Dual decomposition scheme for resource allocation problem in networks with moving nodes

In medical vehicular networks, medical vehicles can serve as efficient mobile medical service points to provide necessary and critical medical services for patients while in motion. The delay requirement is very vital for medical services to guarantee service quality and save the lives of patients. Mobile Edge Computing (MEC), as an emerging network paradigm, enables the computation extensive tasks to be offloaded to edge servers, efficiently reducing the delay and bandwidth demands. MEC technology is a promising solution to provide high-quality medical services for users in medical vehicular networks. However, task offloading and resource allocation incurs additional service delay and energy consumption, affecting the overall service performance and Quality of Experience (QoE) of users. Thus, realizing the optimal task offloading and resource allocation in MEC-enabled medical vehicular networks, to reduce task completion time and energy consumption, becomes a potential challenge. To address the challenge, we investigate the joint task offloading and resource allocation problem in MEC-enabled medical vehicular networks to improve the QoE of users. Considering the resource requirements and QoS constraint, we formulate a multi-objective optimization model, with the target of average task completion time and average energy consumption minimization. On this basis, we propose a MOEAD-based task offloading and resource allocation (IMO) algorithm to solve it. Furthermore, in order to obtain the optimal solution and speed up the algorithm convergence, we design a greedy strategy-based population initialization algorithm. The extensive simulations demonstrate that compared to existing algorithms, our proposed IMO algorithm can obtain a smaller average completion time, and achieve better tradeoff between task completion time and energy consumption.

The problem of optimal resource allocation in wireless networks usually involves scheduling of the network independent sets (ISs), of which the number increases exponentially in the network scale. To deal with such large-scale optimization problems, traditional approaches often resort to some heuristics or iterative algorithms for obtaining a relatively small set of ISs to solve the problems, but at the cost of suboptimality or long convergence time. In this paper, we consider wireless network resource allocation in dynamic flow environments, aiming at maximizing the network capacity. We propose a learning-based approach to find ISs based on the dynamic flow demands. Specifically, instead of searching for individual ISs, we propose to learn groups of ISs by using a deep belief network (DBN). We present detailed design of the DBN-based learning method including details in the offline training and online running phases. Simulation results demonstrate that our DBN-based method outperforms existing ones in terms of achieved network capacity and computation time.

The crowd-creation space is a manifestation of the development of innovation theory to a certain stage. With the creation of the crowd-creation space, the problem of optimizing the resource allocation of the crowd-creation space has become a research hotspot. The emergence of cloud computing provides a new idea for solving the problem of resource allocation. Common cloud computing resource allocation algorithms include genetic algorithms, simulated annealing algorithms, and ant colony algorithms. These algorithms have their obvious shortcomings, which are not conducive to solving the problem of optimal resource allocation for crowd-creation space computing. Based on this, this paper proposes an In the cloud computing environment, the algorithm for optimizing resource allocation for crowd-creation space computing adopts a combination of genetic algorithm and ant colony algorithm and optimizes it by citing some mechanisms of simulated annealing algorithm. The algorithm in this paper is an improved genetic ant colony algorithm (HGAACO). In this paper, the feasibility of the algorithm is verified through experiments. The experimental results show that with 20 tasks, the ant colony algorithm task allocation time is 93ms, the genetic ant colony algorithm time is 90ms, and the improved algorithm task allocation time proposed in this paper is 74ms, obviously superior. The algorithm proposed in this paper has a certain reference value for solving the creative space computing optimization resource allocation.

This paper is devoted to studying the processes of resource allocation in dynamic resource networks. In such networks, the capacities of the arcs depend on time. Resource allocation in the network occurs in discrete time. The resource of each vertex is distributed only between adjacent vertices according to some rules. The study of the processes of resource redistribution in such networks is carried out. The main goal is to develop methods for finding the limit state (distribution) of a resource in a dynamic resource network. It is shown that the approach based on the construction of an auxiliary network is also applicable to reduce the problem of resource allocation in a dynamic network to a similar problem in an auxiliary network. Theorems on the existence of a limit state on an auxiliary graph are proved for strongly regular periodic dynamical networks. To find the limit states, one can use the approaches which are developed for the shortest path problem in dynamic networks.

