As an important support of next-generation network technologies, edge computing provides crucial support for holographic communication services (HCSs) by offering low latency and high computing power. However, in resource-constrained environments, the deployment of HCSs is significantly affected by the coordinated scheduling of computational and transmission resources, as well as the selection of multi-task processing ratios, which in turn curtails service latency and user experience. For this purpose, this paper proposes an efficient edge network offloading and orchestration framework that jointly optimizes adaptive video processing, multi-task offloading, and resource allocation strategies. Specifically, we model computation offloading and video processing as a stochastic optimization problem to maximize system utility, which is defined as a weighted difference between network satisfaction and user utility. Based on Lyapunov optimization theory, the original long-term optimization problem is decomposed into single time slot subproblem, and further reformulated as a Markov Decision Process (MDP). To effectively solve this problem, we design a Graph attention-driven Computing and Networking Coordination based policy optimization Orchestration algorithm (GCNCO). The multi-dimensional policy joint optimization is achieved by fully sensing the contextual relationship of services and network state distribution. Finally, we compare the proposed algorithm with several benchmark algorithms and validate it using a prototype system. Experimental results demonstrate that GCNCO outperforms existing approaches in terms of convergence speed and performance stability, significantly enhancing system utility and improving the success performance of HCS orchestration.

Natural disasters pose a significant threat to human life. In these extreme conditions, terrestrial networks frequently become incapacitated, hindering the provision of essential communication and computing services required for emergency response efforts. In recent years, the rapid advancement of drone technology, coupled with the maturation of lightweight communication and computing equipment, has led to the emergence of unmanned aerial vehicle (UAV) networks as a crucial asset in disaster rescue missions. These networks provide significant advantages, including rapid response times, flexible deployment capabilities, and heightened resilience to complex terrains, showcasing considerable potential for further development. UAV networks exemplify resource-constrained systems where efficient scheduling of computing resources is vital. Especially in emergency rescue scenarios, this complexity is exacerbated by the diverse range of tasks, varying demands, and stringent real-time requirements. Effectively managing and allocating the computational resources of drones is essential for maximizing their operational efficiency in response to the intricate dynamics of disaster situations. To improve the computational service efficiency of the network, this paper proposes an emergency rescue UAVs network architecture. Additionally, we investigate a joint optimization approach for task planning and SFC scheduling. Current research on SFC scheduling primarily focuses on ground data center networks, with comparatively limited investigation into UAV networks. Fully considering the mobility of computing nodes, as well as the wireless transmission modes within the aerial environment, we establish a joint optimization model for task planning and SFC scheduling aiming at minimizing the total weighted end-to-end delay. Then we design the A3C based algorithm to learn the optimization strategy. Simulation results are presented to demonstrate the superiority of the proposed approach in the aspect of total weighted end to end delay and training time against other benchmark algorithms.

A successful blend of network function virtualization (NFV) and software-defined networking (SDN) can offer flexible and varied network services, given the quick ascent of developing applications propelled by the next-generation 6G network vision. In NFV, the ordered execution of service functions that constitute emerging applications is modeled as service function chaining (SFC) and is no longer limited to traditional network functions. Nevertheless, concurrent demands for joint scheduling of network and computing resources with latency sensitivity in resource allocation frequently accompany these application demands. In this paper, we conduct SFC scheduling as an integer linear programming (ILP) problem to tackle this issue. Secondly, we provide a resource-aware SFC scheduling algorithm that combines VNF and timeslots. In order to increase the acceptance rate of latency-sensitive network services, it aims to optimize resource utilization while strictly adhering to application latency requirements by dynamically sensing the availability of resources under various time slots and, consequently, efficiently and collaboratively scheduling computing and network resources under spatiotemporal states. Experimental results demonstrate that the proposed algorithm not only maximizes resource utilization but also accommodates a larger number of latency-sensitive service requests.

In software defined network/network function virtualization (SDN/NFV)-enabled cloud environment, cloud services can be implemented as service function chains (SFCs), which consist of a series of ordered virtual network functions. However, due to fluctuations of cloud traffic and without knowledge of cloud computing network configuration, designing SFC optimization approach to obtain flexible cloud services in dynamic cloud environment is a pivotal challenge. In this paper, we propose a fault tolerance oriented SFC optimization approach based on deep reinforcement learning. We model fault tolerance oriented SFC elastic optimization problem as a Markov decision process, in which the reward is modeled as a weighted function, including minimizing energy consumption and migration cost, maximizing revenue benefit and load balancing. Then, taking binary integer programming model as constraints of quality of cloud services, we design optimization approaches for single-agent double deep Q-network (SADDQN) and multi-agent DDQN (MADDQN). Among them, MADDQN decentralizes training tasks from control plane to data plane to reduce the probability of single point of failure for the centralized controller. Experimental results show that the designed approaches have better performance. MADDQN can almost reach the upper bound of theoretical solution obtained by assuming a prior knowledge of the dynamics of cloud traffic.

