Conference Publications

Permanent URI for this collection

http://hdl.handle.net/10204/11486

Browse

Now showing 1 - 14 of 14

An Investigation into secure, remote, firmware updating mechanisms for peer-to-peer transactive microgrids
(2025-07) Smith, Andrew C; Ledwaba, Lehlogonolo P
Renewable energy-based microgrid deployments are being identified as potential solutions for faster electrification in developing countries. IoT-enabled microgrids solve the physical infrastructure limitations of connecting communities that are geographically distant from main grid energy supply networks and reduce the added demand placed on the already grid. However, with the deployment of long-term, long-lived IoT technologies, a need for appropriate maintenance and updating strategies is introduced to ensure that the network’s security, integrity, and availability is maintained. Hardware would need to access up-to-date features and patches deployed within newer f irmware iterations without significant interaction and effort from the end user. This work aims to identify, evaluate, and recommend appropriate strategies and solutions for remote IoT firmware updating to be used within transactive microgrid deployments. The solutions considered should be able to maintain the security and integrity of the firmware file during distribution and be able to tolerate the unpredictability of transmission utilizing various communications networks and differing levels of network coverage. The investigation compares and analyses various firmware updating methodologies for lightweight operation, capability of minimising the monetary cost of firmware updating to the end user, and coverage of firmware updating attack vectors As part of future work, the identified firmware mechanisms shall be implemented within a demonstrable microgrid network simulation to assess the performance and latency impacts introduced on microgrid transactions and IoT network processes.
A critical appraisal of various implementation approaches for realtime pothole anomaly detection: Towards safer roads in developing nations
(2023-10) Bello-Salau, H; Onumanyi, Adeiza J; Adebiyi, RF; Adekale, AD; Bello, RS; Ajayi, O
Road infrastructure is essential to national security and growth. Potholes on the road surface causes accidents and costly automotive damage. Novel technology that detects potholes and alerts drivers in real time may address this challenge. These approaches can improve road safety and lower vehicle maintenance cost in resource-constrained developing nations. This study reviews deep learning and sensor-based pothole detection approaches. Analysis shows that deep learning computer vision-based algorithms are most accurate, but computational and economic constraints limit their use in developing nations like Nigeria. Meanwhile, the sensor-based solutions are cost-effective and can be utilized in developing nations for potholes detection.
Evaluating trust models for the IoT-enabled peer to-peer energy market
(2025-07) Leotlela, B; Ledwaba, Lehlogonolo PI; Coetzee, M
The decentralised nature of peer-to-peer (P2P) energy markets creates an environment where trust is difficult to establish. Supported by Internet of Things (IoT) devices, trust and security challenges arise, due to the absence of central oversight and the risk of uncooperative participant behaviour. A comparative analysis of existing trust management models and schemes is conducted in this study comparing how they are designed to encourage cooperation and ensure reliable interactions in decentralized energy markets. Emphasis is placed on how these models integrate security mechanisms to build trust and on their computational efficiency for IoT constrained environments. The analysis highlights the trade offs between trust management and IoT device performance, identifying limitations in scalability and latency as participation scales. Results indicate that while several models effectively build trust and promote cooperation, many impose significant resource demands, underscoring the need for balance between trust assurance and operational efficiency. This work provides a comprehensive evaluation of trust mechanisms in transactive energy systems and offers insights into their practical viability in resource-constrained, decentralized environments.
An experimental investigation into high bandwidth wireless communication standards for the underground mine stope
(2023-09) Chetty, Brenton L; Isaac, Sherrin J; Walingo, T
