A GA-stacking ensemble approach for forecasting energy consumption in a smart household: A comparative study of ensemble methods.

The considerable amount of energy utilized by buildings has led to various environmental challenges that adversely impact human existence. Predicting buildings' energy usage is commonly acknowledged as encouraging energy efficiency and enabling well-informed decision-making, ultimately leading to decreased energy consumption. Implementing eco-friendly architectural designs is paramount in mitigating energy consumption, particularly in recently constructed structures. This study utilizes clustering analysis on the original dataset to capture complex consumption patterns over various periods. The analysis yields two distinct subsets that represent low and high consumption patterns and an additional subset that exclusively encompasses weekends, attributed to the specific behavior of occupants. Ensemble models have become increasingly popular due to advancements in machine learning techniques. This research utilizes three discrete algorithms, namely Artificial Neural Network (ANN), K-nearest neighbors (KNN), and Decision Trees (DT). In addition, the application employs three more machine learning algorithms bagging and boosting: Random Forest (RF), Extreme Gradient Boosting (XGB), and Gradient Boosting Trees (GBT). To augment the accuracy of predictions, a stacking ensemble methodology is employed, wherein the forecasts generated by many algorithms are combined. Given the obtained outcomes, a thorough examination is undertaken, encompassing the techniques of stacking, bagging, and boosting, to conduct a comprehensive comparative study. It is pertinent to highlight that the stacking technique consistently exhibits superior performance relative to alternative ensemble methodologies across a spectrum of heterogeneous datasets. Furthermore, using a genetic algorithm enables the optimization of the combination of base learners, resulting in a notable enhancement in prediction accuracy. After implementing this optimization technique, GA-Stacking demonstrated remarkable performance in Mean Absolute Percentage Error (MAPE) scores. The improvement observed was substantial, surpassing 90 percent for all datasets. In addition, in subset-1, subset-2, and subset-3, the achieved R2 scores were 0.983, 0.985, and 0.999, respectively. This represents a substantial advancement in forecasting the energy consumption of residential buildings. Such progress underscores the potential advantages of integrating this framework into the practices of building designers, thereby fostering informed decision-making, design management, and optimization prior to construction.

Carbon footprint of low-energy buildings in the United Kingdom: Effects of mitigating technological pathways and decarbonization strategies.

There is a limited comprehensive analysis of the effectiveness of adopted carbon mitigation strategies for buildings over their life cycle, that are concerned with temporal perspectives of emissions. Accordingly, this paper explores a life cycle assessment (LCA) to address the concerns regarding mitigating the carbon footprint of a UK timber-frame low-energy dwelling. In particular, it aims to investigate the potential greenhouse gas (GHG) emission reduction in terms of three different heating and ventilation options, and to analyze the influence of decarbonization of electricity production as well as the technological progress of the waste treatment of timber on the building's environmental performance. Thus, the whole life­carbon of the building case studies was evaluated for a total of eight investigated prospective scenarios, and they were compared to the LCA results of the baseline scenario, where the existing technology and context remained constant over time. Results show that using a compact heat pump would lead to a significant whole life-cycle emission reduction of the dwelling, by 19 %; while GHG emission savings can be reinforced if the assessed systems are employed simultaneously with grid decarbonization, exhibiting a 25 %-60 % reduction compared to the baseline scenario. Moreover, technological changes in the waste treatments of timber products could substantially reduce the buildings' embodied emissions, representing 3 %-23 %. From these emission-saving measures, the contribution of material efficiency strategies to achieve more embodied carbon savings should be highlighted in future construction practices.

Performance evaluation of using evacuated tubes solar collector, perforated fins, and pebbles in a solar still - experimental study and CO2 mitigation analysis.

The combination of various methods of increasing evaporation rate can highly impact the performance of solar desalination. This investigation aims to find the impact of using evacuated tubes solar collector, perforated fins, and pebbles on the performance enhancement of a solar still. Simultaneously six-evacuated-tube solar collector to raise the evaporation rate of the system, the perforated fins to increase the heat transfer surface between water and absorber, and the immersed pebbles stone in the water to keep the high water temperature at low solar radiation were considered. The hourly and cumulative distillate output (DO) values are presented separately for the daytime and nighttime to provide extensive insight. The results indicate that on a sample day from the six months of experiments, which was in February 2019, the time for DO peak shifts from 1 to 3 p.m. Moreover, the temperature values for MSS experience almost 43 ℃ jumps on the peak and almost 19 ℃ increase on average compared to CSS. Furthermore, the cumulative DO in the daytime reaches from 2.515 to 6.662 L, while during the nighttime, an increase from 0.057 to 0.872 L is observed. Additionally, during the six months, the average DO jumps from 2.88 to 7.03 L, which means a significant enhancement of 144.1%. Moreover, the costs per liter of MSS and CSS are 0.0051 and 0.0056 dollars per liter, respectively. The net amount of CO2 reduction of MSS was improved by about 2.44 times higher than CSS.