2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)最新文献
{"title":"The Influence of the Signal Distortions on the Satellite Based Navigation Systems","authors":"B. Madonsela, I. Davidson, C. Mulangu","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377223","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377223","url":null,"abstract":"The Global Navigation Satellite Systems (GNSS) is widely used in numerous applications that include the agricultural production, aviation, maritime and automobile navigation. GNSS is also involved with the lifesaving application such as the search and rescue. The GNSS is continuously developed with the additional satellite constellations being added to the orbit and the new frequencies are adopted. The new frequencies and the new signal are introduced to eliminate the largest errors that were ever experienced in the GNSS applications and improve the accuracy in terms of the position calculations. The signal distortions are caused by the GNSS signal degradation and the signal multipath becomes the prominent concern. The purpose of this paper is to assess and quantify the impact of the nominal signal interference in the in the GNSS receiver and further provide the brief description and the algorithm of the signal from the space. The results will be open and available for domain use for the researchers or institutions that are studying toward the solution based approach of increasing the GNSS performances. Furthermore it will provide an option to quantify the distortion impact to the GNSS.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121882582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. O. Omoregbee, M. U. Olanipekun, Ayobami Kalesanwo, Oluwaferanmi A. Muraina
{"title":"Design And Construction Of A Smart Ultrasonic Walking Stick For The Visually Impaired.","authors":"H. O. Omoregbee, M. U. Olanipekun, Ayobami Kalesanwo, Oluwaferanmi A. Muraina","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377240","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377240","url":null,"abstract":"In our society, blind people consist a wide number of individuals. In order to improve the quality of life of a blind person, the smart cane was therefore created. This project aims to develop a smart cane for the blind with an ultrasonic sensor and an audio feedback system. This embedded system will mainly have two parts; the system of mobility and feedback. It was been fitted with an ultrasonic sensor for the mobility system, while the vibrating motor and audio input will provide input from the ultrasonic and the vibrating module. An Ultrasonic sensor was used to send the signal to the vibrating motor as soon as an obstacle is detected, which in turn triggers it. With audio feedback alerting the user of the presence of the obstacle, the vibrating motor vibrates with various strengths according to the distance of the obstacle. One major component incorporated into this embedded system is an ATmega328 single-chip microcontroller which was programed in the c language of which the original programing was written with Matlab. It involves the use of a convolution neural network which was trained on the CIFAR 10 dataset. This dataset was chosen because of its composition of images of objects likely to be found as obstacles on a blind man’s path. A 93.8% accuracy was obtained from an unsupervised learning on the data set, after which the C Matlab coder was used to translate the source code into C language for effective embedding into the ATmega328 microcontroller.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127711873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Vulnerability Analysis of False Data Injection Attacks on the Frequency Stability of Isolated Microgrids","authors":"A. Aluko, R. P. Carpanen, D. Dorrell, E. Ojo","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377015","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377015","url":null,"abstract":"In smart grid technology, modern communication infrastructure is utilized for the exchange of data between various elements of the microgrid (MG) system and the MG control center (MGCC). However, the integrity of the data may be compromised through cyber-attack activities leading to disruption in the stability and safe operation of the MG system. This paper investigates the vulnerability of frequency measurements to false data injection (FDI) attacks in an isolated MG system. The impact of two kinds of FDI attack on the frequency stability of the MG system is analyzed. The results show that FDI attacks can stealthily destabilize the stability of the MG with an exogenous FDI attack and more damage can be done with an endogenous FDI attack of negative magnitude. The analysis is done using the MATLAB/Simulink software.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133436552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Knowledge Transfer using Model-Based Deep Reinforcement Learning","authors":"Tlou Boloka, Ndivhuwo Makondo, Benjamin Rosman","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377247","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377247","url":null,"abstract":"Deep reinforcement learning has recently been adopted for robot behavior learning, where robot skills are acquired and adapted from data generated by the robot while interacting with its environment through a trial-and-error process. Despite this success, most model-free deep reinforcement learning algorithms learn a task-specific policy from a clean slate and thus suffer from high sample complexity (i.e., they require a significant amount of interaction with the environment to learn reasonable policies and even more to reach convergence). They also suffer from poor initial performance due to executing a randomly initialized policy in the early stages of learning to obtain experience used to train a policy or value function. Model based deep reinforcement learning mitigates these shortcomings. However, it suffers from poor asymptotic performance in contrast to a model-free approach. In this work, we investigate knowledge transfer from a model-based teacher to a task-specific model-free learner to alleviate executing a randomly initialized policy in the early stages of learning. Our experiments show that this approach results in better asymptotic performance, enhanced initial performance, improved safety, better action effectiveness, and reduced sample complexity.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133944046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Toward Collaborative Reinforcement Learning Agents that Communicate Through Text-Based Natural Language","authors":"Kevin Eloff, H. Engelbrecht","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377018","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377018","url":null,"abstract":"Communication between agents in collaborative multi-agent settings is in general implicit or a direct data stream. This paper considers text-based natural language as a novel form of communication between multiple agents trained with reinforcement learning. This could be considered first steps toward a truly autonomous communication without the need to define a limited set of instructions, and natural collaboration between humans and robots. Inspired by the game of Blind Leads, we propose an environment where one agent uses natural language instructions to guide another through a maze. We test the ability of reinforcement learning agents to effectively communicate through discrete word-level symbols and show that the agents are able to sufficiently communicate through natural language with a limited vocabulary. Although the communication is not always perfect English, the agents are still able to navigate the maze. We achieve a BLEU score of 0.85, which is an improvement of 0.61 over randomly generated sequences while maintaining a 100% maze completion rate. This is a 3.5 times the performance of the random baseline using our reference set.