Multiuser Orthogonal Frequency Division Multiple Access (OFDMA) networks, such as Long Term Evolution networks, use the frequency reuse-1 model to face the tremendous increase of mobile traffic demands, and to increase network capacity. However, inter-cell interference problems are generated, and they have a negative impact on cell-edge users performance. Resource and power allocation should be managed in a manner that alleviates the negative impact of inter-cell interference on system performance. In this paper, we formulate a novel centralized multi-cell resource and power allocation problem for multiuser OFDMA networks. The objective is to maximize system throughput while guaranteeing a proportional fair rate for all the users. We decompose the joint problem into two independent problems: a resource allocation problem and a power allocation problem. We prove that each of these problems is a convex optimization problem, and that their optimal solution is also an optimal solution to the original joint problem. Lagrange duality theory and subgradient projection method are used to solve the centralized power allocation problem. We study the convergence of our centralized approach, and we find out that it reduces inter-cell interference, and increases system throughput and spectral efficiency in comparison with the frequency reuse-1 model, reuse-3 model, fractional frequency reuse, and soft frequency reuse techniques.

The cross-layer resource allocation problem in wireless multi-hop networks (WMHNs) has been extensively studied in the past few years. Most of these studies assume that every node has the perfect channel state information (CSI) of other nodes. In practical settings, however, the networks are generally dynamic and CSI usually becomes outdated when it is used, due to the time-variant channel and feedback delay. To deal with this issue, we study the cross-layer resource allocation problem in dynamic WMHNs with outdated CSI under channel conditions where there is correlation between the outdated CSI and current CSI. Two major contributions are made in this work: (1) a closed-form expression of conditional average capacity is derived under the signal-to-interference-plus-noise ratio (SINR) model; (2) a joint optimization problem of congestion control, power control, and channel allocation in the context of outdated CSI is formulated and solved in both centralized and distributed manners. Simulation results show that the network utility can be improved significantly using our proposed algorithm.

Federated deep reinforcement learning for task offloading and resource allocation in mobile edge computing-assisted vehicular networks

The deployment of 6G vehicle-to-everything (V2X) networks is a challenging task given the 6G requirements of ultra-high data rates along with ultra-low latency levels. For intelligent transportation systems (ITSs), V2X communications involve a high density of user equipment (UE), vehicles, and next-generation Node-B (gNB). Therefore, optimal management of the current network infrastructure plays a key role in minimizing energy and latency. Optimal resource allocation using linear programming methods cannot be scaled to the required scenarios of 6G V2X communications and is not suitable for online allocation. To overcome these limitations, deep reinforcement learning (DRL) is a promising approach given its properties of direct integration with online allocation models. In this work, we investigate the problem of optimal resource allocation in 6G V2X networks, where ITSs are deployed to execute tasks offloaded by vehicles subject to data rate and latency requirements. We apply a policy optimization-based DRL to jointly reduce the number of active gNBs and the latency concerning the offloaded tasks going on in the vehicle. The model is analyzed for several ITS scenarios to investigate the performance observed and the advantages of the proposed policy optimization allocation for 6G V2X networks. Our evaluation results illustrate that the proposed DRL-based algorithm produces dynamic solutions that approximate the optimal ones at reasonable rates of energy consumption. Our numerical results indicate that DRL-based solutions are distinguished by equivalently balanced energy consumption under different scenarios.

This paper considers the network resource allocation problem in multi-service MEC networks, and in particular considers joint spectrum and computing resource allocation in an edge network service system. The resource allocation problem under consideration is formulated as an optimization problem, which takes into account users’ minimum service requirements in terms of the service delay, transmission rate, and computation rate, with an objective to minimize the average service delay of a user’s service request. To solve the problem, we propose a deep-Q-network (DQN) based joint spectrum and computing resource allocation algorithm, which attempts to optimize the resource allocation for each service request by learning a more efficient allocation scheme so as to better adapt to dynamic traffic arrivals, diverse service requirements, and complex environmental conditions. Simulation results show that the proposed resource allocation algorithm can efficiently reduce the average service delay compared with two benchmark algorithms.

