A multi-factor model for range estimation in electric vehicles
- Authors: Smuts, Martin Bradley
- Date: 2019
- Subjects: Electric vehicles , Hybrid electric vehicles Energy consumption Machine learning Information technology -- Management
- Language: English
- Type: Thesis , Doctoral , DPhil
- Identifier: http://hdl.handle.net/10948/43589 , vital:36926
- Description: Electric vehicles (EVs) are well-known for their challenges related to trip planning and energy consumption estimation. Range anxiety is currently a barrier to the adoption of EVs. One of the issues influencing range anxiety is the inaccuracy of the remaining driving range (RDR) estimate in on-board displays. RDR displays are important as they can help drivers with trip planning. The RDR is a parameter that changes under environmental and behavioural conditions. Several factors (for example, weather, and traffic) can influence the energy consumption of an EV that are not considered during the RDR estimation in traditional on-board computers or third-party applications, such as navigation or mapping applications. The need for accurate RDR estimation is growing, since this can reduce the range anxiety of drivers. One way of overcoming range anxiety is to provide trip planning applications that provide accurate estimations of the RDR, based on various factors, and which adapt to the users’ driving behaviour. Existing models used for estimating the RDR are often simplified, and do not consider all the factors that can influence it. Collecting data for each factor also presents several challenges. Powerful computing resources are required to collect, transform, and analyse the disparate datasets that are required for each factor. The aim of this research was to design a Multi-factor Model for range estimation in EVs. Five main factors that influence the energy consumption of EVs were identified from literature, namely, Route and Terrain, Driving Behaviour, Weather and Environment, Vehicle Modelling, and Battery Modelling. These factors were used throughout this research to guide the data collection and analysis processes. A Multi-factor Model was proposed based on four main components that collect, process, analyse, and visualise data from available data sources to produce estimates relating to trip planning. A proof-of-concept RDR system was developed and evaluated in field experiments, to demonstrate that the Multi-factor Model addresses the main aim of this research. The experiments were performed to collect data for each of the five factors, and to analyse their impact on energy consumption. Several machine learning techniques were used, and evaluated, for accuracy in estimating the energy consumption, from which the RDR can be derived, for a specified trip. A case study was conducted with an electric mobility programme (uYilo) in Port Elizabeth, South Africa (SA). The case study was used to investigate whether the available resources at uYilo were sufficient to provide data for each of the five factors. Several challenges were noted during the data collection. These were shortages of software applications, a lack of quality data, technical interoperability and data access between the data collection instruments and systems. Data access was a problem in some cases, since proprietary systems restrict access to external developers. The theoretical contribution of this research is a list of factors that influence RDR and a classification of machine learning techniques that can be used to estimate the RDR. The practical contributions of this research include a database of EV trips, proof-of-concept RDR estimation system, and a deployed machine learning model that can be accessed by researchers and EV practitioners. Four research papers were published and presented at local and international conferences. In addition, one conference paper was published in an accredited journal: NextComp 2017 (Appendix C), Conference Paper, Pointe aux Piments (Mauritius); SATNAC 2017 (Appendix F), Conference Paper, Barcelona (Spain); GITMA 2018 (Appendix B), Conference Paper, Mexico City (Mexico); SATNAC 2018 (Appendix G), Conference Paper, George (South Africa), and IFIP World Computer Congress 2018 (Appendix E), Journal Article.
- Full Text:
- Date Issued: 2019
A framework for the design of business intelligence dashboard tools
- Authors: Smuts, Martin Bradley
- Date: 2016
- Subjects: Business intelligence Dashboards (Management information systems)
- Language: English
- Type: Thesis , Masters , MCom
- Identifier: http://hdl.handle.net/10948/12941 , vital:27136
- Description: Vast amounts of data are collected on a daily basis, making it difficult for humans to derive at valuable information to make effective decisions. In recent years, the field of Business Intelligence (BI) and Information Visualisation (IV) have become a key driver of an organisation’s success. BI tools supporting decision making need to be accessible to a larger audience on different levels of the organisation. The problem is that non-expert users, or novice users, of BI tools do not have the technical knowledge to conduct data analysis and often rely on expert users to assist. For this reason, BI vendors are shifting their focus to self-service BI, a relatively new term where novice users can analyse data without the traditional human mediator. Despite the proliferation of self-service BI tools, limited research is available on their usability and design considerations to assist novice users with decision making and BI analysis. The contribution of this study is a conceptual framework for designing, evaluating or selecting BI tools that support non-expert users to create dashboards (the BI Framework). A dashboard is a particular IV technique that enables users to view critical information at a glance. The main research problem addressed by this study is that non-expert users often have to utilise a number of software tools to conduct data analysis and to develop visualisations, such as BI dashboards. The research problem was further investigated by following a two-step approach. The first approach was to investigate existing problems by using an in-depth literature review in the fields of BI and IV. The second approach was to conduct a field study (Field Study 1) using a development environment consisting of a number of software components of which SAP Xcelsius was the main BI tool used to create a dashboard. The aim of the field study was to compare the identified problems and requirements with those found in literature. The results of the problem analysis revealed a number of problems in terms of BI software. One of the major problems is that BI tools do not adequately guide users through a logical process to conduct data analysis. In addition, the process becomes increasingly difficult when several BI tools are involved that need to be integrated. The results showed positive aspects when the data was mapped to a visualisation, which increased the users’ understanding of data they were analysing. The results were verified in a focus group discussion and were used to establish an initial set of problems and requirements, which were then synthesised with the problems and requirements identified from literature. Once the major problems were verified, a framework was established to guide the design of BI dashboard tools for novice users. The framework includes a set of design guidelines and usability evaluation criteria for BI tools. An extant systems analysis was conducted using BI tools to compare the advantages and disadvantages. The results revealed that a number of tools could be used by non-experts, however, their usability hinders users. All the participants used in all field studies and evaluations were Computer Science (CS) and Information Systems (IS) students. Participants were specially sourced from a higher education institution such as the Nelson Mandela Metropolitan University (NMMU). A second field study (Field Study 2) was conducted with participants using another traditional BI tool identified from the extant systems analysis, PowerPivot. The objective of this field study was to verify the design guidelines and related features that served as a BI Scorecard that can be used to select BI tools. Another BI tool, Tableau, was used for the final evaluation. The final evaluation was conducted with a large participant sample consisting of IS students in their second and third year of study. The results for the two groups revealed a significant difference between participants’ education levels and the usability ratings of Tableau. Additionally, the results indicated a significant relationship between the participants’ experience level and the usability ratings of Tableau. The usability ratings of Tableau were mostly positive and the results revealed that participants found the tool easy to use, flexible and efficient. The proposed BI Framework can be used to assist organisations when evaluating BI tools for adoption. Furthermore, designers of BI tools can use the framework to improve the usability of these tools, reduce the workload for users when creating dashboards, and increase the effectiveness and efficiency of decision support.
- Full Text:
- Date Issued: 2016