Search

Summary: Wireless communications often suffer from legitimate transmissions regarding malicious jamming attacks launched through the smart jammer. The drone or unmanned aerial vehicle (UAV) communication networks derived with reconfigurable intelligent surfaces (RIS) increase the issues of beam selection and proactive handoff in terahertz (THz). Thus, a new heuristic strategy is designed for efficient and incorporated optimization of the beamforming vector and anti‐jamming transmit power allocation in undefined environments. Here, the transmit power allocation and beamforming matrix of UAV are optimized with the developed hybrid heuristic algorithm of the Hybrid Crow Black Widow Search Optimization (HCBWSO) algorithm for maximizing the system achievable rate. Here, the HCBWSO algorithm is implemented to integrate with the Crow search algorithm (CSO) and Black Widow Optimization (BWO). The second contribution is to adopt RIS into THz–UAV communications, a new Enhanced Deep Temporal Convolutional Network (EDTCN) for predicting the future beam and proactive handoff of UAVs based on their prior analysis of the UAV locations, where the HCBWSO algorithm is utilized for recommending EDTCN. Here, the training of the EDTCN needs to be done with the collection of UAV information from the DEEPMIMO dataset for predicting the future beams and, also, tracking the location of the UAV. EDTCN helps in increasing the possibility of expanding the UAV coverage and also increases the consistency of the THz communication system. Thus, the prediction of the future beam increases the coverage area of the UAV and also maximizes the system rate in the THz communication system. [ABSTRACT FROM AUTHOR]

In general, Wireless Sensor Networks (WSNs) require secure routing approaches for delivering the data packets to their sinks or destinations. Most of the WSNs identify particular events in their explicit platforms. However, several WSNs may examine multiple events using numerous sensors in a similar place. Multi-sink and multi-hop WSNs include the ability to offer network efficiency by securing effective data exchanges. The group of nodes in the multi-sink scenario is described through a distance vector. Though, the efficiency of multi-sink WSNs is considerably impacted by the routing of data packets and sink node placement in the cluster. In addition, many WSNs for diverse reasons existed in the similar geographical region. Hence, in this task, a secured energy-efficient routing technique is designed for a Wireless sensor network with Large-scale and multiple sink nodes. Here, the concept of an improved meta-heuristic algorithm termed Adaptive Squirrel Coyote Search Optimization (ASCSO) is implemented for selecting the accurate selection of cluster head. The fitness function regarding residual distance, security risk, energy, delay, trust, and Quality of Service (QoS) is used for rating the optimal solutions. The consumption of energy can be reduced by measuring the mean length along with the cluster head and multiple sink nodes. The latest two heuristic algorithms such as Coyote Optimization Algorithm (COA) and Squirrel Search Algorithm (SSA) are integrated for suggesting a new hybrid heuristic technique. Finally, the offered work is validated and evaluated by comparing it with several optimization algorithms regarding different evaluation metrics between the sensor and sink node. [ABSTRACT FROM AUTHOR]

Edge servers, which are small servers located close to mobile users, have the potential to greatly reduce delay and backhaul traffic of mobile Internet applications by moving cloud services to the edge of the network. Due to limited capacity of edge servers and dynamic request arrival, proper service caching at the edge is essential to guarantee good performance. This paper proposes a tractable online algorithm called retrospective download with least-requested deletion that caches services dynamically without any assumptions on the arrival patterns of mobile applications. We evaluate the competitive ratio of our policy, which quantifies the worst case performance in comparison to an optimal offline policy. We prove that the competitive ratio of our policy is linear with the capacity of the edge server. We also show that no deterministic online policy can achieve a competitive ratio that is asymptotically better than ours. Moreover, we prove that our policy is scalable, in the sense that it only needs doubled capacity to achieve a constant competitive ratio. The utility of our online policy is further evaluated on real-world traces. These trace-based simulations demonstrate that our policy has better, or similar, performance compared with many intelligent offline policies. [ABSTRACT FROM AUTHOR]

The solution strategy of the heuristic algorithm is pre-set and has good performance in the conventional cloud resource scheduling process. However, for complex and dynamic cloud service scheduling tasks, due to the difference in service attributes, the solution efficiency of a single strategy is low for such problems. In this paper, we presents a hyper-heuristic algorithm based on reinforcement learning (HHRL) to optimize the completion time of the task sequence. Firstly, In the reward table setting stage of HHRL,we introduce population diversity and integrate maximum time to comprehensively determine the task scheduling and the selection of low-level heuristic strategies. Secondly, a task computational complexity estimation method integrated with linear regression is proposed to influence task scheduling priorities. Besides, we propose a high-quality candidate solution migration method to ensure the continuity and diversity of the solving process. Compared with HHSA, ACO, GA, F-PSO, etc, HHRL can quickly obtain task complexity, select appropriate heuristic strategies for task scheduling, search for the the best makspan and have stronger disturbance detection ability for population diversity. [ABSTRACT FROM AUTHOR]

To comply with the trend of ubiquitous intelligence in 6G, native AI wireless networks are proposed to orchestrate and control communication, computing, data, and AI model resources according to network status, and efficiently provide users with quality-guaranteed AI services. In addition to the quality of communication services, the quality of AI services (QoAISs) includes multiple dimensions, such as AI model accuracy, overhead, and data privacy. This paper proposes a QoAIS optimization method for AI training services in 6G native AI wireless networks. To improve the accuracy and reduce the delay of AI services, we formulate an integer programming problem to obtain proper task scheduling and resource allocation decisions. To quickly obtain decisions that meet the requirements of each dimension of QoAIS, we further transform the single-objective optimization problem into a multi-objective format to facilitate the QoAIS configuration of network protocols. Considering the computational complexity, we propose G-TSRA and NSG-TSRA heuristic algorithms to solve the proposed problems. Finally, the feasibility and performance of QoAIS optimization are verified by simulation. [ABSTRACT FROM AUTHOR]

The panel block is a quite important "intermediate product" in the shipbuilding process. However, the assembly efficiency of the panel block assembly line is not high. Therefore, rational scheduling optimization is of great significance for improving shipbuilding efficiency. Currently, the processing sequence of the panel blocks in the panel block assembly line is mainly determined using heuristic and metaheuristic algorithms. However, these algorithms have limitations, such as small problem-solving capacity and low computational efficiency. To address these issues, this study proposes an end-to-end approach based on deep reinforcement learning to solve the scheduling problem of the ship's panel block assembly line. First, a Markov decision model is established, and a disjunctive graph is creatively used to represent the current scheduling status of the panel block assembly line. Then, a policy function based on a graph isomorphism network is designed to extract information from the disjunctive graph's state and train it using Proximal Policy Optimization algorithms. To validate the effectiveness of our method, tests on both real shipbuilding data and publicly available benchmark datasets are conducted. We compared our proposed end-to-end deep reinforcement learning algorithm with heuristic algorithms, metaheuristic algorithms, and the unimproved reinforcement learning algorithm. The experimental results demonstrate that our algorithm outperforms other baseline methods in terms of model performance and computation time. Moreover, our model exhibits strong generalization capabilities for larger instances. [ABSTRACT FROM AUTHOR]

