Figure - available via license: CC BY-NC-ND
Content may be subject to copyright.
Source publication
The time series dataset presented here was captured using a real-time energy monitoring device from a three-phase distribution board panel of a student residence. We captured the data from April 2016 to January 2018 in Johannesburg, South Africa. The data from each phase was automatically aggregated and presented as a single data point. The granula...
Contexts in source publication
Context 1
... An asset assessment of the student residence is summarised in Table 1. The electrical energy consumption data presented, was gathered using a real-time energy monitor. ...Context 2
... average energy consumption per day of the appliances has been provided considering the variation of usage. In Table 1, the electric heaters are mostly used only during the austral winter season (June, July and August). Aside, the austral winter season, the heaters are only used on a few occasion of cold fronts typically experienced in South Africa. ...Context 3
... the end of installation and synchronisation, an accuracy test was conducted. The test involves switching off known loads in Table 1 and the reduction in the captured real-time data was concurrent to the power demand of the respective appliances. The online monitor interface as presented in Figure 6, shows the real-time power demand of the entire residence, it provides historical power demand profile as well as historical electrical energy consumption. ...Citations
... Research efforts often go toward measuring the actual electric energy consumption of electrical energy of buildings [11,32,[42][43][44] or on the perceptions and beliefs of the occupants-in this case, students-regarding the use of a variety of electrically powered appliances and devices [45]. An important guide for the inventory of such devices is developed by the World Health Organization in collaboration with the World Bank, which proposes a set of core questions on household energy use [46] related to cooking, heating, and lighting. ...
The understanding of student profiles is critical in educational processes, providing valuable information on the learner’s knowledge, aspirations, expectations, and behaviors. The research aims to profile students’ relationship with electric energy resources across three issues: the use of energy-efficient devices, interactions with available devices and utilities, and the display of adaptive behaviors to environmental conditions and exploitation of resources. The research is undertaken in the oldest university in the western part of Romania, schooling 13,000 students. The methodology consists of monitoring energy consumption on the university campus hosting around 6000 students in 16 dormitories, and of a survey mapping of their energy-related consumption behavior. A total of 1023 participants participated in the study, with responses indicating significant differences in the studied population, which cannot be viewed as a homogenous group. Gender and place of residence influence the results. While the respondents display a relatively high overall awareness and responsible energy-saving behaviors, women and on-campus students seem to be more inclined to adopt energy-saving, sustainable behaviors. The findings of the research are useful for developing data-driven strategies to enhance and consolidate student energy saving behaviors and to plan for nudging messages to induce sustainable choices in the student body.
... Furthermore, the hourly energy consumption of the student residence which covers the four major SA seasons, namely, autumn (1 March-31 May), winter (1 June-31 August), spring (1 September-30 November), and summer (1 December-28/29 February) were obtained for the year 2017. Te energy consumption data for the student residents were obtained from the study of Masebinu et al. [52]. Located on campus, the student residence has 17 rooms (including a kitchen and a washing area) and 4 toilets and bathrooms. ...
... Located on campus, the student residence has 17 rooms (including a kitchen and a washing area) and 4 toilets and bathrooms. Te data comprise realtime power consumption and are a time-series dataset acquired from real-time energy monitoring equipment from the student residence's distribution panel [52]. Figure 2 shows the architectural design of the model under study. ...
Future energy planning relies on understanding how much energy is produced and consumed. In response, this study developed a multihybrid adaptive neuro-fuzzy inference system (ANFIS) for students’ residences, using the University of Johannesburg residence, South Africa as a case study. The model input variables are wind speed, temperature, and humidity, with the output being the equivalent energy consumption for the student housing. While the particle swarm optimization (PSO) technique is versatile and widely used, it falls short by exhibiting premature convergence. To address this problem, the velocity update equation of the original PSO algorithm is modified by incorporating a dynamic linear decreasing inertia weight, which improves the PSO algorithm’s convergence behaviour and aids both local and global search. Following that, the modified PSO (MPSO) is used to optimize the ANFIS parameters for the best model prediction. A comparative analysis is conducted between the MPSO, the original PSO, and six other hybrid models using a dataset division of 70% for training and 30% for testing. Performance evaluation was carried out using three well-known performance benchmarks: root mean square error (RMSE), mean absolute deviation (MAD), and coefficient of variation (RCoV). The experimental results show that the performance of the proposed MPSO-ANFIS outperformed other methods with the least values of the RMSE (1.8928 KWh), MAD (1.5051 KWh), and RCoV (0.1370), respectively. Furthermore, when compared to the PSO-ANFIS, the MPSO-ANFIS demonstrated improvements in RMSE, MAD, and RCoV with 1.58%, 2.11%, and 5.23%, respectively. Based on the results, it can be concluded that the MPSO-ANFIS provides better prediction accuracy which is vital for strategic energy planning.