Remote surgery is an emerging medical business derived from information networking technology and plays an increasingly essential role in the medical system. In remote surgery, it is imperative to facilitate cross-regional information transmission and processing by leveraging medical information networks to establish a collaborative service model served by multiple data centers in different regions, enabling collaboration and support for surgery operations. Additionally, the implementation of service function chain scheduling technology is crucial for the efficient allocation of computing resources of data centers. In this paper, we design a novel multi-cloud collaborative medical information network framework. Based on this framework, the service function chain (SFC) scheduling problem is investigated to minimize the total weighted end-to-end delay. To solve the scheduling problem, the original problem is reformulated as a Multiple Markov Decision Process (MMDP). Then, a multiple-state-action deep reinforcement learning (MSA-DRL) algorithm is developed to learn the best scheduling policy. Simulation results are presented to demonstrate the superiority of the proposed approach in the aspect of total weighted end to end delay against other benchmark algorithms.

Cloud computing enables Network Function Virtualization to dynamically provide and deploy network functions (NFs) to meet business-specific requirements. This approach streamlines NFs’ lifecycle management and lowers the cost of Operation Administration and Maintenance. However, these advantages cause Service Function Chain (SFC) failure to grow in both scope and dimensionality, making it difficult to establish a model to locate the failure effectively. In this paper, we propose a complete analysis scheme DTFL (Digital Twin (DT) based for SFC failure localization (FL)) through the following two steps: one is classifying and locating failures, and the other is conducting root cause analysis. We propose transGNN based on the Graph Neural Network and improved graph search model to achieve the classification and location for SFC failures. On this basis, the FNSG-RCA algorithm (failure based graph model) is proposed to analyze failures. We build a prototype based on the cloud platform and experimental results show that this scheme can achieve an accuracy rate of over 98% in fine-grained classification of 49 failure types. In addition, DTFL delivers desirable performance in RCA, approximately 13% more accurate than SOTA, the state-of-the-art approach. DTFL improves both RCA accuracy and model deployment efficiency compared with the non-DT approaches.

Network function virtualization (NFV) is a ground-breaking technology that decouples network functions (NFs) from customized hardware to support more flexible network services and network resource allocation. However, these improvements also lead to an increase in the possibility of service function chain (SFC) failure due to hardware failures, software bugs, or resource contention. This could lead to minor problems or even serious consequences. Unfortunately, the existing failure detection methods have multiple issues, such as small detection range, single detection function, heavy overhead, and low accuracy. Consequently, we propose FullSight, a feasible framework based on deep learning (DL) models that can efficiently integrate both the control plane and programmable data plane for fault detection and classification. This framework obtains the status and indicators of components and network that cause service quality performance degradation through two planes. These indicators are ultimately sent to the knowledge plane for preprocessing, dimensionality reduction, and fault analysis. In addition, we propose two algorithms based on text convolutional neural network (textCNN) and bidirectional encoder representations from transformers (BERT) to classify SFC faults. We implement and evaluate the proposed FullSight prototype extensively on a prototype with thirteen programmable switches and twenty end-hosts. Our experimental results show that FullSight can rapidly and accurately detect and identify eight categories of fine-grained SFC failures, compared with other state-of-the-art methods. Besides, compared with SFC Path Tracer and Pingmesh, our framework can reduce the average bandwidth overhead of the data plane by 57% and 84%, respectively, and achieve detection accuracy of more than 98%.

Considering the fluctuations of network traffic and dynamics of unknown underlying network state, designing a elastic control model with long-term high Quality of Service (QoS) and low network cost has become a pivotal problem in Software Defined Network/Network Functions Virtualization (SDN/ NFV) network. Based on the problem, we design the multiagent Deep Reinforcement Learning based Elasticity Control approach (DRLEC). Considering multi-objective of maximizing revenue benefit and minimizing migration cost, the optimization problem for elasticity control is modeled as a Markov Decision Process (MDP). Then, taking the binary integer programming model as constraints, DRLEC is designed to solve the optimization problem of maximizing long-term profit. Experimental results demonstrate that DRLEC shows better performance than heuristics and single-agent DQN algorithm. Moreover, DRLEC can nearly achieve the upper bound of the theoretical solution, which is obtained by assuming knowing the dynamics of network traffic in advance.

