity in terms of applications and advantages in connecting the Sub-Region to the rest of the world. WiMAX with the promise of about 75Mbps and the numerous opportunities in terms of coverage are yet to be explored for other applications in security, smart grid control, e-learning, telemedicine, e-governance, and home and factory automation. Ghana as pioneer in African Telecommunication has been in the forefront in the deployment of 4G-WiMAX network across the country [1]. An accelerated deployment of broadband personal communication coupled with the continuously increasing demand for large data rates is supposed to reveal an increasing spectrum scarcity, but that is not the case in Ghana.
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 2022
Facial emotion recognition (FER) forms part of affective computing, where computers are trained t... more Facial emotion recognition (FER) forms part of affective computing, where computers are trained to recognize human emotion from human expressions. Facial Emotion Recognition is very necessary for bridging the communication gap between humans and computers because facial expressions are a form of communication that transmits 55% of a person's emotional and mental state in a total face-to-face communication spectrum. Breakthroughs in this field also make computer systems (robotic systems) better serve or interact with humans. Research has far advanced for this cause, and Deep learning is at its heart. This paper systematically discusses state-of-the-art deep learning architectures and algorithms for facial emotion detection and recognition. The paper also reveals the dominance of CNN architectures over other known architectures like RNNs and SVMs, highlighting the contributions, model performance, and limitations of the reviewed state-of-the-art. It further identifies available op...
The number of anchor nodes required for accurate localization is an important problem in the wire... more The number of anchor nodes required for accurate localization is an important problem in the wireless sensor network research community. The error associated with localization is high when anchor nodes are not optimally placed in the network. No matter how the network is set up, the error associated with localization is inevitable. There are various sources for these errors, one of which is the unavailability of anchor nodes. These conditions arise due to stumpy deployment density or poor signal propagation owing to factors like multipath effects, fading effects and poor visibility. This paper proposes a method of determining the minimum number of anchor nodes required for a given sensor (smart energy meter) network dimension using triangulation as the localization process. The proposed method uses the sensitivity of the sensor nodes and various environmental conditions. Using the sensitivity of the sensor nodes and the environmental conditions, the minimum number of anchor nodes fo...
International Journal of Computer Applications, 2014
enterprise networks, the concept of bringing your own devices (BYOD) to work and also allowing gu... more enterprise networks, the concept of bringing your own devices (BYOD) to work and also allowing guest nodes to connect to the network is encouraged. As a factor the need to control access to the network is critical as visibility of nodes attached to the network is paramount in determining potential threats. The use of opensource technology is not mostly patronized by the corporate world because of the steep learning curve and the assumed complexities involved in the use of these software. This paper throws more light on the need for the use of opensource for enterprise networks especially for such networks for developing economies. Three major open source tools (OpenNAC, PacketFence and FreeNAC) are reviewed to provide a mechanism for assessing and selecting an opensource option for your educational network.
Technologies, 2021
The fast emergence of IoT devices and its accompanying big and complex data has necessitated a sh... more The fast emergence of IoT devices and its accompanying big and complex data has necessitated a shift from the traditional networking architecture to software-defined networks (SDNs) in recent times. Routing optimization and DDoS protection in the network has become a necessity for mobile network operators in maintaining a good QoS and QoE for customers. Inspired by the recent advancement in Machine Learning and Deep Reinforcement Learning (DRL), we propose a novel MADDPG integrated Multiagent framework in SDN for efficient multipath routing optimization and malicious DDoS traffic detection and prevention in the network. The two MARL agents cooperate within the same environment to accomplish network optimization task within a shorter time. The state, action, and reward of the proposed framework were further modelled mathematically using the Markov Decision Process (MDP) and later integrated into the MADDPG algorithm. We compared the proposed MADDPG-based framework to DDPG for network...