Next generation high data rate applications such as High-Definition (HD) video transmission place a heavy load on wireless network resources. To achieve the strict quality of service requirements of HD video in a multi-user network requires efficient resource allocation. Rate-distortion theory provides an appropriate basis for this. The Nash Bargaining Solution (NBS) is proven to generate an optimal solution to a rate-distortion based convex resource allocation problem. Particle Swarm Optimization (PSO) is a meta-heuristic optimizer capable of generating near-optimal solutions. PSO, however, is not constrained to convex optimization problems. The motivation of this work is to demonstrate a PSO implementation capable of achieving an optimal solution to the resource allocation problem. The capability of the PSO approach to reach an optimal solution suggests its potential for resource allocation in a network of heterogeneous applications where convex optimization methods do not apply.

As a promising solution for future indoor access networks, resource allocation in Visible light communication or LiFi networks is subject to lots of researches. An interesting approach for network algorithm design is to use some knowledge about the future of the network. With this regards, the anticipatory design may improve the performance of the system in terms of delay and throughput. This paper reviews the state-of-the-art anticipatory algorithms proposed in the literature, given different prediction capabilities. The key element that all of these algorithms share is to find an event that correlates the current actions to the performance of the network in the future. Apart from the amount of possible prediction, two main approaches have been proposed for problem formulation. The optimal anticipatory resource allocation problem can be formulated in terms of a T-step look-ahead optimization problem. This approach requires more accurate information about the future of the network and yields higher performance improvements. The objective function can be adjusted to achieve high fairness and throughput or low latency in the system. On the other hand, the resource allocation algorithm can be expressed as a matching problem on a bipartite graph. The partial knowledge of the future can be added to the problem using proper heuristic preference functions.

An energy-efficient resource allocation strategy in massive MIMO-enabled vehicular edge computing networks

As one technique for autonomous driving, vehicular networks can achieve high efficiency with vehicle-and-infrastructure cooperation, bringing high safety and many value-added services. To achieve higher communication efficiency, much effort has been done to cope with the resource allocation issues for vehicular networks. Nevertheless, due to the strong nonconvexity and nonlinearity, the classical joint resource allocation problem in vehicular networks is typically NP-hard. The multiagent reinforcement learning (MARL) has emerged as a promising solution to tackle this challenge but its stability and scalability are not satisfactory when the amount of vehicles gets increased. In this article, we mainly investigate the issue of joint spectrum and power allocation in vehicular communication networks, and carefully consider the interactions between the vehicles and environment by incorporating the cooperative stochastic game theory with MARL, named complete-game MARL (CG-MARL), to achieve a better convergence and stability with the theoretical computational complexity <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {O}(n^{N})$ </tex-math></inline-formula> with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> denoting the dimension of action space and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> denoting the number of V2X Vehicular. Furthermore, the mean-field game (MFG) theory is employed to further enhance the MARL for decreasing the horrible computing resource consumption caused by the CG-MARL to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {O}(n^{2})$ </tex-math></inline-formula> while maintaining an approximate performance. The simulation results demonstrate that the proposed mean-field-aided MARL (MF-MARL) for vehicular network resource allocation can achieve 95% near-optimal performance with much lower complexity, which indicates its significant potentials in the scenarios with massive and dense vehicles.

Resource allocation and admission control algorithm based on non-cooperation game in wireless mesh networks

Resource allocation problem in high-speed railway wireless communication networks is one of the key issues to improve the efficiency of resource utilization. However, traditional resource allocation methods cannot be directly applied to this special communication system. In this paper, we propose a resource allocation approach for high-speed railway downlink orthogonal frequency-division multiplexing (OFDM) system with multiple-input multiple-output (MIMO) antennas. Sub-carriers, antennas, time slots, and power are jointly considered, which is formulated as a mixed-integer nonlinear programming problem. The effect of the moving speed on Doppler shift is analyzed to calculate the inter-carrier interference power. The objective is to maximize the throughput under the constraint of total transmission power. In order to reduce computational complexity, suboptimal solution to the optimization problem is obtained by quantum-behaved particle swarm optimization. Simulation results show that the proposed resource allocation strategy has a better performance compared with an existing one.