Nowadays, ocean networks gradually become increasingly important for communication among network entities such as maritime and sea-crossing users. However, ocean networks are highly dynamic because the communication links are composed of satellite and microwave links, which could be easily influenced by the environment such as local climate. Thus, network transmission in ocean networks faces great challenges, including low reliability and low efficiency. In this paper, we propose a smart ocean network architecture, where we use Software Defined Network (SDN) to perform unified management of the network, and Segment Routing (SR) to control data forwarding paths. In this way, we can control network flows and optimize network routing among diverse network entities in an ocean network. However, many Quality of Service (QoS) guaranteed applications in ocean networks, such as remote control, require lower delay. To guarantee the performance for such applications, we further propose QoS routing algorithms based on Fuzzy-Lagrange for the smart ocean networks architecture, where the optimization objective is to ensure service quality provided to users. According to experimental results, it is proved that, in comparison with the benchmark algorithms, the Fuzzy-Lagrange (FuzLag) algorithm proposed based on link fuzzification and Lagrangian Relaxation can improve the performance by 23% at most.
Satellite networks, which have wide coverage and high throughput, are more and more important for the Internet. Low earth orbit (LEO) satellites have been more widely used than other orbiting satellites because they have lower unidirectional links (UDL) transmission delay. However, due to the variability and instability of satellite links, leading to relatively higher UDL transmission delay and more link failures for satellite networks. Thus, fast reroute (FRR) schemes, which can bypass the failure links and improve network performance, are badly needed in satellite networks. However, FRR need relatively large computing resources while satellites have limited resources. Thus, traditional routing technologies cannot be directly applied to satellite network due to frequent topology changes and poor computing performance. To meet the challenges, we propose a hybrid FRR schemes for satellite networks that combines the centralized computing with distributed segment routing (SR). With the scheme, satellites with relatively more computing resources can pre-compute the reroute paths, and distribute the routing rules to satellites that have more forwarding resources. We formulate the problem, propose a classification algorithm that can distinguish satellites according to their computing and forwarding resources. Additionally, we also propose a real-time backup path maintenance algorithm in the hybrid rerouting scheme. Finally, we conduct comprehensive simulations to evaluate the performance of the proposed algorithms, and the results show that under extreme conditions, the proposed LFR algorithm is 30.9% better than traditional algorithms in storage resource utilization; and the proposed LFA+ algorithm is 74.3% better than traditional algorithms in update time comparison.
With the development of 5G technology and Internet of Things (IoT), more and more devices are connected through 5G wirelessly. Radio access network (RAN) slicing, as a key feature of 5G, enables a flexible bandwidth resource allocation policy, and facilitates various types of services to operate on different network slices. However, RAN slicing resources is scarce, thus effective management of wireless bandwidth resources in RAN slicing becomes indispensable to improve user satisfaction. Extensive research has investigated into RAN slicing, but they do not take user mobility into consideration. While RAN slicing allocation has a great impact on user experience in mobile 5G scenarios, user mobility poses great challenges to network management and causing unsatisfaction of users. In this paper, we propose a new RAN slicing allocation strategy based on machine learning, to maximize spectrum efficiency while guaranteeing the Service Satisfaction Ratio (SSR) of various slicing services. To further alleviate the SSR fluctuation brought by user mobility, we study into the temporal characteristics of user mobility and preprocess the state sequences using Long Short-Term Memory (LSTM) networks. Finally, these sequences are taken as the input of an Advantage Actor Critic (A2C) reinforcement learning network to develop a RAN slicing allocation policy. We conduct comprehensive simulations, and the results show that the performance of the proposed mechanism outperforms the traditional mechanism in ensuring SSR and enhancing the spectrum efficiency.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)