Faced with fluctuating network traffic and unknown underlying network traffic dynamics, developing an effective orchestration model with low network cost is still a critical issue in Network Functions Virtualization (NFV)-enabled networks. Thus we propose a Deep Reinforcement Learning based Quality of Service (QoS)/Quality of Experience (QoE)-Aware Adaptive Online Orchestration (DRL-QOR) approach to adapt to the real- time network variations. We formulate the stochastic resource optimization as a Parameterized Action Markov Decision Process (PAMDP), with QoE and specific QoS requirements as key factors in formulating the reward function, aiming to maximize QoE while satisfying QoS constraints. Then we propose DRL-QOR to solve the Non-deterministic Polynomial hard (NP-hard) problem with consideration of improving the long-term profits, where deep neural network combinatorial optimization theory is extended under the constraints of the binary integer programming model. Extensive experimental results in real USANET topology demonstrate that our proposed DRL-QOR converges fast during the training process. Compared with other benchmarks that only consider the current system performance, it shows good performance in QoE provisioning and QoS requirements maintenance for orchestrating SFCs.

To satisfy the various quality-of-service (QoS) re-quirements with minimum network costs, network functions virtualization (NFV) is proposed as an emerging wireless architecture that migrates network functions from dedicated hardware appliances to software instances running in virtual computing platforms. One crucial issue in NFV is to solve the orchestration of virtualized network functions (VNFs) to reduce costs and to improve the management flexibility of telecommunications service providers (TSPs). Particular, multiple objectives are required to be considered for orchestrating VNFs in order to achieve overall system performance. This can be optimally solved in small scale using integer linear programming (ILP) algorithms with high accuracy but low time efficiency. On the other hand, heuristic algorithms can be applied for solving part of the objectives in NFV resource allocation with high time efficiency but low accuracy. To tackle the above challenges, QMORA, a ${Q}$-learning based multi-objective resource allocation approach, is proposed to solve multi-objective optimization in NFV orchestration (NFVO) efficiently and accurately. Particularly, the approach includes reinforcement learning module and VNFs placement module. Reinforcement learning module is responsible for generating the “best” candidate paths. VNFs placement module is responsible for selecting optimal nodes on the generated candidate paths to host VNFs required for flows. The simulation results in the real ISP topology show that the proposed QMORA can balance the multi-objective including maximizing number of flows admitted to the network, minimizing path stretch, balancing the load among VNF instances and minimizing link occupation rate compared with other heuristic approaches.

Information centric network (ICN) is becoming a prevailing design for future Internet to provide data objects to end customers. One crucial problem in ICN is to design routing and forwarding strategy so that traffic can be transmitted efficiently even with the dynamics of network link. In this paper, we consider content centric network (CCN), which is one of the promising candidate architecture design for ICN. Particularly, we consider the scalable CCN with name mapping system, which improves scalability by using router Identifier as name prefix to forward interests. We address the issue of improving link failure resiliency for CCN by designing a dynamic interest transmission approach. We propose the link failure resilient interest transmission algorithm (LFRIT) to enhance link failure resiliency by considering both network traffic and link status information. Additionally, we propose the advanced design of LFRIT (A-LFRIT), which calculates and updates the forwarding table centrally for link updates to further improve network robustness. Numerous simulations are conducted to evaluate the proposed approach under realistic network topologies with respect to packet loss, latency, and network link utilization. Simulation results demonstrate that the packet loss probability and data retrieval delay of A-LFRIT can reduce to 50% of the basic CCN and multi-repository single path approaches.

Content Centric Networking (CCN) is one of the representative Information Centric Networking (ICN) architectures. In CCN, data objects are accessed instead of end hosts, and each router maintains a large size of routing table consisting of all name prefixes announced by content servers. To improve the scalability of CCN, an alternative name space relating to Router IDentifier (RID) has been proposed for forwarding the interest instead of using the name prefix of data object, and a name mapping system is applied for mapping data objects related names to RID related names. In this paper we propose dynamic interest transmission scheme in CCN with name mapping (DIT-NM), in which interest can be forwarded towards dynamically chosen RID through dynamically chosen interface associated with the RID according to real-time monitoring network status and traffic load information. The performance of the proposed scheme is evaluated using realistic network topologies with respect to latency and network link utilization. We also compare with the basic CCN model and multi-repository single path (MRSP) to highlight the advantages of our scheme. Achieved results demonstrate the effectiveness of the proposed scheme in reducing latency, improving robustness and balancing overall traffic distribution in name-mapping CCN environment.