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

In energy-constrained wireless sensor networks, low energy utilization and unbalanced energy distribution are seriously affecting the operation of the network. Therefore, efficient and reasonable routing algorithms are needed to achieve higher Quality of Service (QoS). For the Dempster–Shafer (DS) evidence theory, it can fuse multiple attributes of sensor nodes with reasonable theoretical deduction and has low demand for prior knowledge. Based on the above, we propose an energy efficient and reliable routing algorithm based on DS evidence theory (DS-EERA). First, DS-EERA establishes three attribute indexes as the evidence under considering the neighboring nodes’ residual energy, traffic, the closeness of its path to the shortest path, etc. Then we adopt the entropy weight method to objectively determine the weight of three indexes. After establishing the basic probability assignment (BPA) function, the fusion rule of DS evidence theory is applied to fuse the BPA function of each index value to select the next hop. Finally, each node in the network transmits data through this routing strategy. Theoretical analysis and simulation results show that DS-EERA is promising, which can effectively prolong the network lifetime. Meanwhile, it can also reach a lower packet loss rate and improve the reliability of data transmission.

In massive multiple-input multiple-output (MIMO) system, channel state information (CSI) is essential for the base station to achieve high performance gain. Recently, deep learning is widely used in CSI compression to fight against the growing feedback overhead brought by massive MIMO in frequency division duplexing system. However, applying neural network brings extra memory and computation cost, which is non-negligible especially for the resource limited user equipment (UE). In this paper, a novel binarization aided feedback network named BCsiNet is introduced. Moreover, BCsiNet variants are designed to boost the performance under customized training and inference schemes. Experiments shows that BCsiNet offers over 30× memory saving and around 2× inference acceleration for encoder at UE compared with CsiNet. Furthermore, the feedback performance of BCsiNet is comparable with original CsiNet. The key results can be reproduced with https://github.com/Kylin9511/BCsiNet.

No abstract

No abstract