Photovoltaic (PV) power1 as a source of renewable energy is inherently uncertain due to atmospheric and environmental variables. This uncertainty has, however, not disqualified PV power from attaining commercial success as is evident from the most recent REN21 Global Status Report. The report shows the extent of the contribution made by utility-scale PV-power systems to electrical grids around the world and highlights that “installed power capacity grew more than 200 gigawatts (GW) (mostly solar photovoltaics, PV” in 2019. The exact modelling and forecasting of the power output of PV systems are therefore critical to effectively manage their integration in smart grids, delivery, and storage. In recent years, PV power forecasting has further advanced to become an extremely active research field. 1. The main research objectives 2. Methodology 3. Conclusion Furthermore, as PV system power supply is characteristically intermittent, PV forecasting is essential for decision-makers overseeing electrical grid stability. However, as commercial PV systems increase in physical size, so does the non-uniform exposure for different PV-module segments within the PV system. Since almost all published PV forecasting models are based on a conventional macro-level forecasting approach, there is reason to question the ability of these solutions to capture low-level power dynamics.
As 2021 dawns, we look back at some of the interesting, ground-breaking, and innovative projects our Department was involved and/or students from our Faculty completed. Here are some noteworthy highlights: Cooperative collision avoidance for unmanned aerial vehicles Reinforcement Learning in the Minecraft Gaming Environment High-altitude balloon missions conducted by final-year E&E engineering students Using a hidden Markov model to detect inshore Bryde’s whale short pulse calls Spinning solar sail: Solar Sailing Missions Electric vehicles could reduce carbon emissions without straining electricity grid using solar photovoltaic charging systems Faculty of Engineering researches microwave irradiation as an alternative form of sterilisation for Rooibos tea Department of Electrical and Electronic Engineering partners with Mexican Institute for K-band expansion studies Innovative finger-prick test for the early detection of cancer Save the rhino – Stellenbosch University conducts ground-breaking research to find a durable solution
Similar to technologies that initially started at a military base, unmanned aerial vehicles (UAVs) will soon be affecting civilian life. To date, several industries have built and commercially supplies low-end UAVs technologies for various non-military purposes. However, most of these UAVs are recreational and remote-controlled toys that only fly in secluded areas with minimum impact on the airspace. However, the rate at which technology is advancing, civilian UAVs are no longer restricted to creational use. Despite advancements, the existing collision avoidance systems that are currently regulated within the civilian airspace were unable to integrate both manned and unmanned aircraft. The research discussed in this post therefore presents the design, implementation, and verification of two types of cooperative collision avoidance algorithms for UAVs in multi-aircraft conflict scenarios.
Reinforcement Learning in the Minecraft Gaming Environment 1. Introduction Researchers are keen to solve the challenge of a robot successfully interacting with an external environment. In this regard, the progress made in reinforcement learning (RL), such as Atari 2600 from Google DeepMind, Alpha Go winning the current world champion in the board game Go, and OpenAI winning a 5v5 match against the top players in the world in Dota 2, RL has become a powerful tool to achieve superhuman results in games. RL agents appear to be able to master any game, but what about a game such as Minecraft. The long-term objective of this research is to use RL to teach an agent to survive a day-night cycle in the Minecraft gaming environment. To achieve this, the research tests a new method, referred to as dojo learning based on curriculum learning, against current methods to progress one step closer to the mentioned objective. Although Minecraft is used as a testing platform, the method investigated in this thesis could be generalised and adapted to work in any appropriate gaming environment.
The Electric and Electronic Engineering Department at Stellenbosch University has an ongoing programme of high-altitude balloon (HAB) missions to conduct experiments in near-space conditions. The use of HAB payloads provides many of the same benefits as a low Earth orbit satellite for a fraction of the cost.
As the interest in studying cetaceans’ sounds increases, so has the motivation to develop different automated sound detection and classification methods. One such technique is passive acoustic monitoring (PAM) which was discussed in our previous post. PAM is used extensively to study cetaceans’ sounds over a predetermined period to understand their daily activities within their ecosystem. However, when using PAM, the collected sound datasets are usually large and impractical to manually analyse and detect.
The Department of Science and Technology’s Marine Research Plan focuses on understanding the role of biodiversity in maintaining ecosystems’ functionality, the relationships between human pressures and ecosystems, and the impact of Global Change on marine ecosystems. The Research Plan identified specific research themes including oceans and marine ecosystems under global change, ecosystems, biodiversity and biodiscovery, and coastal and marine resources, society and development. Investigating and developing signal processing algorithms for underwater acoustic signals to detect, classify and track cetaceans forms part of the third theme of the Plan. There are some challenges to monitoring cetacean populations Addressing the challenges Conclusion A good representation of overall marine ecosystem health is evident from the abundance and state of marine mammal populations. Nevertheless, various factors including climate change and human activities can affect these ecosystems. However, the effective monitoring and management of marine living resources – where these living organisms inhabit a vast, mainly inaccessible and hostile environment – requires innovation and the use of the best available technologies and methods.
The soundscapes of our oceans have undergone substantial changes as a result of human anthropogenic activities. This, in turn, threatens the existence of ocean mammals such as the Bryde’s whale, as they use sound to navigate, communicate, avoid predators, recognise prey for survival and function properly within their ecosystem. Anthropogenic activities include shipping, offshore exploration, geophysical seismic surveys, and naval sonar operations. These activities have been detrimental to marine fauna and caused, amongst others, physical injury, physiological dysfunction, and behavioural modification. Overall, it caused a decrease in reproduction rate. Nevertheless, very little information regarding the population dynamics and taxonomic status of Bryde’s whales exists. Recent research strongly suggests that the two ecotypes, namely the resident inshore Bryde’s whale and the seasonal offshore Bryde’s whale, can be split at a species level. This can have far-reaching implications, putting the inshore Bryde’s whale species at a real and substantial risk of extinction.
Our blog series on solar sail technology commenced with a brief overview and introduction to solar sailing as well as the controlling mechanisms of sailcrafts followed by an investigation of the deployment of a spinning solar sail, its theoretical dynamics and its practical aspects. In this final post, we look more closely at some of the different sail satellites that have been deployed successfully. Interplanetary Kite-craft Accelerated by Radiation of the Sun (IKAROS) NanoSail-D2 and FeatherSail Cosmos-1 and LightSail-1 Lightsail 2 The effect of solar radiation pressure was well known and was even used during the Mariner 10 mission. The solar radiation pressure was used to create a windmill torque to maintain the angular rate around its roll axis. The IKAROS satellite from JAXA was the only successful mission dedicated to solar sailing in the past. There are, however, other successful satellites that deploy drag sails including the NanoSail-D2 from NASA and LightSail. There are also several new sail satellites (solar sail and drag sail) that are close to being completed and will be launched soon.
1. Introduction – What is confocal microscopy and how does it work? Confocal microscopy is a leading imaging tool used in molecular life sciences with which to render detailed high-resolution three-dimensional data sets. It is instrumental in biological analysis and research where structures of interest are labelled using fluorescent probes. Typically, the three-dimensional data is rendered as a projection onto a two-dimensional display. However, this could lead to uncertainty in the visual interpretation of the sample’s structures of interest. Besides, analysis and region of interest (ROI) selection are also most commonly performed two-dimensionally which may inadvertently lead to either the exclusion of relevant or the inclusion of irrelevant data points. This, in turn, could affect the accuracy of the analysis.