Heuristic optimization algorithms have been proved to be powerful in solving nonlinear and complex optimization problems; therefore, many effective optimization algorithms have been applied to solve optimization problems in real-world scenarios. This paper presents a modification of the recently proposed Gaining–Sharing Knowledge (GSK)-based algorithm and applies it to optimize resource scheduling in the Internet of Vehicles (IoV). The GSK algorithm simulates different phases of human life in gaining and sharing knowledge, which is mainly divided into the senior phase and the junior phase. The individual is initially in the junior phase in all dimensions and gradually moves into the senior phase as the individual interacts with the surrounding environment. The main idea used to improve the GSK algorithm is to divide the initial population into different groups, each searching independently and communicating according to two main strategies. Opposite-based learning is introduced to correct the direction of convergence and improve the speed of convergence. This paper proposes an improved algorithm, named parallel opposition-based Gaining–Sharing Knowledge-based algorithm (POGSK). The improved algorithm is tested with the original algorithm and several classical algorithms under the CEC2017 test suite. The results show that the improved algorithm significantly improves the performance of the original algorithm. When POGSK was applied to optimize resource scheduling in IoV, the results also showed that POGSK is more competitive. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for network slicing in 5G backhaul networks, targeting services with low or very low latency requirements. We propose a modified A* algorithm that incorporates network quality of service parameters into a composite metric. The algorithm's efficiency outperforms that of Dijkstra's algorithm using a precalculated heuristic function and a real-time monitoring strategy for congestion management. We integrate the algorithm into an SDN module called a path computation element, which computes the optimal path for the network slices. Experimental results show that the proposed algorithm significantly reduces processing time compared to Dijkstra's algorithm, particularly in complex topologies, with an order of magnitude improvement. The algorithm successfully adjusts paths in real-time to meet low latency requirements, preventing packet delay from exceeding the established threshold. The end-to-end measurements using the Speedtest client validate the algorithm's performance in differentiating traffic with and without delay requirements. These results demonstrate the efficacy of our approach in achieving ultra-reliable low-latency communication (URLLC) in 5G backhaul networks. [ABSTRACT FROM AUTHOR]

In this paper, we study an edge caching and blockchain enabled space-air-ground integrated networking (SAGIN) network, where a low-earth-orbit (LEO) satellite serves as the content provider, and multiple edge caching enabled unmanned aerial vehicles (UAVs) will cache some contents to provide user equipments (UEs) with satisfactory content access services together with the satellite. Moreover, there's a blockchain system that is deployed on UAVs, to provide the network with trust mechanism without requiring a centralized authority. From the standpoint of the operator, we intend to maximize the long-term averaged economical revenue by providing UEs with satisfactory and secure content access services. To achieve this purpose, we will jointly optimize the content placement of each UAV, content replacement when each UAV is full, the access control of each UE, and the blockchain deployment strategy about each UAV. the concept of queues in Lyapunov optimization is utilized to represent the backlog of edge equipment, ensuring the stability of virtual queues on UAVs and satellites, while satisfying the caching capacity constraints for content caching and blockchain deployment. Due to the tight coupling of optimization in each time slot and the variables within each time slot, our problem, which involves stochastic optimization and binary integer programming, is challenging to solve. To address this issue, we initially employ Lyapunov optimization theory to transform and decouple the problem into individual time-slot optimization problems. Subsequently, we utilize an effective heuristic algorithm called the fireworks algorithm to solve these individual optimization problems. However, the original fireworks algorithm cannot be directly applied to our problem due to its binary characteristics and inter-coupling constraints. Therefore, we have redesigned the explosion and mutation operations to adapt them to our specific problem. Simulation results demonstrate that our proposed algorithm outperforms other baseline algorithms. [ABSTRACT FROM AUTHOR]

Vehicular fog computing extends the fog computing paradigm to conventional vehicular networks. This allows us to support more ubiquitous vehicles, achieve better communication efficiency, and address limitations in conventional vehicular networks in terms of latency, location awareness, and real-time response (typically required in smart traffic control, driving safety applications, entertainment services, and other applications). Such requirements are particularly important in adversarial environments (e.g., urban warfare and battlefields in the Internet of Battlefield Things involving military vehicles). However, there is no one widely accepted definition for vehicular fog computing and use cases. Thus, in this article, we formalize the vehicular fog computing architecture and present a typical use case in vehicular fog computing. Then we discuss several key security and forensic challenges and potential solutions. [ABSTRACT FROM PUBLISHER]

Mobile micro-clouds are promising for enabling performance-critical cloud applications. However, one challenge therein is the dynamics at the network edge. In this paper, we study how to place service instances to cope with these dynamics, where multiple users and service instances coexist in the system. Our goal is to find the optimal placement (configuration) of instances to minimize the average cost over time, leveraging the ability of predicting future cost parameters with known accuracy. We first propose an offline algorithm that solves for the optimal configuration in a specific look-ahead time-window. Then, we propose an online approximation algorithm with polynomial time-complexity to find the placement in real-time whenever an instance arrives. We analytically show that the online algorithm is $O(1)$ -competitive for a broad family of cost functions. Afterwards, the impact of prediction errors is considered and a method for finding the optimal look-ahead window size is proposed, which minimizes an upper bound of the average actual cost. The effectiveness of the proposed approach is evaluated by simulations with both synthetic and real-world (San Francisco taxi) user-mobility traces. The theoretical methodology used in this paper can potentially be applied to a larger class of dynamic resource allocation problems. [ABSTRACT FROM PUBLISHER]

Global routing is a crucial step in the design of Very Large-Scale Integration (VLSI) circuits. However, most of the existing methods are heuristic algorithms, which cannot conjointly optimize the subproblems of global routing, resulting in congestion and overflow. In response to this challenge, an enhanced Deep Reinforcement Learning- (DRL-) based global router has been proposed, which comprises the following effective strategies. First, to avoid the overestimation problem generated by Q -learning, the proposed global router adopts the Double Deep Q -Network (DDQN) model. The DDQN-based global router has better performance in wire length optimization and convergence. Second, to avoid the agent from learning redundant information, an action elimination method is added to the action selection part, which significantly enhances the convergence performance of the training process. Third, to avoid the unfair allocation problem of routing resources in serial training, concurrent training is proposed to enhance the routability. Fourth, to reduce wire length and disperse routing resources, a new reward function is proposed to guide the agent to learn better routing solutions regarding wire length and congestion standard deviation. Experimental results demonstrate that the proposed algorithm outperforms others in several important performance metrics, including wire length, convergence performance, routability, and congestion standard deviation. In conclusion, the proposed enhanced DRL-based global router is a promising approach for solving the global routing problem in VLSI design, which can achieve superior performance compared to the heuristic method and DRL-based global router. [ABSTRACT FROM AUTHOR]

