skip to main content


Title: A Markovian ROHC Control Mechanism Based on Transport Block Link Model in LTE Networks
In many packet-switched wireless systems including cellular networks, RObust Header Compression (ROHC) plays an important role in improving payload efficiency by reducing the number of header bits in a link session. However, there are only very few research works addressing the optimized control of ROHC. Our recent studies have demonstrated the advantage of a trans-layer ROHC design that exploits lower layer link status. We have presented a unidirectional ROHC design based on a partially observable Markov decision process formulation that enables the transmitter to decide the header compression level without receiver feedback. The present work considers the physical channel dynamics in an LTE environment and how they affect header decompressor status. Our new model takes into consideration the transport block (TBs) size defined in LTE transmission according to the modulation and coding scheme (MCS). Our novel and practical model can significantly improve the efficiency of the transmission when compared to a traditional timer-based ROHC control.  more » « less
Award ID(s):
1702752 1443870
NSF-PAR ID:
10066945
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
IEEE International Conference on Communications
ISSN:
1938-1883
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The two major types are Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks. It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations. Recently two works have focused on FPGA implementation of inference phase of LSTM RNNs with model compression. First, ESE uses a weight pruning based compressed RNN model but suffers from irregular network structure after pruning. The second work C-LSTM mitigates the irregular network limitation by incorporating block-circulant matrices for weight matrix representation in RNNs, thereby achieving simultaneous model compression and acceleration. A key limitation of the prior works is the lack of a systematic design optimization framework of RNN model and hardware implementations, especially when the block size (or compression ratio) should be jointly optimized with RNN type, layer size, etc. In this paper, we adopt the block-circulant matrixbased framework, and present the Efficient RNN (E-RNN) framework for FPGA implementations of the Automatic Speech Recognition (ASR) application. The overall goal is to improve performance/energy efficiency under accuracy requirement. We use the alternating direction method of multipliers (ADMM) technique for more accurate block-circulant training, and present two design explorations providing guidance on block size and reducing RNN training trials. Based on the two observations, we decompose E-RNN in two phases: Phase I on determining RNN model to reduce computation and storage subject to accuracy requirement, and Phase II on hardware implementations given RNN model, including processing element design/optimization, quantization, activation implementation, etc. 1 Experimental results on actual FPGA deployments show that E-RNN achieves a maximum energy efficiency improvement of 37.4× compared with ESE, and more than 2× compared with C-LSTM, under the same accuracy. 
    more » « less
  2. null (Ed.)
    Channel state information (CSI) plays a vital role in scheduling and capacity-approaching transmission optimization of massive MIMO communication systems. In frequency division duplex (FDD) MIMO systems, forward link CSI reconstruction at transmitter relies on CSI feedback from receiving nodes and must carefully weigh the tradeoff between reconstruction accuracy and feedback bandwidth. Recent application of recurrent neural networks (RNN) has demonstrated promising results of massive MIMO CSI feedback compression. However, the cost of computation and memory associated with RNN deep learning remains high. In this work, we exploit channel temporal coherence to improve learning accuracy and feedback efficiency. Leveraging a Markovian model, we develop a deep convolutional neural network (CNN)-based framework called MarkovNet to efficiently encode CSI feedback to improve accuracy and efficiency. We explore important physical insights including spherical normalization of input data and deep learning network optimizations in feedback compression. We demonstrate that MarkovNet provides a substantial performance improvement and computational complexity reduction over the RNN-based work.We demonstrate MarkovNet’s performance under different MIMO configurations and for a range of feedback intervals and rates. CSI recovery with MarkovNet outperforms RNN-based CSI estimation with only a fraction of computational cost. 
    more » « less
  3. Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning, which affects performance and throughput; 2) the increased training complexity; and 3) the lack of rigirous guarantee of compression ratio and inference accuracy. To overcome these limitations, this paper proposes CirCNN, a principled approach to represent weights and process neural networks using block-circulant matrices. CirCNN utilizes the Fast Fourier Transform (FFT)-based fast multiplication, simultaneously reducing the computational complexity (both in inference and training) from O(n2) to O(n log n) and the storage complexity from O(n2) to O(n), with negligible accuracy loss. Compared to other approaches, CirCNN is distinct due to its mathematical rigor: the DNNs based on CirCNN can converge to the same "effectiveness" as DNNs without compression. We propose the CirCNN architecture, a universal DNN inference engine that can be implemented in various hardware/software platforms with configurable network architecture (e.g., layer type, size, scales, etc.). In CirCNN architecture: 1) Due to the recursive property, FFT can be used as the key computing kernel, which ensures universal and small-footprint implementations. 2) The compressed but regular network structure avoids the pitfalls of the network pruning and facilitates high performance and throughput with highly pipelined and parallel design. To demonstrate the performance and energy efficiency, we test CirCNN in FPGA, ASIC and embedded processors. Our results show that CirCNN architecture achieves very high energy efficiency and performance with a small hardware footprint. Based on the FPGA implementation and ASIC synthesis results, CirCNN achieves 6 - 102X energy efficiency improvements compared with the best state-of-the-art results. 
    more » « less
  4. We revisit the performance of a canonical system design for edge-assisted AR that simply combines off-the-shelf H.264 video encoding with a standard object tracking technique. Our experimental analysis shows that the simple canonical design for edge-assisted object detection can achieve within 3.07%/1.51% of the accuracy of ideal offloading (which assumes infinite network bandwidth and the total network transmission time of a single RTT) under LTE/5G mmWave networks. Our findings suggest that recent trend towards sophisticated system architecture design for edge-assisted AR appears unnecessary. We provide insights for why video compression plus on-device object tracking is so effective in edge-assisted object detection, draw implications to edge-assisted AR research, and pose open problems that warrant further investigation into this surprise finding. 
    more » « less
  5. Achieving reliable acoustic wireless video transmissions in the extreme and uncertain underwater environment is a challenge due to the limited bandwidth and the error-prone nature of the channel. Aiming at optimizing the received video quality and the user's experience, an adaptive solution for underwater video transmissions is proposed that is specifically designed for Multi-Input Multi-Output (MIMO -based Software-Defined Acoustic Modems (SDAMs . To keep the video distortion under an acceptable threshold and to keep the Physical-Layer Throughput (PLT high, cross-layer techniques utilizing diversity-spatial multiplexing and Unequal Error Protection (UEP are presented along with the scalable video compression at the application layer. Specifically, the scalability of the utilized SDAM with high processing capabilities is exploited in the proposed structure along with the temporal, spatial, and quality scalability of the Scalable Video Coding (SVC H.264/MPEG-4 AVC compression standard. The transmitter broadcasts one video stream and realizes multicasting at different users. Experimental results at the Sonny Werblin Recreation Center, Rutgers University-NJ, are presented. Several scenarios for unknown channels at the transmitter are experimentally considered when the hydrophones are placed in different locations in the pool to achieve the required SVC-based video Quality of Service (QoS and Quality of Experience (QoE given the channel state information and the robustness of different SVC scalability. The video quality level is determined by the best communication link while the transmission scheme is decided based on the worst communication link, which guarantees that each user is able to receive the video with appropriate quality. 
    more » « less