Dynamic Quality Adaptation and Bandwidth Allocation for Adaptive Streaming Over Time-Varying Wireless Networks

Artificial Intelligence Aided Joint Bit Rate Selection and Radio Resource Allocation for Adaptive Video Streaming over F-RANs

“…The first stage actor network has five layers with six inputs, including current channel quality, predicted channel quality, video chunk information, untransmitted chunk size, and buffer status. The number of neurons in each DNN layer is [6,128,64,32,1]. The hidden layers have a tanh activation function, while the output layer has a softmax function.…”

“…• Pensive [3], where only bit rate selection is involved • Robust MPC [4], which is based on the classic MPC algorithm • DQA [6], which jointly allocates radio resource and selects bit rate, and converts MDP to a time-sliced optimization problem by Lyapunov optimization PerformAnce AnAlysIs on AverAge bIt rAte, rebufferIng rAtIo, bIt rAte vArIAnce, And overAll Qoe In Fig. 4, we evaluate the average bit rate, rebuffering ratio, bit rate variance, and overall QoE.…”

“…Tian et al [10] proposed a joint radio communication, caching, and computing design for mobile virtual reality delivery in F-RANs, while only trying to maximize the average delay tolerance instead of QoE. Most relevant to the approaches considered in this article, joint bit rate selection and radio resource allocation were designed in [6]. However, by finding the maximal QoE for the multiple time slices, the employed greedy-like searching may lead to a local optimum solution.…”

Energy‐efficient computation offloading in 5G cellular networks with edge computing and D2D communications

“…In fact, the Lyapunov optimisation framework is an efficient optimisation approach to deal with the stochastic optimisation problem, and this optimisation framework makes decisions only using current network resource status and current queue backlogs to stabilise the system, and it does not require a‐priori knowledge of computation offloading or network resource status, thus it can make decision online. In addition, the Lyapunov optimisation has achieved great success, and many cases or problems can use this optimisation framework, such as energy efficiency optimisation issue [36, 37], wireless network resource allocation issue [38], adaptive streaming rate control [33, 39] and so on. As for the computation offloading issue in stochastic network, we can also adopt Lyapunov optimisation framework to solve.…”

A QoE-Oriented Scheduling Scheme for Energy-Efficient Computation Offloading in UAV Cloud System

“…Approaches for solving optimizations include game [15], [16], machine learning for control [7], [17] and convex optimization [4]. The resource for allocation may be the access preambles [18], contention window [7], transmission power [7], [17], bandwidth [19] and caching in the sky [4]. 2) Energy efficient or green wireless communication is an other appealing challenge [20].…”