As the commercial and industrial buildings continue to focus on energy efficiency and comfortable indoor environment particularly in multi-zone air conditioning systems, there is a need to enhance thermal management. Many conventional optimization techniques do not fully cater for the challenges involved and the spectrum of non-stationary functions involved in these systems. This research presents a new meta-heuristic optimization algorithm called Bat-Cuckoo Search (BCS) to improve thermal control in a multi-zone air conditioning system within a real-world shopping mall environment. The main objective is to minimize energy usage while at the same time ensuring maximum comfort to the occupants.This paper proposed the BCS framework which brings in flexibility of Bat Algorithm and the solution's quality of the Cuckoo Search bringing in enhancement in the speed of convergence. Many factors including temperature, humidity, scenarios of occupancy, and environmental-time conditions are considered in the optimization process. Performance also shows encouraging results which mean that the use of the new proposed system consumes 23 % less energy than the conventional approaches. Using the comfort models, the Predicted Mean Vote (PMV) and High Predicted Percentage of Dissatisfied (PPD) indicators were assessed to indicate a 15 % increase in occupant comfort. Moreover, the results of the hybrid algorithm were superior to other optimization algorithms and achieved a higher convergence rate (32 % faster) and the best solution.The study establishes that the use of advanced hybrid optimization methods can help overcome the complex issues regarding HVAC control in commercial properties. This research offers a new way to solve the HVAC optimization problem and opens the path for sustainable and energy-efficient temperature control in commercial settings.
This research conducts an in-depth parametric study on hybrid glass fibre-reinforced geopolymer concrete (HGFR-GPC), examining how variations in fibre length and dosage impact performance. A total of 21 different mixes were formulated using glass fibres of four lengths (3 mm, 6 mm, 12 mm, and 24 mm) combined in pairs and applied at three levels of fibre dosages (1.0
A strong photosynthetic multifaceted called photosystem I (PS I) successfully catches photons to produce a charge detached phase through a quantum yield. The low latent reductant that is created is dignified at a redox potential that is conducive to H2 development, and this charge detached phase is constant for around 100 ms. By using dithiol as a molecular wire to link Photo System I to the particles and transport electrons as of the incurable electron transport cofactor of Photo System I, towards the nanoparticle, PS I consumes been covalently connected to the surfaces of like as Pt and also Au nano particles. The Photosystem I or molecular wire or nanoparticle bio conjugates are capable of catalysing the reaction 2H+ + 2e H2 when illuminated. H2 development is not sloweddown by the transference of electrons from PS I in the direction of the nanoparticle via the molecular wire. The speed of H2 evolution is increased fivefold when the system is supplied by means of more effective donor sideways electron-donating kinds. When evaluating hydrogen production based on predicted energy from the sun with observed values falling on unstable slopes, the root mean square error called as RMSE as well as coefficient of determination called R2 are utilised as performance metrics. The most effective model among those taken into consideration, the Deep Learning model performs well and is quite compatible with the observational data. (c) 2023 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.
During the software development process, numerous bugs are reported daily in the software bug repositories. Bug triage assigned these bugs to the most relevant and expert developer for resolution. Moreover, assigning bugs to an incompetent or an over-engaged developer causes repeated reassignment to other developers until it is resolved. This problem can be solved by devising a triage process that assigns bugs to not only expert developers but also to those who are either under-engaged or reasonably engaged but are not over-engaged in work. This paper has designed and implemented work engagement sensitive bug triage that resolves the issue of assigning bugs to developers considering their due work engagement, expertise as well as the current state of activity. For this purpose, a developer profile is built by using metrics to generate three types of scores: technical skill, work engagement and work experience. Metadata features like developer-name, email, developer-work-experience in bug resolution, last and present-work-activity, timestamp, component and priority are used for it. A multi-criteria-based Henry-Garret technique is used to generate a single ranked list of developers from three ranked lists. The performance of the proposed approach is evaluated on four large OOS projects: Mozilla, Eclipse, Netbeans, and Open Office covering 895,439 bug reports accumulated for 33 years of development. The overall system accuracy of the proposed triage using all four datasets is 91.96 +/- 0.05% which is 5.87% better than previously published work. The proposed method is achieved up to 90.30 +/- 0.05 and 97.1 +/- 0.05 MRR and accuracy of reassignment respectively that indicates how significantly it re-assigns the bug to the relevant developers. The results demonstrate improvement in the accuracy of software-bugs triaging as well as a reduction in the probability of bug-tossing.
Accurate forecasting for the different time-series data plays a major role in predicting future analysis that can increase economic benefits. Many research models have been attempted earlier but pose certain challenges due to the random characteristics of the original time-series data in obtaining high-precision forecasting results. To this end, we propose a hybrid convolutional-based extreme learning model named Convolutional Multi-Layer Deep Extreme Learning Machine (CMDELM) adopted with the Extended Elephant Herd Optimization Algorithm (E2HOA) that performs deeper feature extraction with faster learning of optimized features. Also, an Edge-aware Attribute-based Dynamic Graph learning (EADGL) approach is proposed to ensure that the graph-structured network incorporates edge-level information for effective future learning. The CMDELM network employs stacked multiple convolutional ELM layers that use several hidden layers with dense connections to learn high-level features for enhancing forecast accuracy. Dense connections are utilized in the proposed CMDELM task of integrating ELM with CNN to aid the network in extracting feature maps from shallow layers. Moreover, the network's performance is enhanced by adjusting the convolutional kernel sizes and integrating them into the residual unit. Following the convolutional model of a fully connected network, the deep ELM layer is linked to produce the predicted classes for the forecasts. In the forecasting stage, we adopt the E2HOA strategy to optimize the computational parameters for all learning layers and predict an accurate future forecast signal. The E2HOA algorithm improves the separation and updation phases with the consideration of a newborn calf in the elephant herd. E2HOA incorporates new clans and updates them using a threshold value to determine their inclusion, thus achieving an optimal outcome. This makes the learning network achieve the final solution with the optimal key parameters of the CMDELM network. Experimental results covering different competitive models and the evaluated results indicate that our proposed hybrid forecasting system obtains satisfactory accuracy with a Root Mean Square percentage Error (RMSPE) and Symmetric Mean absolute percentage Error (SMAPE) of below 22%, respectively, for PM2.5 concentration, electricity price, and wind speed forecasting results. Hence, the experimental outcomes show that the proposed model performs well in terms of accuracy and provides constant forecasting of time-series.
