Slope Stability Considering the Top Building Load

Slope stability is one of the most important subjects of geotechnics. The slope top-loading plays a key role in the stability of slopes in hill slope areas. When the building load is too large or the point of action from the shoulder is too close, the shear stress of the slope will be significantly greater than its shear strength, resulting in reduced slope stability. Therefore, it is of great importance to study the relationship between the building load and the stability of the slope. This study aims to analyze the influence of different building loads applied at different distances on the top of the slope and deduces their effects on the slope stability. For this purpose, a three-dimensional slope model under different building loads with different distances to the slope shoulder was established using the finite-difference analysis software Flac3D. The results show that the loads applied at different distances on the top of the slope have different effects on the slope stability. The slope factor of safety (FOS) increases with the increase of the distance between the top-loading and the slope shoulder;it varies from 1.37 to 1.53 for the load P = 120 KPa, 1.27 to 1.53 for the load P = 200 KPa, and from 1.18 to 1.44 for P = 300 KPa, resulting in the decrease of the coincidence area between the load-deformation and the potential sliding surface. The slope is no longer affected by the potential risk of sliding at approximately 20 m away from the slope shoulder.

Enhancing source domain availability through data and feature transfer learning for building power load forecasting

During the initial phases of operation following the construction or renovation of existing buildings,the availability of historical power usage data is limited,which leads to lower accuracy in load forecasting and hinders normal usage.Fortunately,by transferring load data from similar buildings,it is possible to enhance forecasting accuracy.However,indiscriminately expanding all source domain data to the target domain is highly likely to result in negative transfer learning.This study explores the feasibility of utilizing similar buildings(source domains)in transfer learning by implementing and comparing two distinct forms of multi-source transfer learning.Firstly,this study focuses on the Higashita area in Kitakyushu City,Japan,as the research object.Four buildings that exhibit the highest similarity to the target buildings within this area were selected for analysis.Next,the two-stage TrAdaBoost.R^(2) algorithm is used for multi-source transfer learning,and its transfer effect is analyzed.Finally,the application effects of instance-based(IBMTL)and feature-based(FBMTL)multi-source transfer learning are compared,which explained the effect of the source domain data on the forecasting accuracy in different transfer modes.The results show that combining the two-stage TrAdaBoost.R^(2) algorithm with multi-source data can reduce the CV-RMSE by 7.23%compared to a single-source domain,and the accuracy improvement is significant.At the same time,multi-source transfer learning,which is based on instance,can better supplement the integrity of the target domain data and has a higher forecasting accuracy.Overall,IBMTL tends to retain effective data associations and FBMTL shows higher forecasting stability.The findings of this study,which include the verification of real-life algorithm application and source domain availability,can serve as a theoretical reference for implementing transfer learning in load forecasting.

Optimal Thermal Insulation Thickness in Isolated Air-Conditioned Buildings and Economic Analysis

The removal building heat load and electrical power consumption by air conditioning system are proportional to the outside conditions and solar radiation intensity. Building construction materials has substantial effects on the transmission heat through outer walls, ceiling and glazing windows. Good thermal isolation for buildings is important to reduce the transmitted heat and consumed power. The buildings models are constructed from common materials with 0 - 16 cm of thermal insulation thickness in the outer walls and ceilings, and double-layers glazing windows. The building heat loads were calculated for two types of walls and ceiling with and without thermal insulation. The cooling load temperature difference method, CLTD, was used to estimate the building heat load during a 24-hour each day throughout spring, summer, autumn and winter seasons. The annual cooling degree-day, CDD was used to estimate the optimal thermal insulation thickness and payback period with including the solar radiation effect on the outer walls surfaces. The average saved energy percentage in summer, spring, autumn and winter are 35.5%, 32.8%, 33.2% and 30.7% respectively, and average yearly saved energy is about of 33.5%. The optimal thermal insulation thickness was obtained between 7 - 12 cm and payback period of 20 - 30 month for some Egyptian Cities according to the Latitude and annual degree-days.

Optimal Scheduling of Air Conditioners for Energy Efficiency

Energy saving is one of the most important research hotspots, by which operational expenditure and CO2 emission can be reduced. Optimal cooling capacity scheduling in addition to temperature control can improve energy efficiency. The main contribution of this work is modeling the telecommunication building for the fabric cooling load to schedule the operation of air conditioners. The time series data of the fabric cooling load of the building envelope is taken by simulation by using Energy Plus, Building Control Virtual Test Bed （BCVTB）, and Matlab. This pre-computed data and other internal thermal loads are used for scheduling in air conditioners. Energy savings obtained for the whole year are about 4% to 6% by simulation and the field study, respectively.

A Conditional Generative adversarial Network for energy use in multiple buildings using scarce data

Building consumption data is integral to numerous applications including retrofit analysis,Smart Grid integration and optimization,and load forecasting.Still,due to technical limitations,privacy concerns and the proprietary nature of the industry,usable data is often unavailable for research and development.Generative adversarial networks(GANs)-which generate synthetic instances that resemble those from an original training dataset-have been proposed to help address this issue.Previous studies use GANs to generate building sequence data,but the models are not typically designed for time series problems,they often require relatively large amounts of input data(at least 20,000 sequences)and it is unclear whether they correctly capture the temporal behaviour of the buildings.In this work we implement a conditional temporal GAN that addresses these issues,and we show that it exhibits state-of-the-art performance on small datasets.22 different experiments that vary according to their data inputs are benchmarked using Jensen-Shannon divergence(JSD)and predictive forecasting validation error.Of these,the best performing is also evaluated using a curated set of metrics that extends those of previous work to include PCA,deep-learning based forecasting and measurements of trend and seasonality.Two case studies are included:one for residential and one for commercial buildings.The model achieves a JSD of 0.012 on the former data and 0.037 on the latter,using only 396 and 156 original load sequences,respectively.