Benjamin Kommey | Kwame Nkrumah University of Science and Technology (original) (raw)

Papers by Benjamin Kommey

IT journal research and development, Feb 15, 2024

IET smart cities, Jan 24, 2024

Energy profligacy and appliance degradation are the apex reasons accounting for the continuous ri... more Energy profligacy and appliance degradation are the apex reasons accounting for the continuous rise in power wastage and high energy bills. The decline in energy conservation and management in residences has been largely attributed to the financial implications of using intrusive methods. This work aimed to resolve the challenges of intrusive load monitoring by introducing artificial intelligence and machine learning to optimise load monitoring. To solve this challenge, a non-intrusive approach was proposed where modalities for load prediction and classification were achieved with a Bagging regressor and a modified multiclass K-Nearest Neighbour algorithms. This developed supervised learning models produced a 0.9624 R 2 score and 78.24% accuracy for prediction and classification, respectively, when trained and tested on a Dutch Residential Energy Dataset. This work seeks to provide a cost-effective approach to the optimisation of energy using steady state active power features. Essentially, the adoption of this nonintrusive technique for load monitoring would effectively aid customers on the distribution network save cost on energy bills, facilitate the detection of faulty appliances, provide recommendations for smart homes and buildings with the required information for efficient decision making and planning of energy needs. In the long term, easing the pressure on power generation to meet demand would translate to reduction in carbon emissions based on a wide-scale implementation of this proposed system. Hence, these are important parameters in realising the development of smart sustainable cities and sustainable energy systems in this current industrial revolution. K E Y W O R D S artificial intelligence, data analytics, data structures and machine learning, smart cities, smart cities applications, smart power grids 2-KOMMEY ET AL.

IET networks, Dec 5, 2023

The enhanced capacity of optical networks is a significant advantage within the global telecommun... more The enhanced capacity of optical networks is a significant advantage within the global telecommunications industry. Optical networks provides transmission of information over large distances with reduced latency. However, the growing intricacy of network topologies poses a significant challenge to network adaptability, network resilience, device compatibility, and service quality in the contemporary era of technology and 5G networks. In light of these challenges, recent studies leverages on disaggregation in the context of Software Defined Network (SDN) and network service orchestrators as a viable remedy. Disaggregated optical systems offer SDON (Software-Defined Optical Networking) enhanced control options and third-party dynamism streamlining upgrades and diminishing single vendor dependency. Although, the advancement of disaggregation improves network flexibility and vendor neutrality of Software Defined Optical Networking (SDON), this improvement comes at the cost of reduced scalability and network controllability performance. The current research paper posits two potential resolutions to the aforementioned challenge. The authors present recommendations and an enhanced architecture that leverages Open Network Operating System (ONOS) containers and Kubernetes orchestration to improve scalability inside the Software-Defined Optical Networking (SDON) architecture. The suggested architectural design has underlining novel flow charts and algorithms that enhances scalability performance by 33% while also preserving flexibility and controllability in comparison to pre-existing SDON architectures. This architecture also makes use of the Mininet-Optical physicallayer architecture to simulate a real-time scenario, as well as yang models from the Open Disaggregated Transport Network (ODTN) working group, the pioneers of SDONs. A detailed analysis of the rules and procedural processes involved in the implementation of the proposed architecture. In order to demonstrate the practical application of this architectural framework to a real-world Software-Defined Optical Network (SDON) system, the pre-existing SDON ONOS architecture within the Optical Transport Domain Networking (OTDN) working group was adjusted and refined. This adaptation aimed to illustrate the use of ONOS in conjunction with established optical network systems, highlighting the advantages it offers. K E Y W O R D S optical communication, software defined networking This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Jordan journal of electrical engineering, Dec 31, 2022

Speech is the most complex part or component of human intelligence and for that matter speech sig... more Speech is the most complex part or component of human intelligence and for that matter speech signal processing is very important. The variability of speech is very high, and this makes speech recognition difficult. Other factors like dialects, speech duration, context dependency, different speech speed, speaker differentiation, environment and locality all add to the difficulty in speech processing. The absence of distinct boundaries between tones or words causes additional problems. Speech has speaker dependent characteristics, so that no one can reproduce or repeat phrases in the same way as another. Nevertheless, a speech recognition system should be able to model and recognize the same words and phrases absolutely. Digital signal processors (DSP) are often used in speech signal processing systems to control these complexities. This paper presents a Hidden Markov Model (HMM) based speech signal modulation through the application of the Baum-Welch, Forward-Backward and Viterbi algorithms. The system was implemented using a 16-bit floating point DSP (TMS320C6701) from Texas instruments and the vocabulary was trained using the Microsoft Hidden Markov Model Toolkit (HTK). The proposed system achieved about 79% correct word recognition which represents approximately 11,804 correct words recognized out of a total of 14960 words provided. This result indicates that the proposed model accuracy and speaker independent system has a very good evaluation score, and thus can be used to aid dictation for speech impaired persons and applications in real time with a 10 ms data exchange rate.