Cloud computing is widely used in various fields, which can provide sufficient computing resources to address users' demands (workflows) quickly and effectively. However, resource failure is inevitable, and a challenge to optimize the workflow scheduling is to consider the fault tolerance. Most of previous algorithms are based on failure prediction and fault-tolerant strategies, which can cause the time delay and waste of resources. In this paper, combining the above two methods through a deep reinforcement learning framework, an adaptive fault-tolerant workflow scheduling framework called RLFTWS is proposed, aiming to minimize the makespan and resource usage rate. In this framework, the fault-tolerant workflow scheduling is formulated as a markov decision process. Resubmission and replication strategy are as two actions. A heuristic algorithm is designed for the task allocation and execution according to the selected fault-tolerant strategy. And, double deep Q network framework (DDQN) is developed to select the fault-tolerant strategy adaptively for each task under the current environment state, which is not only prediction but also learning in the process of interacting with the environment. Simulation results show that the proposed RLFTWS can efficiently balance the makespan and resource usage rate, and achieve fault tolerance. [ABSTRACT FROM AUTHOR]

Resource-reservation-based services have been provided where cloud resources are reserved for tasks within specific time intervals so as fully to exploit the benefits of cloud computing. Such a practice induces an additional decision for task allocation timing and a time index to resource status. Combined with the increasing scale of cloud computing, this increases the complexity of task scheduling in cloud computing. On the other hand, the quality and responsiveness of a task scheduling process should be pursued to meet the desired service features of the market. A task scheduling problem with time-dependent resource availability is formulated, and an heuristic algorithm that derives a high-quality solution to the problem within a very short time is designed to address these challenges. The performance of the algorithm in terms of its optimality and computation efficiency is demonstrated by comparison with the optimal bound found by a commercial optimization solver. [ABSTRACT FROM AUTHOR]

Multicore systems integrated with hardware accelerators provide better performance for executing real-time applications in time-critical fields, such as robots, avionics, and aerospace. The integration of hardware accelerators brings new challenges for system scheduling; the software scheduling problem is extended to a hardware–software co-scheduling problem. Efficient co-scheduling strategy maximizes the benefits of hardware acceleration, which is important for time-critical systems. To solve this problem, we propose a co-scheduling strategy to minimize the system execution time. It combines hardware–software resource allocation and a real-time schedule method. Our scheduling can fit the different parallel in software and hardware (e.g., CPUs and FPGAs). The key component of our strategy is its novel hardware–software resource allocation and a high-performance heuristic scheduling algorithm. In the experiments, we evaluate our approach using both simulated and real parallel applications. The results illustrate that our algorithm obtains efficient solutions within reasonable runtimes compared to the state of the art. [ABSTRACT FROM AUTHOR]

The big data explosion has sparked a strong demand for high-performance data processing. Meanwhile, the rapid development of networked computing systems, coupled with the growth of Divisible-Load Theory (DLT) as an innovative technology with competent scheduling strategies, provides a practical way of conducting parallel processing with big data. Existing studies in the area of DLT usually consider the scheduling problem with regard to fine-grained divisible workloads. However, numerous big data loads nowadays can only be abstracted as coarse-grained workloads, such as large-scale image classification, context-dependent emotional analysis and so on. In view of this, this paper extends DLT from fine-grained to coarse-grained divisible loads by establishing a new multi-installment scheduling model. With this model, a subtle heuristic algorithm was proposed to find a feasible load partitioning scheme that minimizes the makespan of the entire workload. Simulation results show that the proposed algorithm is superior to the up-to-date multi-installment scheduling strategy in terms of achieving a shorter makespan of workloads when dealing with coarse-grained divisible loads. [ABSTRACT FROM AUTHOR]

With the rise of 5G/6G and cloud computing, cluster management has become increasingly popular. Elastic cluster resources allow cloud clients to dynamically scale their resource requirements over time. Existing researches of cluster schedulers focus on improving resource scheduling speed, increasing cluster utilization, compacting the number of active physical machines (PMs) and time satisfaction function (TSF) within a cluster. The TSF is applied as a time to measure the parallel-VM scheduling problem. However, completing execution time (makespan) of task requests is often neglected, which results in inaccurate scheduling and unreasonable total cost computation. The total cost involves PM cost, migrate cost, and balance cost. To solve the problem of inaccurate scheduling of task requests and total cost billing in cluster management, in this paper, we propose an innovative heuristic algorithm, namely, multi-objective two-stage variable neighborhood searching (MO_STVNS), which aims at minimizing total cost while also considering TSF for active PMs. Moreover, we design a Multi-Objective FreeVM (MO-FreeVM) scheduler based on resource prediction, which incorporates a variety of algorithms to work in collaboration to provide near-optimal resource management for cluster. We evaluate MO_STVNS in different real traces and measure it through extensive experiments. The experimental results show that compared with state-of-art methods, the average total cost and average TSF of MO_STVNS are reduced by 33.75% and 60.67% respectively. [ABSTRACT FROM AUTHOR]

Most of the available divisible-load scheduling models assume that all servers in networked systems are idle before workloads arrive and that they can remain available online during workload computation. In fact, this assumption is not always valid. Different servers on networked systems may have heterogenous available times. If we ignore the availability constraints when dividing and distributing workloads among servers, some servers may not be able to start processing their assigned load fractions or deliver them on time. In view of this, we propose a new multi-installment scheduling model based on server availability time constraints. To solve this problem, we design an efficient heuristic algorithm consisting of a repair strategy and a local search strategy, by which an optimal load partitioning scheme is derived. The repair strategy guarantees time constraints, while the local search strategy achieves optimality. We evaluate the performance via rigorous simulation experiments and our results show that the proposed algorithm is suitable for solving large-scale scheduling problems employing heterogeneous servers with arbitrary available times. The proposed algorithm is shown to be superior to the existing algorithm in terms of achieving a shorter makespan of workloads. [ABSTRACT FROM AUTHOR]

It is a hot topic to investigate resource allocation in fog computing. However, currently resource allocation in fog computing mostly supports only fixed resources, that is, the resource requirements of users are satisfied with a fixed amount of resources during the usage time, which may result in low utility of resource providers and even cause a waste of resources. Therefore, we establish an integer programming model for the time-varying multidimensional resource allocation problem in fog computing to maximize the utility of the fog resource pool. We also design a heuristic algorithm to approximate the solution of the model. We apply a dominant-resource-based strategy for resource allocation to improve resource utilization as well as critical value theory for resource pricing to enhance the utility of the fog resource pool. We also prove that the algorithm satisfies truthful and individual rationality. Finally, we give some numerical examples to demonstrate the performance of the algorithm. Compared with existing studies, our approach can improve resource utilization and maximize the utility of the fog resource pool. [ABSTRACT FROM AUTHOR]

Distributed computing, e.g., cluster and cloud computing, has been applied in almost all areas for data processing, while high resource efficiency and user satisfaction are still the ambition of distributed computing. Task scheduling is indispensable for achieving the goal. As the task scheduling problem is NP-hard, heuristics and meta-heuristics are frequently applied. Every method has its own advantages and limitations. Thus, in this paper, we designed a hybrid heuristic task scheduling problem by exploiting the high global search ability of the Genetic Algorithm (GA) and the fast convergence of Particle Swarm Optimization (PSO). Different from existing hybrid heuristic approaches that simply sequentially perform two or more algorithms, the PGA applies the evolutionary method of a GA and integrates self- and social cognitions into the evolution. We conduct extensive simulated environments for the performance evaluation, where simulation parameters are set referring to some recent related works. Experimental results show that the PGA has 27.9–65.4% and 33.8–69.6% better performance than several recent works, on average, in user satisfaction and resource efficiency, respectively. [ABSTRACT FROM AUTHOR]