Wireless technology is increasing rapidly, and the vision of pervasive wireless computing and com... more Wireless technology is increasing rapidly, and the vision of pervasive wireless computing and communications offers the promise of many societal and individual benefits. While consumer devices such as cell phones, PDAs and laptops receive a lot of attention, the impact of wireless technology is much broader, e.g., through sensor networks for safety applications and home automation, smart grid control, medical wearable and embedded wireless devices, and entertainment systems. One of these wireless technologies is the Worldwide Interoperability for Microwave Access (WiMAX) technology. The explosion of wireless applications in some parts of the world has created an ever-increasing demand for more radio spectrum. This is not the case in the West African Sub-Region, especially Ghana where the 2.6GHz and 3.5GHz broadband access bands offering 190MHz and 140MHz bandwidth is underutilized. In this paper, we look at usage of deployed 4G-WiMAX network in Ghana and advocate the need for policy...
The use of trust and reputation models (TRMs) are on the rise due to the increasing complexities ... more The use of trust and reputation models (TRMs) are on the rise due to the increasing complexities of cryptography. The use of cryptography though potent on traditional networks, cannot be supported by the resource constraint wireless sensor network (WSN). Trust evaluations have made use of a number of approaches, such as analytical, bioand socio-inspired methods, in the design of TRMs. The use of socio-inspired methods for TRM design is given less attention though its a simple and effective method. The paper proposes the first sociopsychological TRM simulator (SoTRMSim). The models implemented in SoTRMSim are the consensusaware and privacy-aware sociopsychological TRMs by Rathore and Nunoo-Mensah respectively. The proposed simulator provides an objective way of simultaneously evaluating sociopsychological TRMs.
Security in wireless sensor network (WSN) has become an increasing necessity due to the diverse a... more Security in wireless sensor network (WSN) has become an increasing necessity due to the diverse application areas being implemented. Application areas such as military surveillance and environmental monitoring need to be guided against node tampering and node subversion. Works carried out by wireless sensor network researchers pertaining to increasing the security of the network is significant. Node authentication is a suitable technique against node tampering and the introduction of false nodes. A way of authenticating nodes is by using Message Authentication Code (MAC); this is implemented using hash functions. The limited energy available to sensor nodes, have to be considered when selecting a hash function for implementation. In this paper, comparative analysis of some hash functions (MD-5, SHA-1, SHA-224, SHA-256, SHA-384 and SHA-512) were carried out. The functions were selected based on their popularity. The analysis was done to identify a short-list of hash functions that ca...
International Journal of Advanced Computer Science and Applications
With the exponential increase in connected devices and its accompanying complexities in network m... more With the exponential increase in connected devices and its accompanying complexities in network management, dynamic Traffic Engineering (TE) solutions in Software-Defined Networking (SDN) using Reinforcement Learning (RL) techniques has emerged in recent times. The SDN architecture empowers network operators to monitor network traffic with agility, flexibility, robustness and centralized control. The separation of the control and the forwarding plane in SDN has enabled the integration of RL agents in the networking architecture to enforce changes in traffic patterns during network congestions. This paper surveys major RL techniques adopted for efficient TE in SDN. We reviewed the use of RL agents in modelling TE policies for SDNs, with agents' actions on the environment guided by future rewards and a new state. We further looked at the SARL and MARL algorithms the RL agents deploy in forming policies for the environment. The paper finally looked at agents design architecture in SDN and possible research gaps.
2021 Asian Conference on Innovation in Technology (ASIANCON)
2018 IEEE 4th Middle East Conference on Biomedical Engineering (MECBME)
Artificial Intelligence Review
EURASIP Journal on Wireless Communications and Networking, 2022
The integration of Internet of Things devices onto the Blockchain implies an increase in the tran... more The integration of Internet of Things devices onto the Blockchain implies an increase in the transactions that occur on the Blockchain, thus increasing the storage requirements. A solution approach is to leverage cloud resources for storing blocks within the chain. The paper, therefore, proposes two solutions to this problem. The first being an improved hybrid architecture design which uses containerization to create a side chain on a fog node for the devices connected to it and an Advanced Time-variant Multi-objective Particle Swarm Optimization Algorithm (AT-MOPSO) for determining the optimal number of blocks that should be transferred to the cloud for storage. This algorithm uses time-variant weights for the velocity of the particle swarm optimization and the non-dominated sorting and mutation schemes from NSGA-III. The proposed algorithm was compared with results from the original MOPSO algorithm, the Strength Pareto Evolutionary Algorithm (SPEA-II), and the Pareto Envelope-base...
