In this paper, we introduce a novel scheme for the separate training of deep learning-based autoencoders used for Channel State Information (CSI) feedback. Our distinct training approach caters to multiple users and b...In this paper, we introduce a novel scheme for the separate training of deep learning-based autoencoders used for Channel State Information (CSI) feedback. Our distinct training approach caters to multiple users and base stations, enabling independent and individualized local training. This ensures the more secure processing of data and algorithms, different from the commonly adopted joint training method. To maintain comparable performance with joint training, we present two distinct training methods: separate training decoder and separate training encoder. It’s noteworthy that conducting separate training for the encoder can pose additional challenges, due to its responsibility in acquiring a compressed representation of underlying data features. This complexity makes accommodating multiple pre-trained decoders for just one encoder a demanding task. To overcome this, we design an adaptation layer architecture that effectively minimizes performance losses. Moreover, the flexible training strategy empowers users and base stations to seamlessly incorporate distinct encoder and decoder structures into the system, significantly amplifying the system’s scalability. .展开更多
In this paper, we propose a cross-layer design combining adaptive modulation coding (AMC) and automatic repeat request (ARQ) to minimize the bit energy consumption under both packet loss rate and retransmission delay ...In this paper, we propose a cross-layer design combining adaptive modulation coding (AMC) and automatic repeat request (ARQ) to minimize the bit energy consumption under both packet loss rate and retransmission delay constraints. We analyze the best constellation size of M-ary square quadrature amplitude modulation (MQAM) in different distance, and give advice on retransmission limits under different packet loss rates. The impacts of path loss fading and additive white Gaussian noise (AWGN)are taken into consideration. The computation of energy consumption includes the circuit, transmission and retransmission energies at both transmitter and receiver sides. Numerical results are obtained to verify the validity of our design. We also show that the retransmission benefit varies with the packet loss rate constraint.展开更多
文摘In this paper, we introduce a novel scheme for the separate training of deep learning-based autoencoders used for Channel State Information (CSI) feedback. Our distinct training approach caters to multiple users and base stations, enabling independent and individualized local training. This ensures the more secure processing of data and algorithms, different from the commonly adopted joint training method. To maintain comparable performance with joint training, we present two distinct training methods: separate training decoder and separate training encoder. It’s noteworthy that conducting separate training for the encoder can pose additional challenges, due to its responsibility in acquiring a compressed representation of underlying data features. This complexity makes accommodating multiple pre-trained decoders for just one encoder a demanding task. To overcome this, we design an adaptation layer architecture that effectively minimizes performance losses. Moreover, the flexible training strategy empowers users and base stations to seamlessly incorporate distinct encoder and decoder structures into the system, significantly amplifying the system’s scalability. .
文摘In this paper, we propose a cross-layer design combining adaptive modulation coding (AMC) and automatic repeat request (ARQ) to minimize the bit energy consumption under both packet loss rate and retransmission delay constraints. We analyze the best constellation size of M-ary square quadrature amplitude modulation (MQAM) in different distance, and give advice on retransmission limits under different packet loss rates. The impacts of path loss fading and additive white Gaussian noise (AWGN)are taken into consideration. The computation of energy consumption includes the circuit, transmission and retransmission energies at both transmitter and receiver sides. Numerical results are obtained to verify the validity of our design. We also show that the retransmission benefit varies with the packet loss rate constraint.