In services such as metaverse, which should provide a constant quality of service (QoS) regardless of the user's physical location, the end-to-end (E2E) latency must be fairly distributed over any flow in the network. To this end, we propose a reinforcement learning (RL)-based scheduler for minimizing the maximum network E2E latency. The RL model used the double deep Q-network (DDQN) with the prioritized experience replay (PER). In order to see the performance change according to the type of RL agent, we implemented a single-agent environment where the controller is an agent and a multi-agent environment where each node is an agent. Since the agents were unable to identify E2E latencies in the multi-agent environment, the state and reward were formulated using the estimated E2E latencies. To precisely evaluate the RL-based scheduler, we set out benchmark algorithms to compare with which a network-arrival-time-based heuristic algorithm (NAT-HA) and a maximum-estimated-delay-based heuristic algorithm (MED-HA). The RL-based scheduler, first-in-first-out (FIFO), round-robin (RR), NAT-HA, and MED-HA were compared through large-scale simulations on four network topologies. The simulation results in fixed-packet generation scenarios showed that our proposal, the RL-based scheduler, achieved the minimization of maximum E2E latency in all the topologies. In other scenarios with random flow generation, the RL-based scheduler and MED-HA showed the lowest maximum E2E latency for all topologies. Depending on the topology, the maximum E2E latency of NAT-HA was equal to or larger than that of the RL-based scheduler. In terms of fairness, the RL-based scheduler showed a higher level of fairness than that of FIFO and RR. NAT-HA had similar or lower fairness than the RL-based scheduler depending on the topology, and MED-HA had the same level of fairness as the RL-based scheduler. [ABSTRACT FROM AUTHOR]

Mobile crowdsensing (MCS) has been an effective sensing paradigm by exploiting the pervasive sensor-rich mobile devices for sensor data collection. Online task assignment is an important issue for mobile crowdsensing since tasks typically arrive dynamically and need to be handled in an online manner. In this paper, we study online task assignment for maximizing the total profit of the MCS platform while satisfying the time window requirement of each task. We first describe the crowdsensing model and then study the online task assignment in the following two different scenarios: (1) user-offline-arriving scenario, where all users are fully available throughout the whole sensing period and their movements are fully planned by the platform; (2) user-online-arriving scenario, where users arrive and depart dynamically and each user has a specific participatory time window for task executions. For the former scenario, we propose a benchmark algorithm and also an online heuristic algorithm. The benchmark algorithm tries to provide a best-case performance by assuming all future task arrival information is known in advance. The online algorithm adopts bipartite-matching-based strategy for task assignment and further performs minimal detour based data offloading for reducing the data upload cost, whenever possible. For the latter scenario, we propose an effective online algorithm, which adopts a maximum-profit-first strategy for task assignment and also minimal detour based data offloading for reduction of data upload cost whenever applicable. For all the proposed algorithms, we present their detailed design and deduce their time complexities. Extensive simulations are conducted and the results demonstrate that our proposed algorithms can largely increase the total profit of the platform as compared with existing work. [ABSTRACT FROM AUTHOR]

Network on chip (NoC) is a promising solution to the challenge of multi-core System-on-Chip (SoC) communication design. Application mapping is the first and most important step in the NoC synthesis flow, which determines most of the NoC design performance. NoC mapping has been confirmed as an NP-hard (Non-Polynomial hard) problem, which could not be solved in polynomial time. Various heuristic mapping algorithms have been applied to the mapping problem. However, the heuristic algorithm easily falls into a local optimal solution which causes performance loss. Additionally, regular topologies of NoC, such as the ring, torus, etc., may generate symmetric solutions in the NoC mapping process, which increase the performance loss. Machine learning involves data-driven methods to analyze trends, find relationships, and develop models to predict things based on datasets. In this paper, an NoC machine learning mapping algorithm is proposed to solve a mapping problem. A Low-complexity and no symmetry NoC mapping dataset is defined, and a data augmentation approach is proposed to build dataset. With the dataset defined, a multi-label machine learning is established. The simulation results have confirmed that the machine learning mapping algorithm is proposed have at least 99.6% model accuracy and an average of 96.3% mapping accuracy. [ABSTRACT FROM AUTHOR]

With the continuous renewal and rise of various flight equipment, this article designs a method of water data collection, which is realized through the coordination of an unmanned surface vehicle (USV) carrying unmanned aerial vehicles (UAVs, commonly called drones). In reality, multiple UAVs take-off and landing sites, energy consumption, and other complex issues closely related to USV recovery, UAVs must be considered. If mixed integer linear programming (MILP) is used directly, it is difficult to get satisfactory results in an acceptable time range. Therefore, a heuristic algorithm is proposed to solve the problem of data collection by these devices, which can not only quickly solve the large-scale collaborative optimization problem, but also rationally utilize the total energy consumption of the equipment. The effectiveness of the proposed algorithm is verified and analyzed by experimenting a different number of monitoring nodes, different number of UAVs and different task time. It can not only shorten the cycle of data acquisition task, but also reduce the waiting time of the UAV and USV. [ABSTRACT FROM AUTHOR]

At present, some studies have combined federated learning with blockchain, so that participants can conduct federated learning tasks under decentralized conditions, sharing and aggregating model parameters. However, these schemes do not take into account the trusted supervision of federated learning and the case of malicious node attacks. This paper introduces the concept of a trusted computing sandbox to solve this problem. A federated learning multi-task scheduling mechanism based on a trusted computing sandbox is designed and a decentralized trusted computing sandbox composed of computing resources provided by each participant is constructed as a state channel. The training process of the model is carried out in the channel and the malicious behavior is supervised by the smart contract, ensuring the data privacy of the participant node and the reliability of the calculation during the training process. In addition, considering the resource heterogeneity of participant nodes, the deep reinforcement learning method was used in this paper to solve the resource scheduling optimization problem in the process of constructing the state channel. The proposed algorithm aims to minimize the completion time of the system and improve the efficiency of the system while meeting the requirements of tasks on service quality as much as possible. Experimental results show that the proposed algorithm has better performance than the traditional heuristic algorithm and meta-heuristic algorithm. [ABSTRACT FROM AUTHOR]

As a novel network architecture, network function virtualization greatly improves the flexibility of service deployment but also increases the complexity of network function virtualization resource allocation (NFV-RA). Many scholars have studied the above problems and put forward corresponding schemes. These schemes are often individually designed and are difficult to compare. A general and efficient simulation platform for the NFV-RA problem is conducive to integration, comparison and analysis of these schemes and speeds up research progress. This paper presents a general simulation platform SFCSim for NFV-RA. SFCSim adopts the discrete-time event scheduling engine, which can support the simulation of static and dynamic deployment of service function chain, service migration, mobility management and other scenarios. Finally, a load-balancing shortest path and three heuristic embedding algorithms are implemented in the platform for the service function chain embedding problem can be used as the benchmark algorithm, and SFCSim is fully compared with the Alevin to verify the performance of the platform [ABSTRACT FROM AUTHOR]