Proceedings on Engineering Sciences, 2022
Technologies, 2022
The move towards intelligent systems has led to the evolution of IoT. This technological leap has... more The move towards intelligent systems has led to the evolution of IoT. This technological leap has over the past few years introduced significant improvements to various aspects of the human environment, such as health, commerce, transport, etc. IoT is data-centric; hence, it is required that the underlying protocols are scalable and sufficient to support the vast D2D communication. Several application layer protocols are being used for M2M communication protocols such as CoAP, MQTT, etc. Even though these messaging protocols have been designed for M2M communication, they are still not optimal for communications where message size and overhead are of much concern. This research paper presents a Lightweight Messaging Protocol (LiMP), which is a minified version of CoAP. We present a detailed protocol stack of the proposed messaging protocol and also perform a benchmark analysis of the protocol on some IoT devices. The proposed minified protocol achieves minimal overhead (a header size...
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 2022
Social Internet of Things (SIoT) involves integrating social networking concepts in the Internet ... more Social Internet of Things (SIoT) involves integrating social networking concepts in the Internet of Things (IoT) to enhance social interactions among IoT objects and users. SIoT is envisaged to provide adequate service selection and discovery. Trust is an essential factor whenever social concepts are discussed in communication networks. Trust usually leads to a mutual relationship between two parties (i.e., the trustor and trustee) where they both enjoy mutual benefits. For secure social relationships, Trust management (TM) is a crucial feature of SIoT. The primary aim of this work is to provide a comprehensive review of trust management proposals/schemes available for SIoT. Four main trust calculation algorithms for trust management were selected for this review, and they were examined in detail. The IEEE Xplore, Scopus, ResearchGate, and Google Scholar databases were searched for articles containing the terms "Trust aggregation approaches in IoT", and "Trust computa...
Engineering Reports, 2020
Emotion detection (ED) is a branch of sentiment analysis that deals with the extraction and analy... more Emotion detection (ED) is a branch of sentiment analysis that deals with the extraction and analysis of emotions. The evolution of Web 2.0 has put text mining and analysis at the frontiers of organizational success. It helps service providers provide tailor-made services to their customers. Numerous studies are being carried out in the area of text mining and analysis due to the ease in sourcing for data and the vast benefits its deliverable offers. This article surveys the concept of ED from texts and highlights the main approaches adopted by researchers in the design of text-based ED systems. The article further discusses some recent state-of-the-art proposals in the field. The proposals are discussed in relation to their major contributions, approaches employed, datasets used, results obtained, strengths, and their weaknesses. Also, emotion-labelled data sources are presented to provide neophytes with eligible text datasets for ED. Finally, the article presents some open issues and future research direction for text-based ED.
International Journal of Computer Applications, 2018
International Journal of Communication Systems, 2017
The security of a wireless sensor network is greatly increased with increasing levels of trustwor... more The security of a wireless sensor network is greatly increased with increasing levels of trustworthiness of nodes on the network. There are a number of trust models proposed that employ various trust evaluation methods. The paper categorises trust evaluation methods for wireless sensor networks into socio-inspired, bio-inspired and analytical methods. Biologically inspired methods and socio constructs are rarely employed in the design of trust schemes as opposed to analytical methods (probability, agent based, fuzzy, etcetera). The paper discusses existing bio-inspired and socio-inspired based trust schemes implemented for wireless sensor networks, viz. Quality-based Distance Vector (QDV) protocol, Enhanced Bio-inspired Trust and Reputation Model for Wireless Sensor Network (EBTRM-WSN), Bio-inspired Trust Routing Protocol (B-iTRP), Machine Learning based Bio-inspired Trust and Reputation Model (MLBTRM), Socio-psychological Trust and Reputation Model, and finally Reputation Framework for Sensor Network (RFSN). A summary of recent trust models (analytical, biological and socio inspired) have been discussed based on their contributions, trust evaluation method, and their limitations was conducted. The pros and cons of analytical, socio and biologically inspired algorithms for computing are outlined in order to easily ascertain the relevance of adopting either biological or socio-inspired approaches for solving trust related problems in wireless sensor networks.
