In recent years, with the explosive growth of visual sensors and a large number of related video applications in Internet of Things (IoT), massive video data is generated by IoT devices. Since the volume of video data is far greater than traditional data in IoT, it is challenging to ensure high Quality of Service (QoS) for video uplinking in IoT. To address this challenge, we integrate non-orthogonal multiple access (NOMA) and scalable video coding (SVC) in IoT. To improve the video quality, we formulate a power allocation problem to maximize the average QoS in the proposed integrated system. Due to that the problem is non-convex, we transform it into a monotonic problem based on its hidden monotonicity. Then a power allocation algorithm based on polyblock outer approximation is proposed to solve the problem effectively. Finally, simulation results demonstrate that the proposed algorithm outperforms existing OMA and NOMA based schemes for video uplinking in IoT in terms of QoS and energy efficiency.

Under dynamic traffic, service function chain (SFC) migration is considered as an effective way to improve resource utilization. However, the lack of future network information leads to non-optimal solutions, which motivates us to study reinforcement learning based SFC migration from a long-term perspective. In this paper, we formulate the SFC migration problem as a minimization problem with the objective of total network operation cost under constraints of users' quality of service. We firstly design a deep Q-network based algorithm to solve single SFC migration problem, which can adjust migration strategy online without knowing future information. Further, a novel multi-agent cooperative framework, called MSDF, is proposed to address the challenge of considering multiple SFC migration on the basis of single SFC migration. MSDF reduces the complexity thus accelerates the convergence speed, especially in large scale networks. Experimental results demonstrate that MSDF outperforms typical heuristic algorithms under various scenarios.

Index modulation (IM) brings the reduction of power consumption and complexity of transmitter to classical multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. However, due to the introduction of IM, the complexity of the detector at receiver is greatly increased. Furthermore, the detector also requires the channel state information at receiver (CSIR), which leads to high system overhead. To tackle these challenges, in this paper, we introduce deep learning (DL) in designing a non-iterative detector. Specifically, based on the structural sparsity of the transmitted signal in IM aided MIMO-OFDM (IM-MIMOOFDM) systems, we first formulate the detection process as a sparse reconstruction problem. Then, a DL based detector called IMNet, which combines two subnets with the traditional least square method, is designed to recover the transmitted signal. To the best of our knowledge, this is the first attempt that designs the DL based detector for IM-MIMO-OFDM systems. Finally, to verify the adaptability and robustness of IMNet, simulations are carried out with consideration of correlated MIMO channels and imperfect CSIR. The simulation results demonstrate that the proposed IMNet outperforms existing detectors in terms of bit error rate and computational complexity under various scenarios.

Edge caching has been regarded as an effective way to relieve backhaul pressure as well as reduce service delivery delay. In this paper, we attempt to improve user’s quality of experience (QoE) of video services in cache-enabled heterogeneous networks (HetNets). Scalable video coding (SVC) based video services are considered and hence the proper video quality can be selected for each user according to its channel conditions. Intuitively, caching video layers that cannot be delivered to users leads to the waste of limited cache resource. Based on this observation, we formulate the joint video quality selection and caching problem, with the goal to maximize user’s QoE. Furthermore, we propose a two-fold dynamic programming algorithm to approach the optimal video quality selection and caching strategies. Finally, the simulation results demonstrate that the proposed strategies can utilize the limited cache space more effectively and achieve more QoE gains compared to existing caching strategies.

Recently, a mmWave-based access and backhaul integration heterogeneous networks (HetNets) architecture (mABHetNets) has been envisioned to provide high wireless capacity. Since the access link and the backhaul link share the same mm-wave spectral resource, a large spectrum bandwidth is occupied by the backhaul link, which hinders the wireless access capacity improvement. To overcome the backhaul spectrum occupation problem and improve the network throughput in the existing mABHetNets, we introduce the cache at base stations (BSs). In detail, by caching popular files at small base stations (SBSs), mABHetNets can offload the backhaul link traffic and transfer the redundant backhaul spectrum to the access link to increase the network throughput. However, introducing cache in SBSs will also incur additional power consumption and reduce the transmission power, which can lower the network throughput. In this paper, we investigate spectrum partition between the access link and the backhaul link as well as cache allocation to improve the network throughput in mABHetNets. With the stochastic geometry tool, we develop an analytical framework to characterize cache-enabled mABHetNets and obtain the signal-to-interference-plus-noise ratio (SINR) distributions in line-of-sight (LoS) and non-line-of-sight (NLoS) paths. Then we utilize the SINR distribution to derive the average potential throughput (APT). Extensive numerical results show that introducing cache can bring up to 80% APT gain to the existing mABHetNets.

To cope with rapid growth of video traffic and energy consumption in mobile networks, we propose a spatial modulation (SM) and non-orthogonal multiple access (NOMA) integrated system for multi-user video transmission (SNIS-MUVT). SNIS-MUVT attempts to exploit the benefits from SM and NOMA to achieve high energy efficiency and high throughput. The main contribution of SNIS-MUVT lies in cross-layer design for video-aware transmission and quality of experience (QoE)-driven power allocation. With scalable video coding, base layers (BLs) are transmitted in the spatial domain while enhancement layers (ELs) are transmitted in the signal domain. In the spatial domain, layered SM is performed to support multi-user transmission according to the required BL rates and channel conditions of different users. In the signal domain, ELs are first extracted based on the estimated channel capacity. Then, the extracted ELs are handled by unequal error protection according to their importance before superposed for NOMA transmission. We formulate the QoE-driven power allocation problem in SNIS-MUVT. Both optimal algorithm based on the hidden monotonicity of the problem and suboptimal iterative algorithm with polynomial time are proposed. Finally, simulation results demonstrate that the proposed SNIS-MUVT outperforms existing SM and SM-NOMA integrated schemes in terms of QoE under various scenarios.