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133062181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Decentralized Control Scheme Applied To Domestic Electric Water Heaters To Minimize Frequency Deviations: Initial Results.","authors":"Ouma Bosaletsi, Prof Willem Cronje","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377244","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377244","url":null,"abstract":"This study is an attempt to address the frequency regulation of an islanded microgrid using domestic electric water heaters (EWHs). Decentralized control strategy is adopted to control individual EWHs supplied from a diesel generator. All dynamic models are developed in MATLABlSimulink environment. Simulation results demonstrated that the proposed control method has the potential to reduce the frequency deviations and improve the oscillations damping of the microgrid.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115658532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Power Distribution System Fault Diagnostic Using Genetic Algorithm and Neural Network","authors":"K. Moloi, A. Yusuff","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377241","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377241","url":null,"abstract":"Fault determination and isolation is an important aspect for maintaining the health index of a power grid. In this paper, a protection fault scheme is proposed. The protection scheme uses a discrete wavelet transform (DWT), genetic algorithm (GA) and neural network (NN). The DWT technique is used to analyze fault current signals at different levels. From the analyzed signals, statistical features are extracted to minimize the size of the original signal to improve the computational efficiency. Subsequently, the features are used to train and test the NN fault classifier scheme. To improve the performance of the classier, the GA technique is used to determine the optimal parameters of the NN scheme. The scheme is tested on a practical network and a high accuracy is obtained for fault determination.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129924538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Algorithmic Music Composition Using Probabilistic Graphical Models and Artificial Neural Networks","authors":"Marc Marsden, Ritesh Ajoodha","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377235","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377235","url":null,"abstract":"Composing music algorithmically has been a goal long-pursued by many computer scientists. Various methods have been implemented to achieve this, ranging from randomly selecting musical components to deep learning models. The main focus of this research is to develop a model which fools a human into believing the output music is human-made. This study uses a collection of rock music MIDI files which the notes, chords, pitches and duration are extracted as features. A Bayesian network is selected as the main model for this research and a Long Short-Term Memory (LSTM) network as the benchmark model. A Turing test was performed on 20 people for both models and the LSTM on average was identified as human-made 36% of the time, while the Bayesian network, on average, had been misidentified 39% of the time. These results may indicate that music is more probabilistic than time-dependent.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129361105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nomhle Loji, Kabulo Loji, R. Tiako, I. Davidson, T. K. Akindeji
{"title":"Loadability Assessment of a Photovoltaic Penetrated Grid to Offset Intermittency and Reduce Total Losses using Battery Energy Storage System","authors":"Nomhle Loji, Kabulo Loji, R. Tiako, I. Davidson, T. K. Akindeji","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377026","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377026","url":null,"abstract":"Because of many substantial benefits over other renewable energy resources (RES), photovoltaic (PV) and wind technologies are the most important distributed generation (DG) means and, they are rapidly and widely propagating. However, they are non-dispatchable and, the stochastic and intermittent natures of solar irradiation and wind, are some of the fundamental barriers and challenges to their development and their large-scale deployment. As a result, power systems operators have no control over DG’s available resources and are compelled to operate conventional generators to both cater for normal changes in load demand and make provision for DG’s output variations. This paper investigates, the effectiveness the integration of battery storage system (BSS) to offset the challenge of intermittency on a power grid with photovoltaic penetration. The simulation results on a modified IEEE-9 test network show that energy storage can successfully shape the fluctuation thereby reducing total losses of the combined PV-Battery plant while increasing the system loadability.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130594866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Financial Feasibility of Solar PV within eThekwini Municipality - Business Customers","authors":"S. Sewchurran, I. Davidson","doi":"10.1109/SAUPEC/RobMech/PRASA52254.2021.9377214","DOIUrl":"https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377214","url":null,"abstract":"Rising electricity tariffs, electricity shortages, under frequency load shedding, Carbon Taxes and reducing costs of solar PV systems in South Africa has made investment in solar PV a lucrative option to many business customers. However, revenue loss remains a major concern to the municipalities who have historically designed bundled business tariffs which relies on the municipality selling electricity to ensure business sustainability. Municipalities have come up with many new proposed tariff structures to try and counter act the impact of reduced electricity sales by implementing net billing tariffs with fixed costs based on the customer inverter size. An investigation was carried out to better understand the impact on the feasibility of a business roof top solar PV systems with and without the implementation of the new net billing electricity tariffs, as well as its impact on the customer’s payback periods. The eThekwini Municipalities proposed Business and General Net Billing Feed in Tariff was utilized for the case studies.","PeriodicalId":442944,"journal":{"name":"2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132903501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}