There are many challenges associated with developing a feasible wireless communication system for the harsh underground mining environment. Radio signals suffer from strong attenuations due to the excessive reflections, diffractions, scatterings, and multipath caused by the irregular surface characteristics of the stope. This necessitates the need for a robust underground mine wireless communication network that can withstand these phenomena. The network will still need to provide enough bandwidth for productivity enhancement applications as well as maintain low latency alongside robustness for critical mine safety applications. Coded OFDM (COFDM) was identified as the wireless standard for dealing with the harsh mining environment. However, due to the standard not being mainstream, the implementation of such a system will be extremely expensive. This research identifies the possibility of utilising Wi-Fi6 (802.11ax) which utilizes Orthogonal Frequency Division Multiple Access (OFDMA) as a more cost-effective alternative as compared to COFDM. Experimental investigations for comparing COFDM and Wi-Fi6 have been conducted in terms of latency, jitter and throughput measurements in several different topology and configurations. The uncoded Wi-Fi6 was found to be quite capable for high bandwidth productivity enhancement applications for the stope at an economical price point as compared to the more robust COFDM. Hence the more expensive COFDM should only be deployed for the critical mine safety applications.
Exploratory analysis of modified deep learning model for potholes data augmentation
(2025-04) Adebiyi, RF; Bello-Salau, H; Onumanyi, Adeiza J; Adebiyi, BH; Adekale, AD; Bello-Salahuddeen, R
A major factor contributing factor resulting to a large proportion of vehicular-related traffic accidents in developing nations is the poor condition of road networks, characterized by potholes, bumps, and other anomalies. Despite efforts by authorities to address these issues, they persist. A new approach involves equipping vehicles with sensors to detect road anomalies, enabling drivers to make informed decisions. Various models using road surface images to detect and classify these anomalies have been proposed, with recent methods leveraging deep learning. The effectiveness of these models depends on the presence of abundant and well-labelled training datasets. To address this need, a modified Deep Denoising Diffusion Probabilistic Model (mDDPM) was proposed, enhancing the U-Net backbone architecture to improve the original DDPM's performance in augmenting pothole images. The mDDPM generates more diverse augmented images, evaluated through subjective and objective assessments, including the Fréchet Inception Distance (FID) score. Experimental results showed that 98% of participants could not distinguish between real and synthetic images, classifying the augmented images as real. Additionally, an FID score of 0.52 indicated that the augmented images closely resemble real pothole images. This demonstrates the model's effectiveness in generating training data for deep learning models aimed at road anomaly detection and classification, contributing to the development of robust models for detecting and classifying potholes and other road anomalies.
Gas sensing materials roadmap
(2021-06) Wang, H; Ma, J; Zhang, J; Feng, Y; Vijjapu, MT; Yuvaraja, S; Surya, SG; Salama, KN; Tshabalala, ZP; Akande, Amos A
Gas sensor technology is widely utilized in various areas ranging from home security, environment and air pollution, to industrial production. It also hold great promise in non-invasive exhaled breath detection and an essential device in future internet of things. The past decade has witnessed giant advance in both fundamental research and industrial development of gas sensors, yet current efforts are being explored to achieve better selectivity, higher sensitivity and lower power consumption. The sensing layer in gas sensors have attracted dominant attention in the past research. In addition to the conventional metal oxide semiconductors, emerging nanocomposites and graphene-like two-dimensional materials also have drawn considerable research interest. This inspires us to organize this comprehensive 2020 gas sensing materials roadmap to discuss the current status, state-of-the-art progress, and present and future challenges in various materials that is potentially useful for gas sensors.
Interconnected smart transactive microgrids—A survey on trading, energy management systems, and optimisation approaches
(2024-03) Machele, IL; Onumanyi, Adeiza J; Abu-Mahfouz, Adnan MI; Kurien, AM
The deployment of isolated microgrids has witnessed exponential growth globally, especially in the light of prevailing challenges faced by many larger power grids. However, these isolated microgrids remain separate entities, thus limiting their potential to significantly impact and improve the stability, efficiency, and reliability of the broader electrical power system. Thus, to address this gap, the concept of interconnected smart transactive microgrids (ISTMGs) has arisen, facilitating the interconnection of these isolated microgrids, each with its unique attributes aimed at enhancing the performance of the broader power grid system. Furthermore, ISTMGs are expected to create more robust and resilient energy networks that enable innovative and efficient mechanisms for energy trading and sharing between individual microgrids and the centralized power grid. This paradigm shift has sparked a surge in research aimed at developing effective ISTMG networks and mechanisms. Thus, in this paper, we present a review of the current state-of-the-art in ISTMGs with a focus on energy trading, energy management systems (EMS), and optimization techniques for effective energy management in ISTMGs. We discuss various types of trading, architectures, platforms, and stakeholders involved in ISTMGs. We proceed to elucidate the suitable applications of EMS within such ISTMG frameworks, emphasizing its utility in various domains. This includes an examination of optimization tools and methodologies for deploying EMS in ISTMGs. Subsequently, we conduct an analysis of current techniques and their constraints, and delineate prospects for future research to advance the establishment and utilization of ISTMGs.
