No abstract

In massive multiple-input multiple-output (MIMO) system, user equipment (UE) needs to send downlink channel state information (CSI) back to base station (BS). However, the feedback becomes expensive with the growing complexity of CSI in massive MIMO system. Recently, deep learning (DL) approaches are used to improve the reconstruction efficiency of CSI feedback. In this paper, a novel feedback network named CRNet is proposed to achieve better performance via extracting CSI features on multiple resolutions. An advanced training scheme that further boosts the network performance is also introduced. Simulation results show that the proposed CRNet outperforms the state-of-the-art CsiNet under the same computational complexity without any extra information. The open source codes are available at https://github.com/Kylin9511/CRNet

No abstract

Typical plug-in hybrid electric buses (PHEBs) with fast-charged Lithium titanate battery, which might be fulfill about 70 percent distance of a representative city-bus-route, have been adopted in many Chinese cities. Considering that the detailed information of the driving cycle could be deduced with the historical driving data and online estimation methods, there might be an opportunity for applying the dynamic programming (DP)-based global optimal energy management strategy for these PHEBs. But the road-slopes or the variable loads might induce transient fluctuations of the driving resistance in a given driving cycle. Meantime, the single-shaft parallel configuration, with Automatic Mechanical Transmission (AMT), might constrain the implementability of the optimal energy distribution from DP-based strategy. Therefore, in this paper a novel correctional DP algorithm is brought forward to balance the optimization of the fuel economy and the drivability. Simulation results demonstrate that, integrated with the correctional logic of the AMT gear-shifting, the proposed energy management strategy can guarantee the engine and the electric machine (EM) work in the high-efficiency area with the optimal energy distribution, while keeping the drivability in the variation of the road-slope and loads. The proposed method might give a technical solution to these typical PHEB with a lower cost system configuration of the powertrain in China.Index Terms-plug-in hybrid electric bus; single-shaft parallel hybrid powertrain; energy management strategy; dynamic programming; drivability

No abstract