One of the key issues with large distributed systems, such as IoT platforms, is gaining timely access to data objects. As a result, decreasing the operation time of reading and writing data in distributed communication systems become essential demands for asymmetric system. A common method is to replicate the data objects across multiple servers. Replica placement, which can be performed statically or dynamically, is critical to the effectiveness of distributed systems in general. Replication and placing them on the best available data servers in an optimal manner is an NP-complete optimization problem. As a result, several heuristic strategies for replica placement in distributed systems have been presented. The primary goals of this research are to reduce the cost of data access time, reduce the number of replicas, and increase the reliability of the algorithms for placing replicas. In this paper, a discretized heuristic algorithm with artificial individuals and a hybrid imitation method were developed. In the proposed method, particle and gray-wolf-based individuals use a local memory and velocity to search for optimal solutions. The proposed method includes symmetry in both local and global searches. Another contribution of this research is the development of the proposed optimization algorithm for solving the data object replication problem in distributed systems. Regarding the results of simulations on the standard benchmark, the suggested method gives a 35% reduction in data access time with about six replicates. Furthermore, the standard deviation among the results obtained by the proposed method is about 0.015 which is lower than the other methods in the same experiments; hence, the method is more stable than the previous methods during different executions. [ABSTRACT FROM AUTHOR]

Fog computing is an emerging paradigm that supplies storage, computation, and networking resources between traditional cloud data centers and end devices. This article focuses on the resource provisioning problem in collaborative fog computing for multiple delay‐sensitive users. Our goal is to implement a resource provisioning strategy for network operators to minimize the total monetary cost by considering the deadline and capacity constraints. Two scenarios are considered: unlimited‐processor fog nodes (UPFN) and limited‐processor fog nodes (LPFN). In either scenario, we prove that the resource provisioning problem is NP‐hard. First, we consider the UPFN scenario that the processors of fog nodes are unlimited and users' requests can be ideally processed in parallel. Two algorithms are proposed which greedily delete fog nodes based on the local or global collaborative influences until there is no feasible provisioning to guarantee the deadline of users. Then we extend the resource provisioning problem to a more realistic and complicated scenario LPFN in which the scheduling delay cannot be ignored. Two types of tasks are considered. One is the arbitrarily divided tasks, and a near‐optimal solution bounded by 83OPT+ϵ28mα has been found. m is the number of fog nodes, and α is the upper bound on the Lipschitz constant of the delay function. Another one is the application‐driven tasks, and we propose a heuristic algorithm. Extensive experiments validate the efficiency of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Communication infrastructure is damaged by disasters and it is difficult to support communication services in affected areas. UAVs play an important role in the emergency communication system. Due to the limited airborne energy of a UAV, it is a critical technical issue to effiectively design flight routes to complete rescue missions. We fully consider the distribution of the rescue area, the type of mission, and the flight characteristics of the UAV. Firstly, according to the distribution of the crowd, the PSO algorithm is used to cluster the target-POI of the task area, and the neural collaborative filtering algorithm is used to prioritize the target-POI. Then we also design a Trans-UTPA algorithm. Based on MAPPO 's policy network and value function, we introduce transformermodel tomake Trans-UTPA's policy learning have no action space limitation and can be multi-task parallel, which improves the efficiency and generalization of sample processing. In a three-dimensional space, the UAV selects the emergency task to be performed (data acquisition and networking communication) based on strategic learning of state information (location information, energy consumption information, etc.) and action information (horizontal flight, ascent, and descent), and then designs the UAV flight path based on the maximization of the global value function. The experimental results show that the performance of the Trans-UTPA algorithm is further improved compared with the USCTP algorithm in terms of the success rate of each UAV reaching the target position, the number of collisions, and the average reward of the algorithm. Among them, the average reward of the algorithm exceeds the USCTP algorithm by 13%, and the number of collisions is reduced by 60%. Compared with the heuristic algorithm, it can cover more target-POIs, and has less energy consumption than the heuristic algorithm. [ABSTRACT FROM AUTHOR]

Multi-server jobs are imperative in modern cloud computing systems. A noteworthy feature of multi-server jobs is that, they usually request multiple computing devices simultaneously for their execution. How to schedule multi-server jobs online with a high system efficiency is a topic of great concern. First, the scheduling decisions have to satisfy the service locality constraints. Second, the scheduling decisions needs to be made online without the knowledge of future job arrivals. Third, and most importantly, the actual service rate experienced by a job is usually in fluctuation because of the dynamic voltage and frequency scaling (DVFS) and power oversubscription techniques when multiple types of jobs co-locate. A majority of online algorithms with theoretical performance guarantees are proposed. However, most of them require the processing speeds to be knowable, thereby the job completion times can be exactly calculated. To present a theoretically guaranteed online scheduling algorithm for multi-server jobs without knowing actual processing speeds apriori, in this article, we propose Esdp (Efficient Sampling-based Dynamic Programming), which learns the distribution of the fluctuated processing speeds over time and simultaneously seeks to maximize the cumulative overall utility. The cumulative overall utility is formulated as the sum of the utilities of successfully serving each multi-server job minus the penalty on the operating, maintaining, and energy cost. Esdp is proved to have a polynomial complexity and a logarithmic regret, which is a State-of-the-Art result. We also validate it with extensive simulations and the results show that the proposed algorithm outperforms several benchmark policies with improvements by up to 73%, 36%, and 28%, respectively. [ABSTRACT FROM AUTHOR]

Recommender systems are technology-driven marketing solutions for businesses that analyze user behavior data. However, collaborative data sharing between enterprises is often prohibited by privacy protection regulations, leading to insufficient data for graph neural networks (GNNs) training. Fortunately, federated learning (FL), a collaborative training framework without exposing source data, can be applied congruently. Nevertheless, most of FL-based GNN model training methods adopt federated averaging, which performs poorly on highly heterogeneous graph data. To solve this problem, a FL-based GNN Model Training framework for cross-enterprise recommendation, named FL-GMT, is proposed. Specifically, a GNN-based recommendation model is deployed as the local training model. Then, considering the performance inequity caused by uneven sample quality, a loss-based federated aggregation algorithm is designed, effectively improving the performance of disadvantaged participants. To improve the system stability at the end of the aggregation, a dynamic update method of loss attention is designed. Extensive experiments on benchmark datasets demonstrate that FL-GMT outperforms baselines in terms of system fairness, stability, and accuracy. [ABSTRACT FROM AUTHOR]

Wireless Rechargeable Sensor Networks based on wireless energy transmission successfully solve the problem of node death caused by energy shortage in traditional wireless sensor networks. Existing studies on joint energy replenishment and data collection have planned charging path first and then perform data collection. This approach does not effectively extend network life and improve network performance in data collection. In this paper, we jointly consider the impact of energy replenishment and data collection on network performance and use the Least Squares Support Vector Machine based regression prediction with dynamically changing energy consumption rate and data generation rate of sensor nodes. To solve the above problem, we propose a multi-objective path planning model for joint energy replenishment and data collection with the optimization objectives of maximizing the remaining lifetime of sensor nodes, maximizing the data collection of MC, and minimizing the amount of data loss. The conventional exact algorithm is difficult to solve the path planning problem, so heuristic algorithms have gradually become the main algorithm to solve the problem. Based on discrete fireworks algorithm and co-evolutionary algorithm, we present a grid-based multi-objective cooperation fireworks algorithm. Simulation results show that the proposed algorithm performs better in convergence and diversity. In terms of the average remaining lifetime of sensor nodes, the proposed algorithm is 0.43%, 0.52%, 1.97%, and 0.81% higher than MPACO, MODFA, NSGA-II, and SPEA-II, respectively. Similarly, the target value of solutions in data collection increased by 1.87%, 1.22%, 4.49%, and 2.10%, respectively. [ABSTRACT FROM AUTHOR]