International Journal of Mobile Network Communications & Telematics, 2014
ABSTRACT The widespread nature of wireless computing and communications offers the promise of man... more ABSTRACT The widespread nature of wireless computing and communications offers the promise of many societal and individual benefits. Consumer devices such as cell phones, PDAs and laptops have received a lot of attention over the years, even though the impact of wireless technology is much broader, e.g., through sensor networks for safety applications and home automation, smart grid control, medical wearable and embedded wireless devices, and entertainment systems. These applications have been supported by the rapid developments in wireless technology and standards. One of these wireless technologies is the Worldwide Interoperability for Microwave Access (WiMAX) technology. The WiMAX technology with its growing interest in the West African Sub-Region offers an immerse opportunity in terms of applications and advantages in connecting the Sub-Region to the rest of the world. WiMAX with the promise of about 75Mbps and the numerous opportunities in terms of coverage are yet to be explored for other applications in security, smart grid control, e-learning, telemedicine, e-governance, and home and factory automation. Ghana as pioneer in African Telecommunication has been in the forefront in the deployment of 4G-WiMAX network across the country [1]. An accelerated deployment of broadband personal communication coupled with the continuously increasing demand for large data rates is supposed to reveal an increasing spectrum scarcity, but that is not the case in Ghana.
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 2022
Facial emotion recognition (FER) forms part of affective computing, where computers are trained t... more Facial emotion recognition (FER) forms part of affective computing, where computers are trained to recognize human emotion from human expressions. Facial Emotion Recognition is very necessary for bridging the communication gap between humans and computers because facial expressions are a form of communication that transmits 55% of a person's emotional and mental state in a total face-to-face communication spectrum. Breakthroughs in this field also make computer systems (robotic systems) better serve or interact with humans. Research has far advanced for this cause, and Deep learning is at its heart. This paper systematically discusses state-of-the-art deep learning architectures and algorithms for facial emotion detection and recognition. The paper also reveals the dominance of CNN architectures over other known architectures like RNNs and SVMs, highlighting the contributions, model performance, and limitations of the reviewed state-of-the-art. It further identifies available op...
The number of anchor nodes required for accurate localization is an important problem in the wire... more The number of anchor nodes required for accurate localization is an important problem in the wireless sensor network research community. The error associated with localization is high when anchor nodes are not optimally placed in the network. No matter how the network is set up, the error associated with localization is inevitable. There are various sources for these errors, one of which is the unavailability of anchor nodes. These conditions arise due to stumpy deployment density or poor signal propagation owing to factors like multipath effects, fading effects and poor visibility. This paper proposes a method of determining the minimum number of anchor nodes required for a given sensor (smart energy meter) network dimension using triangulation as the localization process. The proposed method uses the sensitivity of the sensor nodes and various environmental conditions. Using the sensitivity of the sensor nodes and the environmental conditions, the minimum number of anchor nodes fo...
International Journal of Computer Applications, 2014
enterprise networks, the concept of bringing your own devices (BYOD) to work and also allowing gu... more enterprise networks, the concept of bringing your own devices (BYOD) to work and also allowing guest nodes to connect to the network is encouraged. As a factor the need to control access to the network is critical as visibility of nodes attached to the network is paramount in determining potential threats. The use of opensource technology is not mostly patronized by the corporate world because of the steep learning curve and the assumed complexities involved in the use of these software. This paper throws more light on the need for the use of opensource for enterprise networks especially for such networks for developing economies. Three major open source tools (OpenNAC, PacketFence and FreeNAC) are reviewed to provide a mechanism for assessing and selecting an opensource option for your educational network.
