Building energy consumption prediction is important in energy system management, building operation, and energy supply planning. This study proposes a novel model with attention based seq2seq method, which is a deep learning algorithm, to improve the prediction performance. The developed model is performed with experiment on a real energy profile data of an office building in Shenzhen, China. The prediction performance of the proposed hybrid model is evaluated with indicators of MSE, RMSE, MAE and SMAPE. The results demonstrate that attention mechanism can improve the prediction performance of model whose input are time series. Compared with the metrics of prediction result of other models, the MSE, RMSE, MAE, SMAPE of prediction result of proposed model decrease by more than half percent.
New solutions to decarbonisation in the transport sector are prominently required to replace oil consumption. Full battery electric vehicles (BEVs) are usually limited to light-duty vehicles due to their energy density. The aim in this study is to evaluate the technical and economic feasibility of electric trucks that are supplemented by electrified highways (eHighways), instead of using conventional diesel, petrol, and full BEVs. The battery is the most expensive component of electric vehicles, especially for heavy-duty trucks. The principle of eHighway is that electricity is supplied to electric vehicles directly from the electric grid as they travel along the road. The eHighway concept is being developed with two primary methods to connect the roadway to the vehicle: conductive power transfer (CPT) where electric connection to the vehicle can be provided from above or below the vehicle and inductive power transfer that is in-motion wireless power transfer (WPT). If eHighways are installed on the major links that connect main cities, the eHighway technology can be suitable for long-distance journeys. This research evaluates the eHighway technologies of both CPT and in-motion WPT. A case study has been conducted. Various costs are calculated and analyzed. Results show that the driving cost (or selling price) of a heavy-duty electric truck on the eHighways using CPT technology ranges from $0.21 to 0.67 per km with varying daily traffic volume. The driving cost of a heavy-duty electric truck on the eHighways using in-motion WPT technology ranges from $0.22-1.03 depending on daily traffic volume. If fuel and vehicle prices evolve as predicted between now and 2050, eHighways could become an economically feasible form of road transport, especially for heavy-duty trucks, resulting in energy savings and thus reductions in CO2 emission.