44 research outputs found
Optimization of hybrid renewable energy generation using a nature-inspired algorithm with advanced IoT analytics
No full textSubmitted in fulfillment of the requirements of the degree of Doctor of Philosophy in Information Technology (IT) at Durban University of Technology, Durban, South Africa, 2022.A stable and cost-effective power supply in an autonomous hybrid energy system requires
an efficient design process for renewable energy technologies. Accordingly, the best
design of a standalone hybrid renewable energy system (HRES) should consider several
factors such as renewable energy data, load profile, technical and economic analysis of the
renewable technologies, ideal location for the power system, etc. Different data from
renewable energy sources are modelled into an optimization problem which incorporates
the crucial point, in HRES, of the correct sizing of the various power components, which
directly affect the cost and power security/reliability of the system. This thesis proposes an
innovative meta-heuristic optimization algorithm called Social Spider-Prey (SSP) that
mimics the foraging behaviour of social spiders and prey(s) on the social web. By
examining the foraging behavioural traits of social spiders and prey(s), a global
optimization algorithm was developed to solve a hybrid renewable energy optimization
problem of correct sizing, minimal cost, and highest reliability. In SSP, artificial spiders
are considered search agents. On the one hand, every spider can freely roam the social
web, a hyperdimensional search space, to implement an exploratory search scheme. On the
other hand, nearby spiders relative to a captured prey search the neighbourhood, which is
implemented as an exploitative search mechanism. These two search strategies are
harmonized in SSP to solve the multi-source renewable power generation optimization
problem effectively. Four different power generation scenarios were analysed to determine
optimal power generation using experimental real-time environment data collected with
sensors and secondary data retrieved from a benchmark dataset, National Renewable
Energy Laboratory (NREL). The optimization algorithms inspired by nature, namely
Social Spider-Prey (SSP), Particle Swarm Optimization (PSO), Teaching-Learning Based
Optimization (TLBO) algorithm and Social Spider Algorithm (SSA), were used in a
comparative study to search for a near-optimal result for the hybrid system configuration
that satisfies the optimization problem. The results show the economic and reliable
implications of different system configurations that meet the specified combined criteria,
as indicated in the HRES optimization problem, to make the best investment decision. The
SSP guaranteed optimal annualized system costs and met the reliability constraints for all
the case scenarios: wind/biomass/battery (ZAR 3,431,512.26 and LPSP of 0.011),
PV/wind/ biomass (ZAR 2,549,792.71 and LPSP of 0, 0011), PV/biomass/battery (ZAR1,
638,628.82 and LPSP of 0.00021) and PV/wind/biomass/battery (ZAR1, 412,142.80 and
LPSP of 0.0141). Based on this result, the study proposes the SSP as an optimization
approach for the solar PV/wind/biomass/battery hybrid system, as it ensures 99.98% power
reliability. In addition, a Kruskal-Wallis test was performed to determine the significant
differences among the comparison algorithms.
Bio-inspired optimisation of a new cost model for minimising labour costs in computer networking infrastructure
No full textSubmitted in fulfillment of the requirements of the degree of Doctor of Philosophy in Information Technology (IT), Durban University of Technology, Durban, South Africa, 2024.This thesis revolves around the bio-inspired optimisation of a newly formulated cost model tailored for initial installation of a user-specified computer networking infrastructure, motivated by requirements of networking industries, with a focal point on minimising labour costs. The new cost function of this infrastructure installation incorporates essential decision variables related to labour, encompassing the daily requirements and costs of both skilled and unskilled workers, their respective hourly rates, installation hours, and the overall project duration. This deliberate emphasis on labour-centric factors aim to offer nuanced insights into the intricacies of project budgeting and resource allocation. The research critically evaluates the effectiveness of the cost function by examining various factors, such as daily fixed costs, a size and complexity factor tailored to individual scenarios, and a penalty coefficient aimed at ensuring compliance with project schedules. Significantly, the deliberate exclusion of equipment, material, maintenance and operational costs underscores the focused examination of labour-related expenditures, providing a unique contribution to the optimisation landscape within the installation of the user-specified computer networking infrastructure projects. Utilising advanced bio-inspired optimisation techniques, alongside real-world data, this study endeavours to gauge the effectiveness of the new cost model in minimising labour expenses while upholding optimal network performance. The anticipated outcomes of this study extend beyond theoretical contexts to practical implications, providing actionable insights and recommendations for network infrastructure planners. The significance of labour-centric considerations in project planning and design is underscored, providing a more encompassing perspective that aligns with the evolving landscape of modern technological infrastructures. By giving attention to labour-intensive aspects within installation of computer networking infrastructure projects, the thesis aspires to enhance budgeting accuracy and streamline resource allocation processes, thereby fostering more efficient and cost-effective project outcomes.
