Deep reinforcement learning (DRL) has superior autonomous decision-making capabilities, combining deep learning and reinforcement learning (RL). Unlike DRL employs deep neural networks (DNNs), broad RL (BRL) adopts the broad learning system (BLS) that is established with flat networks to generate the strategy. This article proposes the multiagent adaptive broad-DRL (ABDRL) approach for traffic light control (TLC), which combines the broad network with the deep network structure. Specifically, the structure of ABDRL first expands in the form of flatted broad networks. Then, the feature representation module that contains DNNs is employed to extract the critical traffic information. In addition, experiences sampled randomly by the experience replay mechanism cannot reflect the current training status of the agent effectively. In order to alleviate the impacts caused by random sampling, the forgetful experience mechanism (FEM) is incorporated into ABDRL. The FEM enables the agent to discriminate the importance of experiences stored in the experience reply buffer to improve robustness and adaptability. We validate the effectiveness of ABDRL in TLC, and the results illustrate the optimality and robustness of ABDRL over the state-of-the-art multiagent DRL (MADRL) algorithms.

Dynamic Adaptive Streaming over HTTP (DASH) has been widely adopted to deal with such user diversity as network conditions and device capabilities. In DASH systems, the computation-intensive transcoding is the key technology to enable video rate adaptation, and cloud has become a preferred solution for massive video transcoding. Yet the cloud-based solution has the following two drawbacks. First, a video stream now has multiple versions after transcoding, which increases the network traffic traversing the core network. Second, the transcoding strategy is normally fixed and thus is not flexible to adapt to the dynamic change of viewers. Considering that mobile users, who normally experience dynamic network conditions from time to time, have occupied a very large portion of the total users, adaptive wireless transcoding is of great importance. To this end, we propose an adaptive wireless video transcoding framework based on the emerging edge computing paradigm by deploying edge transcoding servers close to base stations. With this design, the core network only needs to send the source video stream to the edge transcoding server rather than one stream for each viewer, and thus the network traffic across the core network is significantly reduced. Meanwhile, our edge transcoding server cooperates with the base station to transcode videos at a finer granularity according to the obtained users' channel conditions, which smartly adjusts the transcoding strategy to tackle with time-varying wireless channels. In order to improve the bandwidth utilization, we also develop efficient bandwidth adjustment algorithms that adaptively allocate the spectrum resources to individual mobile users. We validate the effectiveness of our proposed edge computing based framework through extensive simulations, which confirm the superiority of our framework.

In order to achieve seamless integration between heterogeneous wireless networks on the basis of maintaining good compatibility, this paper designs an innovative heterogeneous wireless convergence protocol stack. Based on the protocol stack, the parallel transmission of heterogeneous wireless networks is studied. The optimized resource allocation strategy is adopted to achieve load balancing between heterogeneous networks and high-speed wireless access at the user end. The cross-layer ARQ method is adopted to guarantee service quality.