Journal of Energy & Technology (JET) [U.S. ISSN 2768-1025] 2021-01-01T22:16:48+00:00 Editorial Office Open Journal Systems <p><strong>About this Journal</strong></p> <p>The <em><strong>Journal of Energy &amp; Technological (JET) </strong></em>(U.S. ISSN 2768-1025) is an open-access wide range of specific and subfields of generating energies and its technologies in engineering and sciences<strong>. </strong> It encourages a broad spectrum of contributions in the multi-sources of renewable and non-renewable energies. Articles of interdisciplinary nature are also welcome. Manuscripts focusing on all aspects of energy-related engineering and sciences are to be submitted to the Journal's open-access publishing.</p> Dynamic forecasting, optimization and real-time energy management of gridable vehicle – a review 2020-07-02T21:09:20+00:00 Abdilaziz J. Alshareef Ahmed Saber Ibrahim M. Mehedi <p>This paper investigates the concept of the new generation smart power grid that includes gridable vehicles and renewable energy sources. Here it is analyzed the feasibility of developing a real-time dynamic stochastic optimization approach that will result in a combined cost-emission reduction by the maximum utilization of clean energy sources. The concept in this paper is look at a gridable vehicle (GV) as a small portable power plant (SP3) and a smart parking lot (Smart Park) as a virtual power plant (VPP). After an extensive investigation of existing literature review, it is recommended that a dynamic stochastic optimization (DSO) approach can be used to automatically schedule and coordinate non-stationary sources to get full benefits of renewable energy sources (RESs) such that (1) load demand can be leveled; (2) cost and emission will be reduced; (3) reserve and reliability of a smart grid can be increased when millions of new loads, e.g., GVs, are to be integrated.</p> <p>DOI:</p> 2020-07-02T00:00:00+00:00 Copyright (c) 2020 Journal of Energy & Technology (JET) Techno-Economic Evaluation of Hybrid Supply System for Sustainable Powering the Saint Martin Island in Bangladesh 2020-08-14T23:05:12+00:00 Ummey Sufia Mousumi Md. Asaduzzaman Md. Abu Zardar Khondoker Ziaul Islam <p>With the progression of new technology, renewable energy (RE) based supply systems are becoming popular day by day. The main concern of this work is to examine the viability of renewable energy-oriented hybrid systems for powering the Saint Martin Island, the southern area of Bangladesh. This work proposed a hybrid solar PV/wind turbine (WT) arrangement to provide a way out to the power crisis of off-grid Saint Martin Island with optimizing hybrid power generation schemes focused on the locally obtainable renewable resources. The techno-economic feasibility of the hybrid solar PV/WT system along with back supply such as diesel generator (DG) and battery bank (BB) has been critically analyzed using the HOMER optimization software with genuine climate statistics and nominal load profile under the condition of summer and winter seasons. Simulation results find that the RE focused supply system technically feasible and includes a minimum amount of total net present cost (TNPC) along with the lower value of per unit electricity generation cost. Moreover, the amount of released gas for the RE focused supply system is far less than the gas released if the total electrical load was supplied by only diesel generators. Finally, the hybrid solar PV/WT system along with backup supply is a realistic solution which includes the initial cost of 89,620 $, the replacement cost of $ 59,791, operating cost of 22,701 $/year, TNPC of 250,919 $ and electricity generation cost of 0.206 $/kWh.</p> 2020-08-22T00:00:00+00:00 Copyright (c) 2020 Journal of Energy & Technology (JET) The Impact of Design Space on the Accuracy of Predictive Models in Predicting Chiller Demand Using Short-Term Data 2020-12-28T20:30:55+00:00 Rodwan Elhashmi Kevin P. Hallinan Salahaldin Alshatshati <p>Predicting cooling load is essential for many applications such as diagnosing the health of existing chillers, providing better control functionality, and minimizing peak loads. In this study, short-term chiller and total building demand are acquired for five different commercial buildings in the Midwest USA. Four different machine learning models are then used to predict the chiller demand using the total building demand, outdoor weather data, and day/time information. Two data collection scenarios are considered. The first relies upon use of multiple weeks of data collection that includes very warm periods and season transitional periods where the outdoor temperature ranged from very warm to cool conditions in order to envelope all cooling season weather conditions. The second scenario employs use of contiguous data for a several weeks during only the warmest period of the year. The results show that using two or more separate time periods to envelope most of the weather data yields a much more accurate model in comparison to use of data for only one time period. These research findings have importance to energy service companies which often do short term audits (measurements) in order to estimate potential savings from chiller system upgrades (controls or otherwise).</p> 2021-01-17T00:00:00+00:00 Copyright (c) 2021 Journal of Energy & Technology (JET) Roadmap for Utilizing Machine Learning in Building Energy Systems Applications: Case Study of Predicting Chiller Running Capacity for School Buildings Using Stacking Learning 2021-01-01T22:14:30+00:00 Rodwan Elhashmi Kevin P. Hallinan Abdulrahman Alanezi <p>Cooling accounts for 12-38% of total energy consumption in schools in the US, depending on the region. In this study, stacking learning is utilized to predict chiller running capacity for four school buildings (regression) and to predict the chiller status for four another schools (classification) using a collection of interval chiller data and building demand. Singular and multiple measurement periods within one or more seasons are considered. A generalized methodology for modeling building energy systems is posited that informs selection of features, data balancing to attain the best model possible, ensemble-based stacked learning in order to prevent over-fitting, and final model development based upon the results from the stacked learning. The results show that ensemble-based stacked learning improves the model performance substantially; providing the most accurate results for both regression and classification. for both classification and regression. For, classification, the balanced accuracy is 99.79% while Kappa is 99.39%. For regression, the R-squared value, the mean absolute error (MAE) error, and the root mean squared error (RMSE) are 1.78 kW, 2.77 kW, and 0.983 respectively.</p> 2021-03-09T00:00:00+00:00 Copyright (c) 2021 Journal of Energy & Technology (JET) Machine Learning Enabled Large-Scale Estimation of Residential Wall Thermal Resistance from Exterior Thermal Imaging 2021-01-01T22:16:48+00:00 Salahaldin Alshatshati Kevin P. Hallinan Rodwan Elhashmi Kefan Huang <p>Traditional building energy audits are both expensive, in the range of USD$1.29/m<sup>2</sup>-$5.37/m<sup>2</sup>, and inconsistent in their prediction of potential energy savings. Automation to reduce costs of evaluating the energy effectiveness of buildings is strongly needed. A key element of such automation is a means to estimate the building envelope energy effectiveness. We present a method that addresses this need by using infrared thermography to characterize building wall envelope effectiveness. To date, thermal imaging approaches for estimating wall R-Values, based upon thermal-physical models of walls, require additional manual measurements and analysis which prohibit low-cost, large-scale implementation. To overcome this implementation challenge, a machine learning approach is used to predict wall R-Values for a set of residences with known thermal resistance by utilizing the measured wall imaging temperature, prior weather conditions, historical energy consumption data, and available building geometrical data. The developed model is shown to predict wall R-Values with a maximum test-set root mean squared error of 7% using as few as nine training houses. This result has significant implications for low-cost large-scale envelope energy effectiveness characterization.</p> 2021-03-09T00:00:00+00:00 Copyright (c) 2021 Journal of Energy & Technology (JET)