International Journal of Applied Sciences and Smart Technologies, Dec 25, 2023

The development of Software Defined Networking (SDN) has altered the landscape of computer networ... more The development of Software Defined Networking (SDN) has altered the landscape of computer networking in recent years. Its scalable architecture has become a blueprint for the design of several advanced future networks. To achieve improve and efficient monitoring, control and management capabilities of the network, software defined networks differentiate or decouple the control logic from the data forwarding plane. As a result of this, logical control is solely centralized in the controller. Due to the centralized nature, SDNs are exposed to several vulnerabilities such as Spoofing, Flooding, and primarily Denial of Service (DoS) and Distributed Denial of Service (DDoS) among other attacks. In effect, the performance of SDN degrades based on these attacks. This paper presents a comprehensive review of several DoS and DDoS defense/mitigation strategies and classifies them into distinct classes with regards to the methodologies employed. Furthermore, based on the discussions raised, suggestions have been made to enhance current mitigation strategies accordingly.

JOIN (Jurnal Online Informatika), May 24, 2024

The significant contributions of information and communication technology (ICT) and other operati... more The significant contributions of information and communication technology (ICT) and other operational technologies (OTs) or cyber networks have had a tremendous impact on the real-time monitoring, management, and control of the power or energy system facilities. Thus, the integration of these technologies into the energy grid system created a smart, complex, and interdependent system. This system is established and referred to as a smart grid cyber physical power system (SGCPPS). The performances of cyber physical systems are achieved via computation and communication and are imperatively based on a realtime feedback mechanism. In reference to the energy system, monitoring and control of the grid systems is extremely essential in ensuring efficient power supply, quality, reliability, stability and resilience among other determinants. However, their interdependence and integrated nature exposes the grid to disturbances subsequently leading to faults in the grid. Hence, failure to know the grid conditions at a particular period subjugates it to complete system collapse. This paper focused on the development of a mathematical model for a smart grid cyber physical system. Additionally, simulations were performed to study the behaviour of the Smart grid cyber-physical power system (SGCPPS) with regards to monitoring and controlling the physical systems using MATLAB Simulink tool to facilitate system awareness.

A solar tracking system is used to orient solar reflectors, photovoltaic panels, and other solar ... more A solar tracking system is used to orient solar reflectors, photovoltaic panels, and other solar energy harvesting equipment toward the sun mainly to maximize energy output. The LEESOLA system offers an optimized way to increase the amount of energy produced by exposing the harvesting equipment to the sun's rays. This project is a crucial step towards a more sustainable future and reducing the reliance of humans on traditional energy sources. The system architecture of the LEESOLA solar tracker consists of a microcontroller-based control unit, an ultraviolet (UV) sensor module, motor drivers and PV panels. The UV sensor module detects the location of the sun and sends signals to the control unit. The control unit then passes signals to the motor drivers to introduce a change in the position of the solar panels. The control unit makes use of a suitable algorithm for keeping track of the location of the sun throughout the day and changes the angle of the PV panels accordingly. The UV sensor module makes use of essential optoelectronic components such as photodiodes or phototransistors to detect the position of the sun accurately. As a measure of eliminating any occurrence of misalignment due to factors such as weather conditions, the system has a built-in feedback mechanism that actively monitors the solar panel's position and adjusts the motor drivers to correct any misalignment. The proposed system obtained an improvement of about 69.29%, 59.41% and 184.96% mean percentage difference in the measured power readings for morning, afternoon, and evening durations respectively. Therefore, this LEESOLA system provided an all-rounded performance improvement over the limiting static methods.

Reinforcement Learning (RL) is fast gaining traction as a major branch of machine learning, its a... more Reinforcement Learning (RL) is fast gaining traction as a major branch of machine learning, its applications have expanded well beyond its typical usage in games. Several subfields of reinforcement learning like deep reinforcement learning and multi-agent reinforcement learning are also expanding rapidly. This paper provides an extensive review on the field from the point of view of Machine Learning (ML). It begins by providing a historical perspective on the field then proceeds to lay a theoretical background on the field. It further discusses core reinforcement learning problems and approaches taken by different subfields before discussing the state of the art in the field. An inexhaustive list of applications of reinforcement learning is provided and their practicability and scalability assessed. The paper concludes by highlighting some open areas or issues in the field.

IJASST, 2023

Journal of Innovation Information Technology and Application, Jun 30, 2022