... A paradigm transition from classical to artificial techniques has been noted in the last decades. The study by Masebinu et al [7] carried out an experimental investigation of the electrical energy consumption of the University of Johannesburg campus residences based on environmental conditions. Recently, intelligent forecasting techniques have been applied such as Artificial Neural Networks (ANN) [8], Autoregressive Integrated Moving Average (ARIMA) [9], non-linear autoregressive neural network (NARNET) [5], adaptive neuro-fuzzy inference system (ANFIS) [10] for electrical energy forecast. ...
... The data used for building the model for the prediction of electrical energy consumption in Campus residences in this study is extracted from real-time electricity consumption data from Masebinu et al. [7]. The authors captured raw data comprising hourly and daily electrical energy consumption (kWh) from the University of Johannesburg, Auckland Park campus residence from April 2016 to January 2018. ...
Developing a viable data-driven policy for the management of electrical-energy consumption in campus residences is contingent on the proper knowledge of the electricity usage pattern and its predictability. In this study, an adaptive neuro-fuzzy inference systems (ANFIS) was developed to model the electrical energy consumption of students’ residence using the University of Johannesburg, South Africa as a case study. The model was developed based on the environmental conditions vis-à-vis meteorological parameters namely temperature, wind speed, and humidity of the respective days as the input variables while electricity consumption (kWh) was used as the output variable. The fuzzy c-means (FCM) is a type of clustering technique that is preferred owing to its speed boost capacity. The best FCM-clustered ANFIS-model based on a range of 2–10 clusters was selected after evaluating their performance using relevant statistical metrics namely; mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute deviation (MAD). FCM-ANFIS with 7 clusters outperformed all other models with the least error and highest accuracy. The RMSE, MAPE, MAD, and R2-values of the best models are 0.043, 0.65, 1.051, and 0.9890 respectively. The developed model will assist in optimizing energy consumption and assist in designing and sizing alternative energy systems for campus residences.
... About 14,000 h of data points were recorded in the study. It was concluded that the data obtained could be helpful in making informed decisions regarding the best model of electricity for student residences [48]. ...
One of the issues associated with the supply of electricity is its generation capacity, and this has led to prevalent power cuts and high costs of usage experienced in many developing nations, including South Africa. Historical research has shown that the annual rate of increase for electricity has grown at an alarming rate since 2008 and, in some years, has grown as much as 16%. The objectives of this study are to estimate the cost analysis of electricity usage at the twenty-nine residences of the University of Johannesburg (UJ-Res) and propose a model for our university, as well as other South African universities, to become more energy-efficient. This was achieved by analyzing the tariffs between 2015 and 2021. A forecast was made for a period of five years (2021 to 2026) using a non-linear autoregressive exogenous neural network (NARX-NN) time-series model. From the results obtained, the better NARX-NN model studied has a root mean squared error (RMSE) of 2.47 × 10 5 and a determination coefficient (R 2) of 0.9661. The projection result also shows that the annual cost of energy consumed will increase for the projected years, with the year 2022 being the peak with an estimated annual cost of over ZAR 30 million (USD 2,076,268).
... • In sub-Saharan Africa, the lack of real-time electricity consumption data during the design and sizing of renewable energy technology systems make variability between simulated and real system performance differ significantly [1] . The data presented is useful in residential apartments electrification planning where real-world variability is required. ...
... • In sub-Saharan Africa, the lack of real-time electricity consumption data during the design and sizing of renewable energy technology systems make variability between simulated and real system performance differ significantly [1] . The data presented is useful in residential apartments electrification planning where real-world variability is required. ...
The real-time hourly electricity consumption data of a middle-income household in the Gauteng Province of South Africa was tracked for 30 months (i.e. 2019 to 2021) over three different residential properties. Layout diagram and physical characteristics of each of the residential properties are provided. An energy audit of all appliances at the residence was conducted at the beginning of the study and acquisition of new appliances was also captured. The aggregated electricity consumption throughout the study of all appliances at the family residence was captured from a single-phase electricity distribution sub-panel. The granularity of the captured data was at the hourly resolution level and presented as kilowatt-hour. A total of 20,852 hours of data points were captured. The data has not been processed further. In addition to the energy consumption data, 16 months of hourly data for wind speed, temperature, and humidity of the closest weather station to two of the residential properties has been provided. The energy consumption data will be useful for teaching and research in energy consumption prediction studies, and energy management strategy development. Considering the timing of the study that encompasses pre-COVID-19 and three peaks of COVID-19 in South Africa, the data can be useful in analysing the impact of COVID-19 on household electricity consumption.