The Cloud Radio Access Network (C-RAN) with centralized processing features achieves efficient and unified resource management to meet the quality of service (QoS) requirements, while results in an increment of energy consumption. To reach a tradeoff between energy efficiency and QoS, jointly considering baseband unit (BBU) computing resource, remote radio head (RRH) power, and fronthaul (FH) link capacity optimization for delay-aware traffic is an NP-hard problem. In this paper, we propose a system energy efficiency optimization model jointing multiple resources allocation for C-RAN downlink transmission. The end-to-end delay (De) in the proposed model is formulated by the established user data queue model, which satisfies the strict Lyapunov stability. Then, based on defining an improved Drift-Plus-Penalty function F DPP to transform the proposed original problem into two sub-problems which are BBU service rate allocation and RRH power control problems. The optimal BBU service rate and RRH transmission power of a single slot are obtained through solving a linear equation and applying a convolution neural network (CNN), respectively. Further, we propose an iterative-based optimization algorithm to achieve the optimal resource allocation for each slot. The simulation results show that the proposed optimization algorithm effectively reaches the balance between energy efficiency and QoS, and achieves better energy efficiency compared with the decomposition allocation method based on heuristic algorithm and BBU scheduling based on first-fit-decreasing (FFD) algorithm with lower computational complexity. [ABSTRACT FROM AUTHOR]

Given the rapid growth of user-generated videos, internet traffic has been heavily dominated by online video streaming. Caching videos on edge servers in close proximity to users has been an effective approach to reduce the backbone traffic and the request response time, as well as to improve the video quality on the user side. Video popularity, however, can be highly dynamic over time. The cost of cache replacement at edge servers, particularly that related to service interruption during replacement, is not yet well understood. This paper presents a novel lightweight video caching algorithm for edge servers, seeking to optimize the hit rate with real-time decisions and minimized cost. Inspired by recent advances in deep Q-learning, our DQN-based online video caching (DQN-OVC) makes effective use of the rich and readily available information from users and networks. We decompose the Q-value function as a product of the video value function and the action function, which significantly reduces the state space. We instantiate the action function for cost-aware caching decisions with low complexity so that the cached videos can be updated continuously and instantly with dynamic video popularity. We used video traces from Tencent, one of the largest online video providers in China, to evaluate the performance of our DQN-OVC and to compare it with state-of-the-art solutions. The results demonstrate that DQN-OVC significantly outperforms the baseline algorithms in the edge caching context. [ABSTRACT FROM AUTHOR]

Ship path planning plays an important role in the intelligent decision-making system which can provide important navigation information for ship and coordinate with other ships via wireless networks. However, existing methods still suffer from slow path planning and low security problems. In this paper, we propose a second-order ship path planning model, which consists of two main steps, i.e., first-order static global path planning and second-order dynamic local path planning. Specifically, we first create a raster map using ArcGIS. Second, the global path planning is performed on the raster map based on the Dyna-Sarsa(λ ) model, which integrates the eligibility trace and the Dyna framework on the Sarsa algorithm. Particularly, the eligibility trace has a short-term memory for the trajectory, which can improve the convergence speed of the model. Meanwhile, the Dyna framework obtains simulation experience through simulation training, which can further improve the convergence speed of the model. Then, the improved ship trajectory prediction model based on stacked bidirectional gated recurrent unit is used to identify the risk of ship collision and switch the path planning from the first order to the second order. Finally, the second-order dynamic local path planning is presented based on the FCC-A* algorithm, where the cost function of the traditional path planning A* algorithm is rewritten using the fuzzy collision cost membership function (fuzzy collision cost, FCC) to reduce the collision risk of ships. The proposed model is evaluated on the Baltic Sea geographic information and ship trajectory datasets. The experimental results show that the eligibility trace and the Dyna learning framework in the proposed model can effectively improve the planning efficiency of the ship's global path planning, and the collision risk membership function can effectively reduce the number of collisions in A* local path planning and thus improve the navigation safety of encountering ships. [ABSTRACT FROM AUTHOR]

Multi-cloud computing is becoming a promising paradigm to provide abundant computation resources for Internet-of-Things (IoT) devices. For a multi-device multi-cloud network, the real-time computing requirements, frequently varied wireless channel gains and changeable network scale, make the system more dynamic. It is critical to satisfy the dynamic nature of network with different constraints of IoT devices in multi-cloud environment. In this paper, we establish a continuous-discrete hybrid decision offloading model, each device should learn to make coordinated actions, including cloud server selection, offloading ratio and local computation capacity. Therefore, both continuous-discrete hybrid decision and coordination among IoT devices are challenging. To this end, we first develop a probabilistic method to relax the discrete action (e.g. cloud server selection) to a continuous set. Then, by leveraging a centralized training and distributed execution strategy, we design a cooperative multi-agent deep reinforcement learning (CMADRL) based framework to minimize the total system cost in terms of the energy consumption of IoT device and the renting charge of cloud servers. Each IoT device acts as an agent, which not only learns efficient decentralized policies, but also relieves IoT devices' computing pressure. Experimental results demonstrate that the proposed CMADRL could efficiently learn dynamic offloading polices at each IoT device, and significantly outperform the four state-of-the-art DRL based agents and two heuristic algorithms with lower system cost. [ABSTRACT FROM AUTHOR]

Dynamic off-chain routing in payment channel network (PCN)-based Internet of Things (IoT) is attracting increasing research attention. However, there are two major issues in dynamic routing in PCN-based IoT with resource-limited devices. The first issue is how to achieve high long-term transaction efficiency in PCN with dynamic channel capacities. The second issue is how to achieve a lightweight routing algorithm deployed on IoT devices while achieving high transaction efficiency, i.e., successful payment amount and success ratio. Therefore, in this paper, we propose a compact deep reinforcement learning (DRL) algorithm to learn the joint dynamic and lightweight routing policy for maximizing long-term transaction efficiency. To obtain optimal performance in dynamic routing problems for off-chain systems, a proximal policy optimization algorithm is employed to create an actor–critic learning structure for training the teacher DRL model. To obtain a compact and efficient student DRL model, an adaptive pruning technique is utilized for pruning unnecessary parameters of networks in the teacher model adaptively without affecting its learning ability. Furthermore, knowledge distillation is leveraged to improve the performance of the student network. Thus, a compact and efficient student DRL model can be developed and implemented to maximize the long-term transaction efficiency in off-chain systems on resource-limited IoT devices. The simulation results demonstrate that the proposed DRL algorithm outperforms the other baseline algorithms in PCN transaction efficiency while requiring only 10% of the computation and storage resources compared with that of the original teacher model. [ABSTRACT FROM AUTHOR]