Investigating distance bounding for delegated proof-of-proximity consensus within IIoT
(2022-06) Ledwaba, Lehlogonolo PI; Hancke, GP; Isaac, Sherrin J
With limited processing, energy and storage along with a deadline sensitive operational environment, the combination of the Industrial IoT (IIoT) with distributed ledger technologies (DLTs) could serve to introduce intolerable latency into network processes; counteracting the potential advantages that come from combining the two technologies. In an effort to improve the compatibility of DLTs for the industrial informatics context, the authors developed a lightweight consensus for IIoT environments based off delegated proof of stake (DPoS), called Delegated Proof of Proximity (DPoP), to limit the processing and energy effort required by DLTs. DPoP will, however, require an existing, IIoT neighbour discovery process to facilitate a proof of proximity for the consensus process. Thus, this preliminary work aims to evaluate distance bounding as a possible mechanism for establishing a secure proof of proximity and neighbour discovery between nodes during the DPoP consensus process to improve the scalability and flexibility of DLT solutions, like Ethereum, for IIoT use cases.
A micro grid information architecture with open source components
(2021-12) Smith, Andrew C; Mkhize, Cyprian B; Mahlobo, Boitumelo T; Isaac, Sherrin J
Presented is an information system architecture based on open source platforms to support the successful management of a micro grid. The paper justifies the use of open source platforms in the micro grid context. Also given are the benefits of a micro grid as it relates to distributed energy generation and subsequently the need explained for an information system that keeps a record of all devices and their interconnections, while simultaneously providing access to instantaneous data along various points in the micro grid. Three examples of services made possible by the architecture are given.
Mitigating the rock fall and rockburst risk in South African gold and platinum mines through advanced knowledge of the ore body
(2023-10) Pienaar, M; Durrheim, RJ; Manzi, MSD; Nwaila, GT; Grobler, HCI; Kgarume, Thabang E; Pretorius, Dean D; Van Schoor, Michael; Oberholster, AJ
The Mandela Mining Precinct was launched in 2018 with the goal of modernizing the South African mining industry. It comprises three major initiatives that seek to improve efficiency, health and safety in current mining operations; develop fully mechanized systems to mine narrow tabular ore bodies in hard rock; and develop non-explosive rock-breaking systems. The crosscutting Advanced Orebody Knowledge (AOK) program seeks to develop technologies to characterize the rock mass ahead of mining and identify potentially hazardous geological features. Mining methods, layouts and rock support systems will be adjusted accordingly to mitigate the risk of rock falls and bursts. Technologies include rock drilling, light detection and ranging (LiDAR), ground penetrating radar (GPR), electrical resistance tomography (ERT), and various acoustic, thermographic and seismic techniques. Machine learning methods are being implemented to improve data processing and interpretation. This paper describes the status of the research program at 31 May 2023.
Optimizing SVM hyperparameters for breast cancer data classification using Hybrid Particle Swarm Optimization
(2024-05) Sulaiman, AT; Bello-Salau, H; Onumanyi, Adeiza J; Salawudeen, AT
The classification efficacy of Support Vector Machines (SVMs) heavily relies on hyperparameter selection, and optimizing parameters such as kernel type and regularization is particularly challenging due to the non-convex nature of the SVM objective function. In response to this challenge, we introduce a novel approach, the trailPSO technique, which combines Particle Swarm Optimization (PSO) with Smell Agent Optimization (SAO) to achieve a balance between exploration and exploitation. The trailPSO algorithm is applied to optimize SVM hyperparameters, resulting in the trail PSOSVM model. We assess the performance of trailPSOSVM by employing it to classify breast cancer datasets, revealing superior outcomes compared to conventional methods. Notably, the proposed approach attains 100% accuracy with zero errors, showcasing its ability to identify optimal hyperparameter settings for enhanced classification accuracy and robustness. This study is part of an ongoing efforts towards extending the trailPSO algorithm for sentiment analysis and addressing imbalanced datasets in the realm of natural language processing.
