Beam hopping (BH) is considered to provide a high level of flexibility manage irregular and time-varying traffic requests in future multi-beam satellite systems. In BH optimization, adopting conventional iterative heuristics may have their own limitations providing timely solutions, directly using data-driven technique approximate optimization variables lead constraint violation degraded performance. this paper, we explore combined learning-and-optimization (L&O) approach an efficient,...

In unmanned aerial vehicle (UAV) applications, the UAV's limited energy supply and storage have triggered development of intelligent energy-conserving scheduling solutions. this paper, we investigate minimization for UAV-aided communication networks by jointly optimizing data-transmission UAV hovering time. The formulated problem is combinatorial non-convex with bilinear constraints. To tackle problem, firstly, provide an optimal algorithm (OPT) a golden section search heuristic (GSS-HEU)....

Low earth orbit (LEO) satellite-assisted communications have been considered as one of the key elements in beyond 5G systems to provide wide coverage and cost-efficient data services. Such dynamic space-terrestrial topologies impose an exponential increase degrees freedom network management. In this paper, we address two practical issues for over-loaded LEO-terrestrial system. The first challenge is how efficiently schedule resources serve a massive number connected users, such that more...

Data-driven approaches, e.g., deep learning (DL),have been widely studied in terrestrial wireless communications fields, proving the benefits and potentials of such techniques. In comparison, DL for satellite networks is to a limited extent literature. this paper, we develop assisted approach facilitate efficient beam hopping (BH) multibeam systems. BH adopted provide high level flexibility manage irregular time variant traffic requests coverage area. Conventional iterative optimization...

The integrated terrestrial and non-terrestrial networks in 5G beyond are envisioned to support dynamic, seamless, differentiated services for emerging use cases with stringent requirements. Such service heterogeneity rapid growth network complexity pose difficulties management resource orchestration. Network slicing paves the way delivering highly customized enabling service-oriented allocation. In this context, artificial intelligence (AI) becomes a key enabler management. However, AI-based...

In practical content delivery, when the time-frequency resources are limited, it is a challenging task to satisfy terminals' data demand in heavy-traffic and mutual-interfered scenario. this paper, we investigate time-efficient energy-efficient solutions for delivery at network edge. We formulate two resource allocation problems, aiming minimizing total transmission time/energy delivery. The problems formulated as mixed-integer linear programming. obtain global optimal solution by...

In recent decade, wireless networks face a large challenge of delivering HTTP adaptive streaming (HAS) due to the dramatic increase traffic. Content caching is an effective method relieve burden and has attracted considerable attention. Although some schemes have been investigated for content in cloud-based radio access (C-RAN), most them were not designed HAS. this paper, we address problem SVC- based HAS over C-RAN. We propose strategy with considering layered property video, hierarchical...

In this paper, we investigate a user-timeslot scheduling problem for downlink unmanned aerial vehicle (UAV)-aided networks, where the UAV serves as an base station. We formulate optimization by jointly determining user and hovering time to minimize UAV's transmission energy. An offline algorithm is proposed solve based on branch bound method golden section search. However, executing suffers from exponential growth of computational time. Therefore, apply deep reinforcement learning (DRL)...

With the exponential growth of mobile video traffic and dramatic diversity wireless channels among users, maintaining a tradeoff between resource consumption perceived experience users is overwhelming challenges. Dynamic Adaptive Streaming over HTTP(DASH), as promising technique to improve transmission efficiency, achieves bitrate adaption at users' ends accommodate unstability channel conditions. However, thriving live services, multicast widely used mode which gains huge economization...

As one of the key enabler technologies 6G, low earth orbit (LEO) satellites can provide ubiquitous coverage and seamless connectivity for data gathering remote areas. In this paper, we consider an optimization problem transmission from numerous Internet Things (IoT) terminals to LEO satellites. A large amount IoT-to-LEO links be connected could render a heavy-loaded scenario which may result in longer waiting time lower throughput. Thus, with limited resources certain duration visible LEO,...

In unmanned aerial vehicle (UAV) applications, the UAV's limited energy supply and storage have triggered development of intelligent energy-conserving scheduling solutions. this paper, we investigate minimization for UAV-aided communication networks by jointly optimizing data-transmission UAV hovering time. The formulated problem is combinatorial non-convex with bilinear constraints. To tackle problem, firstly, provide an optimal relax-and-approximate solution develop a near-optimal...