Nowadays, the mobile communication networks have become a consistent part of our everyday life by transforming huge amount of data through communicating devices, that leads to new challenges. According to the Cisco Networking Index, more than 29.3 billion networked devices will be connected to the network during the year 2023. It is obvious that the existing infrastructures in current networks will not be able to support all the generated data due to the bandwidth limits, processing and transmission overhead. To cope with these issues, future mobile communication networks must achieve high requirements to reduce the amount of transferred data, decrease latency and computation costs. One of the essential challenging tasks in this subject area is the optimal self-organized service placement. In this paper a heuristic-based algorithm for service placement in future networks was presented. This algorithm achieves the ideal placement of services replicas by monitoring the load within the server and its neighborhood, choosing the node that contributes with the highest received load, and finally replicating or migrating the service to it based on specific criteria, so that the distance of requests coming from clients becomes as small as possible because of placing services within nearby locations. It was proved that our proposed algorithm achieves an improved performance by meeting the services within a shorter time, a smaller bandwidth, and thus a lower communication cost. It was compared with the traditional client-server approach and the random placement algorithm. Experimental results showed that the heuristic algorithm outperforms other approaches and meets the optimal performance with different network sizes and varying load scenarios. [ABSTRACT FROM AUTHOR]

To solve the shortcomings of wireless sensor networks (WSNs) in data collection in a wide range, long distance, and other complex environments, such as high networking cost, short network life cycle, and difficult data collection, a data collection strategy based on the unmanned aerial vehicle (UAV) cluster collaborative networking is proposed. First, the node structure and deployment application of WSNs are analyzed, and the architecture of UAV collaborative data collection is designed. Second, the related models of communication energy consumption between WSNs’ network and UAV cluster, UAV cluster task allocation, and path planning are established successively. Then, a simple but efficient task planning strategy considering UAV forward and return distances is proposed. Finally, for the problem of model solving, the solution strategy of the heuristic swarm intelligence algorithm is proposed. The simulation results verify that the strategy reduces the overall network energy consumption by 42.16% and the total range of UAV by 9.7% and realizes the relative minimization of WSNs energy consumption and UAV flight cost on the premise of ensuring the full coverage of WSNs’ nodes. [ABSTRACT FROM AUTHOR]

Large-scale Internet applications running on data centers are typically instantiated as a set of containers. Assigning a container to its affinity machine can reduce communication and transport costs while assigning it to the anti-affinity machine may affect the proper operation of the container. Existing container scheduling methods cannot accommodate these two types of requirements. In order to reduce the operation and maintenance cost of data centers, this article focuses on the container instance allocation problem in heterogeneous server cluster, and proposes a global cost-aware scheduling algorithm (GCCS) to solve it. The purpose is to minimize the total power consumption of the cluster from a global perspective, while trying to meet the affinity/anti-affinity requirements of applications. We study the number of containers per server selected by the application, model it as an integer linear program (ILP), and then propose a heuristic search algorithm to repair the relaxation solution of the ILP into a suboptimal feasible solution. In particular, we use Bayesian optimizer to perform a number of automated development and exploration processes for the selection of the cost coefficient. The experiments are carried out with the best cost coefficient recommended by Bayesian optimizer. Finally, the results demonstrate that GCCS can significantly reduce the total power consumption of the cluster, while maintaining a high affinity satisfaction ratio. [ABSTRACT FROM AUTHOR]

In recent years, the increasing use of the Internet of Things (IoT) has generated excessive amounts of data. It is difficult to manage and control the volume of data used in cloud computing, and since cloud computing has problems with latency, lack of mobility, and location knowledge, it is not suitable for IoT applications such as healthcare or vehicle systems. To overcome these problems, fog computing (FC) has been used; it consists of a set of fog devices (FDs) with heterogeneous and distributed resources that are located between the user layer and the cloud on the edge of the network. An application in FC is divided into several modules. The allocation of processing elements (PEs) to modules is a scheduling problem. In this paper, some heuristic and meta-heuristic algorithms are analyzed, and a Hyper-Heuristic Scheduling (HHS) algorithm is presented to find the best allocation with respect to low latency and energy consumption. HHS allocates PEs to modules by low-level heuristics in the training and testing phases of the input workflow. Based on simulation results and comparison of HHS with traditional, heuristic, and meta-heuristic algorithms, the proposed method has improvements in energy consumption, total execution cost, latency, and total execution time. [ABSTRACT FROM AUTHOR]

Network slicing is a promising technique for wireless service providers to support enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (URLLC) services in a shared radio access network (RAN) infrastructure. In this paper, we apply numerology, mini-slot based transmission, and punctured scheduling techniques to support eMBB and URLLC network slices. For efficient allocation of radio resources (e.g., physical resource blocks, transmit power) to the users, we formulate RAN slicing problem as a multi-timescale problem. To solve this problem and address the dynamics of the traffic, we propose a hierarchical deep learning framework. Specifically, in each long time slot, the service provider employs a deep reinforcement learning (DRL) algorithm to determine the slice configuration parameters. The eMBB and URLLC schedulers use their own attention-based deep neural network (DNN) algorithm to allocate radio resources to their corresponding users in each short and mini time slot, respectively. Simulation results show that the proposed framework can achieve a higher aggregate throughput and a higher service level agreement (SLA) satisfaction ratio compared to some other RAN slicing approaches, including the resource proportional placement algorithm, decomposition and relaxation based resource allocation algorithm, and distributed bandwidth optimization algorithm. [ABSTRACT FROM AUTHOR]

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 in the degrees of freedom in network management. In this paper, we address two practical issues for an over-loaded LEO-terrestrial system. The first challenge is how to efficiently schedule resources to serve a massive number of connected users, such that more data and users can be delivered/served. The second challenge is how to make the algorithmic solution more resilient in adapting to dynamic wireless environments. We first propose an iterative suboptimal algorithm to provide an offline benchmark. To adapt to unforeseen variations, we propose an enhanced meta-critic learning algorithm (EMCL), where a hybrid neural network for parameterization and the Wolpertinger policy for action mapping are designed in EMCL. The results demonstrate EMCL’s effectiveness and fast-response capabilities in over-loaded systems and in adapting to dynamic environments compare to previous actor-critic and meta-learning methods. [ABSTRACT FROM AUTHOR]

Utilizing the millimeter-wave (mmWave) frequency is a promising solution to meet fast-growing traffic demand over wireless networks. However, mmWave communications are sensitive to physical obstructions on signal propagation. In this paper, the reconfigurable intelligent surfaces (RISs) are investigated to overcome the limitations of mmWave communications. Particularly, an RIS is deployed to reflect the mmWave signals towards vehicular users who experience direct link blockages that may occur due to static or dynamic obstacles. To this end, a risk-averse optimization problem is designed to optimize the Base Station (BS) precoding matrix and the RIS phase shifts under stochastic link blockages. A solution approach is developed in two phases: the BS precoding optimization and the RIS phase shift control phases. In the first phase, a Decomposition and Relaxation-based Precoding Optimization (DRPO) algorithm is developed to obtain the optimal precoding matrix. In the second phase, a learning-based method is introduced to dynamically adjust the direction of reflected signals under channel uncertainty. Extensive simulations are presented to validate the efficacy of the developed algorithms. The obtained results show that the developed algorithms can ensure reliable transmissions to users in non-LoS areas and improve network performance. [ABSTRACT FROM AUTHOR]