Technologies, 2021
The fast emergence of IoT devices and its accompanying big and complex data has necessitated a sh... more The fast emergence of IoT devices and its accompanying big and complex data has necessitated a shift from the traditional networking architecture to software-defined networks (SDNs) in recent times. Routing optimization and DDoS protection in the network has become a necessity for mobile network operators in maintaining a good QoS and QoE for customers. Inspired by the recent advancement in Machine Learning and Deep Reinforcement Learning (DRL), we propose a novel MADDPG integrated Multiagent framework in SDN for efficient multipath routing optimization and malicious DDoS traffic detection and prevention in the network. The two MARL agents cooperate within the same environment to accomplish network optimization task within a shorter time. The state, action, and reward of the proposed framework were further modelled mathematically using the Markov Decision Process (MDP) and later integrated into the MADDPG algorithm. We compared the proposed MADDPG-based framework to DDPG for network...
Wireless technology is increasing rapidly, and the vision of pervasive wireless computing and com... more Wireless technology is increasing rapidly, and the vision of pervasive wireless computing and communications offers the promise of many societal and individual benefits. While consumer devices such as cell phones, PDAs and laptops receive a lot of attention, the impact of wireless technology is much broader, e.g., through sensor networks for safety applications and home automation, smart grid control, medical wearable and embedded wireless devices, and entertainment systems. One of these wireless technologies is the Worldwide Interoperability for Microwave Access (WiMAX) technology. The explosion of wireless applications in some parts of the world has created an ever-increasing demand for more radio spectrum. This is not the case in the West African Sub-Region, especially Ghana where the 2.6GHz and 3.5GHz broadband access bands offering 190MHz and 140MHz bandwidth is underutilized. In this paper, we look at usage of deployed 4G-WiMAX network in Ghana and advocate the need for policy...
The use of trust and reputation models (TRMs) are on the rise due to the increasing complexities ... more The use of trust and reputation models (TRMs) are on the rise due to the increasing complexities of cryptography. The use of cryptography though potent on traditional networks, cannot be supported by the resource constraint wireless sensor network (WSN). Trust evaluations have made use of a number of approaches, such as analytical, bioand socio-inspired methods, in the design of TRMs. The use of socio-inspired methods for TRM design is given less attention though its a simple and effective method. The paper proposes the first sociopsychological TRM simulator (SoTRMSim). The models implemented in SoTRMSim are the consensusaware and privacy-aware sociopsychological TRMs by Rathore and Nunoo-Mensah respectively. The proposed simulator provides an objective way of simultaneously evaluating sociopsychological TRMs.
Security in wireless sensor network (WSN) has become an increasing necessity due to the diverse a... more Security in wireless sensor network (WSN) has become an increasing necessity due to the diverse application areas being implemented. Application areas such as military surveillance and environmental monitoring need to be guided against node tampering and node subversion. Works carried out by wireless sensor network researchers pertaining to increasing the security of the network is significant. Node authentication is a suitable technique against node tampering and the introduction of false nodes. A way of authenticating nodes is by using Message Authentication Code (MAC); this is implemented using hash functions. The limited energy available to sensor nodes, have to be considered when selecting a hash function for implementation. In this paper, comparative analysis of some hash functions (MD-5, SHA-1, SHA-224, SHA-256, SHA-384 and SHA-512) were carried out. The functions were selected based on their popularity. The analysis was done to identify a short-list of hash functions that ca...
International Journal of Advanced Computer Science and Applications
With the exponential increase in connected devices and its accompanying complexities in network m... more With the exponential increase in connected devices and its accompanying complexities in network management, dynamic Traffic Engineering (TE) solutions in Software-Defined Networking (SDN) using Reinforcement Learning (RL) techniques has emerged in recent times. The SDN architecture empowers network operators to monitor network traffic with agility, flexibility, robustness and centralized control. The separation of the control and the forwarding plane in SDN has enabled the integration of RL agents in the networking architecture to enforce changes in traffic patterns during network congestions. This paper surveys major RL techniques adopted for efficient TE in SDN. We reviewed the use of RL agents in modelling TE policies for SDNs, with agents' actions on the environment guided by future rewards and a new state. We further looked at the SARL and MARL algorithms the RL agents deploy in forming policies for the environment. The paper finally looked at agents design architecture in SDN and possible research gaps.
2021 Asian Conference on Innovation in Technology (ASIANCON)
2018 IEEE 4th Middle East Conference on Biomedical Engineering (MECBME)
Artificial Intelligence Review