Performance analysis of machine learning classifiers for pothole road anomaly segmentation
(2021-06) Bello-Salau, H; Onumanyi, Adeiza J; Adebiyi, RF; Adedokun, EA; Hancke, Gp
Recently, machine learning (ML) classifiers are being widely deployed in many intelligent transportation systems towards improving the safety and comfort of passengers as well as to ease and enhance road navigation. However, the comparative performance analyses of different ML classifiers within the confines of road anomaly detection remain unexplored under some specific capture conditions such as bright light, dim light, and hazy image conditions. Consequently, this paper investigates the performance of six different state-of-the-art ML classification algorithms, viz: random forest, JRip, One-R,naive Bayesian, J48, and AdaBoost for segmenting pothole road anomalies under three different environmental conditions viz: bright, dim, and hazy light conditions. The results obtained suggest that either the J48 random forest or JRip classifiers are suitable for classifying pothole anomalies captured under broad day light (bright light) conditions with an average accuracy performance of 95%. On the other hand, the One-R classifier sufficed as more suitable for use under hazy image condition yielding an average accuracy of 73%, whereas the random forest algorithm yielded the best classification accuracy of 55%under dim light conditions. These results are helpful particularly towards determining the best ML classifiers for use towards developing robust artificial intelligence-based real-time algorithms for detecting and characterizing road anomalies effectively in autonomous vehicles.
Transactive energy: State-of-the-art in control strategies, architectures, and simulators
(2021-09) Onumanyi, Adeiza J; Isaac, Sherrin J; Kruger, Carel P; Abu-Mahfouz, Adnan MI
The concept of transactive energy (TE) in smart grid systems is gaining increased research attention for its potential to optimize distributed energy resources, improve system reliability, as well as provide a balanced ecosystem for fair economic transaction between prosumers. TE is defined by the GridWise Architecture Council as a system of economic and control mechanisms that allows the dynamic balance of supply and demand across the entire electrical infrastructure using value as a key operational parameter. With control mechanisms being a key part of TE systems, in this article, we discuss the state-of-the-art in TE control strategies, architectures, and relevant simulators for designing, evaluating, and analysing TE systems. Most importantly, existing TE control strategies are examined and discussed via a hierarchical structure comprising four different levels wherein TE control strategies/controllers can be deployed. Architecturewise, we highlight the different types of TE architectures including the centralized, decentralized, distributed, and hierarchical architecture. In terms of existing and potential simulators for designing and evaluating TE models, we discuss and compare notable software across different characteristics of interest. We conclude this article by highlighting the basic components of a typical TE controller and other future research directions spanning across security concerns, privacy issues, communication challenges, simulation and validation demands. As a main contribution, different from existing survey articles, this article presents a synthesis of existing works regarding TE control strategies, architectures, and TE-based simulators for the benefit of the budding researcher whose interest may lie in the study of TE systems.
Trust requirements and mechanisms in peer-to-peer energy markets
(2024-11) Leotlela, Boitumelo; Ledwaba, Lehlogonolo PI; Coetzee, M
Peer-to-peer (P2P) energy markets are emerging as a promising solution to address the challenges faced by traditional energy systems. However, the decentralised nature of these markets necessitates robust trust mechanisms to ensure secure and reliable energy transactions. This paper presents a comprehensive review of trust requirements and trust-building mechanisms in P2P energy markets. It explores the role of blockchain technology, zero-trust architecture, and reputation systems in establishing trust among market participants. It identifies several trust requirements, including security, privacy, transparency, fairness, and reputation. The study further highlights the limitations of existing works and proposes future research directions to enhance trust and security in P2P energy markets. By addressing these limitations, the full potential of P2P energy trading can be unlocked, contributing to a more sustainable and resilient energy future.

Browse

Browsing Conference Publications by browse.metadata.impactarea "Advanced Internet of Things"

Results Per Page

Sort Options