The Third Generation Partnership Project has standardized cellular vehicle-to-everything (C-V2X) sidelink Mode 4 to support direct communication between vehicles. In Mode 4, the sensing-based semipersistent scheduling (SPS) scheme enables vehicles to autonomously reserve and select radio resources. In particular, SPS has three processes to realize the resource scheduling, including continuously sensing resources, probabilistically reselecting resources, and periodically reserving resources. However, vehicles randomly select resources from the available resource lists in the resource reselection process, resulting in frequent packet collisions especially when radio resources are insufficient. Unlike the traditional SPS, this paper proposes a multiagent deep reinforcement learning-based SPS (RL-SPS) algorithm to help vehicles select appropriate radio resources with the aim of reducing packet collisions. Furthermore, a multi-head attention mechanism is adopted to improve the training efficiency by helping vehicles selectively pay attention to the observations and actions of neighbouring vehicles. It is worth noting that the RL-SPS algorithm fits the characteristics of Mode 4, which selects resources without requiring any global information. Simulation results show that RL-SPS outperforms other decentralized approaches and demonstrate the scalability and robustness of RL-SPS in a dynamic vehicular network. [ABSTRACT FROM AUTHOR]

The main purpose of the work was examining various methods of decomposition of a network optimization problem of simultaneous routing and bandwidth allocation based on Lagrangian relaxation. The problem studied is an NP-hard mixed-integer nonlinear optimization problem. Multiple formulations of the optimization problem are proposed for the problem decomposition. The decomposition methods used several problem formulations and different choices of the dualized constraints. A simple gradient coordination algorithm, cutting-plane coordination algorithm, and their more sophisticated variants were used to solve dual problems. The performance of the proposed decomposition methods was compared to the commercial solver CPLEX and a heuristic algorithm. [ABSTRACT FROM AUTHOR]

Earth observation resources are becoming increasingly indispensable in disaster relief, damage assessment, and other related domains. Many unpredictable factors, such as changes in observation task requirements, bad weather, and resource malfunctions, may cause the scheduled observation scheme to become infeasible. In these cases, it is crucial to promptly reformulate high-quality observation schemes while exerting minimal negative effects on the previously scheduled tasks. Accordingly, in this study, a bottom-up distributed coordination framework together with an improved contract net is proposed, aiming to facilitate dynamic task replanning for heterogeneous Earth observation resources. This hierarchical framework consists of three levels: 1) neighboring resource coordination; 2) single planning center coordination; and 3) multiple planning center coordination. The observation tasks affected by unpredicted factors are managed along with a bottom-up route from resources to planning centers. This bottom-up distributed coordination framework transfers part of the computing load to various nodes of the observation systems to plan tasks more efficiently and robustly. To support the prompt replanning of multiple tasks to proper Earth observation resources in dynamic environments, we propose a multiround combinatorial allocation (MCA) method. Moreover, a new float interval-based local search algorithm is proposed to quickly obtain a promising replanning scheme. The simulation results demonstrate that the MCA method can achieve a better task completion rate for large-scale tasks with satisfactory time efficiency. In addition, this method can efficiently obtain replanning schemes based on original schemes in dynamic environments. [ABSTRACT FROM AUTHOR]

In Industry 4.0, massive heterogeneous industrial devices generate a great deal of data with different quality of service requirements, and communicate via industrial wireless networks (IWNs). However, the limited time-frequency resources of IWNs cannot well support the high concurrent access of massive industrial devices with strict real-time and reliable communication requirements. To address this problem, a deep reinforcement learning-based dynamic priority multichannel access (DRL-DPMCA) algorithm is proposed in this article. Firstly, according to the time-sensitivity of industrial data, industrial devices are assigned with different priorities, based on which their channel access probabilities are dynamically adjusted. Then, the Markov decision process is utilized to model the dynamic priority multichannel access problem. To cope with the explosion of state space caused by the multichannel access of massive industrial devices with dynamic priorities, DRL is used to establish the mapping from states to actions. Next, the long-term cumulative reward is maximized to obtain an effective policy. Especially, with joint consideration of the access reward and priority reward, a compound reward for multichannel access and dynamic priority is designed. For breaking the time correlation of training data while accelerating the convergence of DRL-DPMCA, an experience replay with experience-weight is proposed to store and sample experiences categorically. Besides, the gated recurrent unit, dueling architecture and step-by-step $\varepsilon$ -greedy method are employed to make states more comprehensive and reduce model oscillation. Extensive experiments show that, compared with slotted-Aloha and deep Q network algorithms, DRL-DPMCA converges quickly, and guarantees the highest channel access probability and the minimum queuing delay for high-priority industrial devices in the context of minimum access conflict and nearly 100% channel utilization. [ABSTRACT FROM AUTHOR]

The Internet of Vehicles (IoV) is undoubtedly at the core of the future of intelligent transportation. It will prevail over the road ecosystem, and it will have a huge impact on our lives throughout the provision of seamless connectivity among diverse transportation means. For the network to operate efficiently, the data needs to be quickly spread throughout the network, which requires low computational and bandwidth overheads. However, the dynamics of vehicular environments due to frequent node mobility poses many challenges to realize efficient data dissemination. This work addresses this type of problem by proposing a novel clustering algorithm at the edge of the network and an efficient message routing approach, which is known as Group’n Route (GnR). Both mechanisms resort to machine learning and graph metrics that reflect the social relationships between the nodes. Our performance evaluation reveals that the clustering algorithm yields stable results with varying road scenarios, which are becoming an advisable approach in the presence of mobile IoV nodes. Also, the designed routing protocol achieves two orders of magnitude smaller overhead and almost double the delivery rate when it is compared to traditional routing protocols, which thereby justify that the combination of our two proposed clustering and routing methods are a plausible alternative to support IoV communications in real-world setups. [ABSTRACT FROM AUTHOR]

Traffic supply-demand mismatching has a severe impact on intelligent transportation systems. Fortunately, order dispatching is a promising option to mitigate the traffic supply-demand imbalance. Along this line, this article proposes the Multi-Driver Multi-Order Dispatching (MDMOD) method to make efficient order dispatching policy and enhance the experience of drivers and passengers. In the proposed MDMOD method, the Dynamic Multi-Objective Reward Learning (DMRL) algorithm is proposed to measure the driver-order-pair value, which illustrates the importance of a driver serving a specific order. A centralized matching algorithm is introduced to match all drivers and orders to maximize all driver-order-pair values. The multi-objective reward in the DMRL algorithm considers both immediate gains (i.e., pick-up distance) and future gains (i.e., the future traffic demand of order destination) to effectively improve the experience of drivers and passengers. Furthermore, by introducing the driver service level into the multi-objective reward, the “outstanding driver better reward” mechanism is realized to promote the ecological development of ride-sharing platforms. Notably, the Temporal-Graph Convolutional Network algorithm is proposed to predict the future traffic demand. Some virtual orders, which generated with the predicted future traffic demand, are dispatched to idle drivers to multiplex the traffic supply fully. A simulator is designed to test the performance of the proposed MDMOD method, experimental results demonstrate that the MDMOD method outperforms the state-of-the-art methods in terms of Average Driver Income and Order Response Rate. [ABSTRACT FROM AUTHOR]