Meta-heuristic search methods for big data analytics and visualization of frequently changed patterns
No full textSubmitted in fulfilment of the requirements of the degree of Doctor of Philosophy in Information Technology (IT), Durban University of Technology, Durban, South Africa. 2019.Throughout the world, data plays a prominent role in making decisions relevant to the socio-economic growth of organizations. As organizations grow, they tend to use diverse technologies or platforms to collect data and make data readily available for quick decision-making. These technologies have resulted in exponential growth of data whereby the problem of managing this data in a limited time interval increases in complexity, starting from the preprocessing stage to the visualization stage. Apart from the issue of managing the huge growth of data, finding a suitable method to manage certain aspects of this frequently changed data has been overlooked. These frequent changes in data form the topic of interest of this thesis. Consequently, there is a need to develop a framework both to manage big data at different stages of processing, from preprocessing to visualization, and to handle frequently changed data. The need to develop such a framework arises because traditional methods/algorithms are limited to finding frequent patterns of frequently occurring items while overlooking frequently changed data, which has a numeric and time dimension that can provide interesting business insights. Additionally, traditional visualization methods are challenged with performance scalability and response time. This thesis looked at resolving this limitation by using a meta-heuristic/bio-inspired algorithm that is modelled based on observation of the behavior and characteristics of two different animals, namely the kestrel and the dung beetle. The motivation behind the use of these animals is their ability to explore, exploit and adapt to different situations in their natural environment. The development of the computational model and testing with actual data were formulated as a six-step procedure. Based on the six steps, the proposed computational model was evaluated against selected comparative algorithms, namely BAT, WSA-MP, PSO, Firefly and ACO. The main findings on optimal value/results suggest that, in handling frequently changed data during the data preprocessing, pattern discovery and visualization stages, the proposed computational models performed optimally against the comparative meta-heuristic algorithms on test datasets. Further statistical tests, using the Wilcoxon signed rank test, were conducted on optimal results from the comparative meta-heuristic algorithms. The basis for using the statistical procedure was to select the best choice of algorithm without making any underlying assumption on accuracy of results from the comparative meta-heuristic algorithms. Theoretically, the study contributes to enhancing frequency of item frameworks by including time and numeric dimensions of item occurrence. Practically, the contribution of the study lies in its finding frequently changed patterns in big data analytics. Additionally, the concept of half-life of substances/trails was applied as part of the computational model, and this also forms part of the unique contribution of this thesis. The half-life constitutes the lifetime of interestingness of recent patterns that were discovered. In summary, this thesis is about the mathematical formulation of animal behavior and characteristics into an implementable big data management algorithm and its application to frequently changed patterns.
Kestrel-Based Search Algorithm for Association Rule Mining and Classification of Frequently Changed Items
No full textNature inspired approaches have been used in the design of computer solutions for real life problems. These computer solutions take the form of algorithms which characterize specific behaviour of animals or birds in their natural habitat. The two bio-inspired computational concepts in modern times includes evolutionary and swarm intelligence. A novel introduction to the bio-inspired computational concepts of swarm behaviour is the study of characteristics of kestrel birds. The study presents, as a concept paper, a meta-heuristic algorithm called kestrel-based search algorithm (KSA) for association rule mining and classification of frequently changed items on big data environment. This algorithm aims to find best possible rules and patterns in dataset using minimum support and minimum confidence.Copyright: 2016. IEEE. Due to copyright restrictions, only the abstract is available. For access to the full text item, please consult the publisher's website. The definitive version of the work is published in 2016 8th International Conference on Computational Intelligence and Communication Networks. IEEE, 356-360. DOI 10.1109/CICN.2016.7
Health Information System and Health Care Applications Performance in the Healthcare Arena: A Bibliometric Analysis
No full textThere have been several studies centred on health information systems with many insights provided to enhance health care applications globally. These studies have provided theoretical schemes for fortifying the enactment and utilisation of the Health Information System (HIS). In addition, these research studies contribute greatly to the development of HIS in alignment with major stakeholders such as health practitioners and recipients of health care. Conversely, there has been trepidation about HIS’ sustainability and resilience for healthcare applications in the era of digitalization and globalization. Hence, this paper investigates research on HIS with a primary focus on health care applications to ascertain its sustainability and resilience amidst the transformation of the global healthcare space. Therefore, using a bibliometric approach, this paper measures the performance of health information systems and healthcare for health care applications using bibliometric data from the web of science database. The findings reveal solid evidence of the constructive transformation of health information systems and health care applications in the healthcare arena, providing ample evidence of the adaptation of HIS and health care applications within the healthcare arena to the fourth industrial revolution and, additionally, revealing the resilient alignment of health care applications and health information systems