... Unlike the majority of students at the institution, due to the software requirements of the student's major, arrangements had been made for this particular subset of students to have comprehensive access to the internet. Whilst students did struggle with internet connectivity, and in particular the impacts of load-shedding 3 (Masebinu et al. 2020), I could assume a degree of digital literacy in the class itself. It also meant that I was able to undertake synchronous teaching at a moment when that was rarely possible at the South African undergraduate level, in addition to significant interaction and support via the university's electronic learning platform as well as WhatsApp. ...
This article uses a student assessment developed in the "emergency" conditions of the Covid-19 pandemic in South Africa as a tool for refracting and reflecting (Strassler 2011) the changing realities of higher education around the world. It examines the Archive of Kindness as an example of the possibilities enabled by digitally mediated learning, as well as the challenges of teaching and learning in environments where students enter university with varying degrees of digital literacy and skill. It poses questions pertaining to the futures of higher education in a world in which biopolitics are increasingly determined by and through screens, and suggests that uncritical engagements with digital platforms and the corporate entities behind them pose dangers to emerging forms of citizenship. The article details the processes of knowledge curatorialism which are increasingly likely to determine the shape of learning in tertiary education, particularly within the university sector. Here, it argues that the Humanities and Social Sciences will need to play a leading role in providing the language and tools for thinking through the pedagogy of hyperlinkages, where the boundaries between online and offline spaces are increasingly difficult to parse.
... Unlike the majority of students at the institution, due to the software requirements of the student's major, arrangements had been made for this particular subset of students to have comprehensive access to the internet. Whilst students did struggle with internet connectivity, and in particular the impacts of load-shedding 3 (Masebinu et al. 2020), I could assume a degree of digital literacy in the class itself. It also meant that I was able to undertake synchronous teaching at a moment when that was rarely possible at the South African undergraduate level, in addition to significant interaction and support via the university's electronic learning platform as well as WhatsApp. ...
This article uses a student assessment developed in the “emergency” conditions of the Covid-19 pandemic in South Africa as a tool for refracting and reflecting (Strassler 2011) the changing realities of higher education around the world. It examines the Archive of Kindness as an example of the possibilities enabled by digitally mediated learning, as well as the challenges of teaching and learning in environments where students enter university with varying degrees of digital literacy and skill. It poses questions pertaining to the futures of higher education in a world in which biopolitics are increasingly determined by and through screens, and suggests that uncritical engagements with digital platforms and the corporate entities behind them pose dangers to emerging forms of citizenship. The article details the processes of knowledge curatorialism which are increasingly likely to determine the shape of learning in tertiary education, particularly within the university sector. Here, it argues that the Humanities and Social Sciences will need to play a leading role in providing the language and tools for thinking through the pedagogy of hyperlinkages, where the boundaries between online and offline spaces are increasingly difficult to parse.
... In order to have a better grasp on the population that is the main object of this study, i.e., the students, other studies that could shed light on the students' sustainable electricity behaviors were investigated. Students' electricity patterns have been studied by researchers in the USA [39], South Africa [40] and the Netherlands [41], among others, with the purpose of understanding the variables in energy use by the students. Still, these studies do not discuss the existence of sustainable electricity consumption among students. ...
The Organization for Economic Co-operation and Development (OECD) estimates that the environmental pressure from households will increase significantly by 2030. Sustainable consumption means making consumers aware of the social and environmental impacts of the goods and services they use. In this respect, special attention must be paid to electricity consumption since its generation affects the environment. The present research aims at capturing electricity consumption behaviors among students, after having applied an online questionnaire between March and April 2021, recording 816 responses. The results of this research highlighted the fact that for seven out of fourteen statements, percentages of over 50% for the “always” and “often” answer variants were recorded, but cases when the highest percentages were for the “rarely” and “never” answer variants (e.g., “You read the hours on the light bulb packs before purchasing them”, “You put your mobile phone in the power saving mode so that you don’t have to charge it so often” and “You unplug the electrical and electronic equipment that you do not use”) were also observed. Decrypting consumer behaviors is a key point for building strategies that will lead to consumers’ awareness of conserving electricity in households and, thus, to a reduction in their environmental impact.
This data article presents data related to 100 residential units in Tehran, Iran, each of which has approximately "average monthly electricity consumption" data for 190 months. In addition, some physical characteristics of each building are given in the dataset. Presented data includes collected electricity end-users in residential units as well as thermos-physical characteristics of the buildings through a structured questionnaire on the. Physical characteristics include the number of floors, morphology of the yard and the dimensions of the windows on each side, window material, the area and floor number of the desired residential unit, its location in the city, cooling system, heating system, and so on. Information provided in this data article can be useful for research on energy prediction studies and also energy management strategies, and policy making to achieve sustainability factors. Having few datasets published on this topic and in hot and arid geographic regions, authors believe that the result of this data study can be generalized to the larger region of the Middle East and North Africa (MENA). The data consists of two parts; 1. Physical specifications of the building and 2. History of electricity consumption.