In unmanned aerial vehicle (UAV)-assisted networks, UAV acts as an base station which acquires the requested data via backhaul link and then serves ground users (GUs) through access network. this paper, we investigate energy minimization problem with a limited power supply for both links. The difficulties solving such non-convex combinatorial lie at high computational complexity/time. solution development, consider approaches from actor-critic deep reinforcement learning (AC-DRL)...

Towards the next generation networks, low earth orbit (LEO) satellites have been considered as a promising component for beyond 5G networks. In this paper, we study downlink LEO-5G communication systems in practical scenario, where integrated LEO-terrestrial system is over-loaded by serving number of terminals with high-volume traffic requests. Our goal to optimize resource scheduling such that amount undelivered data and unserved can be minimized. Due inherent hardness formulated quadratic...

In this paper, we investigate resource allocation algorithm design for secure non-orthogonal multiple access (NOMA) systems empowered by wireless power transfer. With the consideration of an existing eavesdropper, objective is to obtain and energy efficient transmission among users optimizing time, subchannel allocation. Moreover, also take into practical case that statistics channel state information eavesdropper not available. order address optimization problem its high computational...

Energy-efficient federated learning (FL) is important for decentralized learning-based edge computing. The energy consumption of FL largely affected by the efficiency local training in devices and their communication to central server. majority studies have focused on improving latter while continuing use traditional neural networks training. This can be computationally heavy devices, especially given limited supply computation capabilities. In this paper, we propose a joint lightweight...

In this paper, we address ajoint user scheduling and power allocation problem from a machine-learning perspective in order to efficiently minimize data delivery time for multiple-input single-output (MISO) systems. The joint optimization is formulated as mixed-integer non-linear programming problem, such that the requests can be delivered by minimum delay, consumption meet practical requirements. For solving global optimum, provide solution decouple optimization. Due problem's inherent...

In order to improve the effect of online interactive teaching English, this paper analyzes data English in combination with generation confrontation network and simulates human interaction process perform simulation. Moreover, introduces strategy gradient reinforcement learning generator solve problem that is difficult be used for dialogue generation. addition, combines intelligent algorithms construct an system English. The experimental research results show based on B/S model proposed has...

Dynamic Adaptive Streaming over HTTP (DASH) is a prospective video transmission technique. It can select appropriate bitrates for users according to channel conditions and capacities of user equipments. Multicast DASH promising but challenging way improve spectrum efficiency. has not been sufficiently researched. However, in this paper, we focus on investigating allocation scheme multicast service. To end an optimization problem formulated assignment algorithm called Fairness (DMF) proposed....

In the mobile video era, dynamic adaptive streaming over HTTP (DASH) is widely concerned due to its favorable performance in time-variant channel environments. Although DASH follows a decentralised and client-pull paradigm, networks are expected play more active role assist rate adaption. On other hand, heterogeneous cellular (HetNet) considered as an efficient solution cope with exponential growth of traffic, where cell association one key issues. However, most existing methods were not...

Federated Learning (FL), as an effective decentral-ized approach, has attracted considerable attention in privacy-preserving applications for wireless edge networks. In practice, devices are typically limited by energy, memory, and computation capabilities. addition, the communications be-tween central server with constrained resources, e.g., power or bandwidth. this paper, we propose a joint sparsification optimization scheme to reduce energy consumption local training data transmission. On...

Abstract In unmanned aerial vehicle ( UAV )-assisted networks, acts as an base station to serve ground users GUs ) through access network, and meanwhile, the requested data traffic is acquired backhaul link. this paper, we investigate energy minimization problem with limited power supply for both links. The difficulties solving such a non-convex combinatorial lie at high computational complexity/time. solution development, consider approaches from actor-critic deep reinforcement learning...

Low earth orbit (LEO) satellite-assisted communications have been considered as one of key elements in beyond 5G systems to provide wide coverage and cost-efficient data services. Such dynamic space-terrestrial topologies impose exponential increase the degrees freedom network management. In this paper, we address two practical issues for an over-loaded LEO-terrestrial system. The first challenge is how efficiently schedule resources serve massive number connected users, such that more users...