Load balancing routing algorithm based on extended link states in LEO constellation network

Uneven traffic demand in satellite networks can lead to link congestion and influence network communication quality. To tackle this problem, we propose a state‐aware routing algorithm based on traffic prediction to disperse network traffic. Reducing the onboard processing requirements, the routing algorithm in this paper introduces a software‐defined network to decouple the control plane and data plane of the satellite network. Also, to better sense the trend of network state, the routing algorithm devises a Spatial‐Temporal Attention Fusion Graph Neural Network (STAFGNN) to predict the future network state by capturing the spatial‐temporal correlation of satellite network traffic. In the control plane, the routing algorithm senses the network state by predicting the future satellite traffic and aggregates the real‐time states of neighboring satellites to identify the load level of the zone. The data plane forwards data based on the control information. Based on the routing algorithm in this paper, multipath routing is designed to reduce the probability of link congestion by dispersing each end‐to‐end traffic. The simulation results demonstrate that the routing algorithm in this paper reduces the number of congestion links and balances the load distribution. The proposed algorithm provides an idea to introduce deep learning to solve the load balancing problem in satellite networks.

Single-attribute decision-making is often unable to achieve ideal results in Ad Hoc routing problems. Therefore, a multi-attributes decision-making routing algorithm for Ad Hoc network is proposed in order to achieve better optimization results. Compared with single-attribute decision-making, the main issue of multi-attributes decision-making is the Incommensurability between attributes and the contradiction produced by attributes. To deal with this problem, this paper proposes a reinforcement learning based multi-attributes decision-making routing algorithm for Ad Hoc network. We adopt option-critic framework based on hierarchical reinforcement learning to train agents and take into account the transmission bandwidth, packet loss rate, number of communication nodes, transmission delay. For each decision-making attribute, the combination weighting method is used to calculate the weight of each decision-making attribute, and a decision model based on multiple attributes is established. The mobile node selects the best next hop node to forward the data according to the multi-attributes decision model. The proposed algorithm evaluates various attributes and network conditions of mobile nodes comprehensively. Moreover, it can dynamically adjust the routing strategy in real time according to the load status of each node, and distribute the data in the network evenly. The simulation results show that compared with traditional multi-attribute routing algorithm, the algorithm not only has better convergence, but also finds a better path faster than the traditional multi-attribute algorithm when there is a preference for routing attributes. The proposed algorithm also has excellent performance in delivery ratio and cost, and improves the network performance.

Aiming at the problems of high dynamic topology and limited on-board resources in Low Earth Orbit (LEO) satellite networks leading to poor performance of traditional routing algorithms, this paper combines the centralized control idea of Software-Defined Networking (SDN) with the collective learning ability of the Particle Swarm Optimization (PSO) algorithm to propose an adaptive potential field routing algorithm based on PSO. This algorithm models the network as a dynamic potential field, defines potential energy based on the cumulative congestion degree to guide data packet transmission; adaptively learns and optimizes link cost weights through the PSO mechanism, achieving dynamic evolution of the path evaluation criterion; and adopts a probability-based multi-path forwarding mechanism to achieve load balancing. Simulation results show that compared to traditional algorithms such as Dijkstra and ACO (Ant Colony Optimization), this algorithm significantly improves performance in terms of average end-to-end delay, network throughput, and load balancing, especially suitable for dynamic traffic scenarios.

LEO satellite networks have many advantages, such as global coverage and short latency, which play a crucial role in the future global communications. Under the tide of the Internet of Things, LEO satellite networks, as an effective means of connecting remote regions, will become indispensable pillars in the integrated system of the Internet of Things. In LEO satellite communication systems, routing have always been a big challenge due to the relative motion of satellites. The K shortest route algorithm is a typical one of the routing algorithms that emerged in recent years. By calculating K shortest path routes, an optional route set is formed, and then the best route is determined by the route selection strategy. For the massiveness and suddenness of the IoT terminals, the original K Shortest path algorithm cannot balance the load, resulting in partial link congestion affecting the overall system performance. In this paper, the route selection strategy of K Shortest path is improved by the routing strategy of the algorithm, and the rerouting process is added. Under the Iridium constellation, the packet loss rate, throughput and delay of the shortest path algorithm after the improvement are analyzed. The results show that the improved algorithm can effectively reduce the packet loss rate and improve the link utilization and throughput of the system.

Two quasi-static minimax open shortest path first (OSPF) routing algorithms in networks supporting the Switched Multi-megabit Data Service (SMDS) are presented and compared. In OSPF routing, the network is modeled as a graph and each link is associated with a nonnegative arc weight. A shortest path spanning tree is calculated for each origin to carry both the individually addressed and the group addressed (multicast) traffic. The OSPF routing protocol is adopted as a major part of the default inter-switching system interface (ISSI) routing algorithm for SMDS networks where arc weights are inversely proportional to the aggregate link set capacities. The problem of choosing a set of link set metrics is considered so that the maximum link utilization factor is minimized in an SMDS network. The problem is formulated as a nonlinear mixed integer programming problem.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

For the purpose of saving the resources of wireless sensor networks, it is necessary to fuse the existing data in wireless sensor networks. When using the current method to fuse data in wireless sensor networks, the fusing time is too long to remove the noise signal in wireless sensor networks effectively. In the process of fusing, data packet loss is easy to occur. There are some problems such as low fusion efficiency, poor denoising performance and high packet loss rate. A multi-path data hierarchical fusion method based on routing algorithm is proposed in this paper. The redundant node decision method based on mesh partitioning is combined with the grid algorithm and EECRS protocol to establish a routing protocol based on redundant node elimination, and the redundant data existing in the redundant nodes of the wireless sensor network is removed. Based on the statistical data of the data, the probability density function is deduced and analyzed, and the noise filtering matrix is constructed to optimize the measurement matrix and remove the noise existing in the wireless sensor network. The multi-path scheduling technology is used to synthesize the pheromone table and the data forwarding flow table, and the ant is used to actively monitor the link QOS real-time information in the path finding process to update the pheromone table and the flow table, and calculate the link idle rate according to the update result. According to the calculation result, the data transmission path is selected, and the multi-path data layer fusion is completed. The experimental results show that the proposed method has high fusion efficiency, good denoising performance and low packet loss rate.

The Space-Air-Ground integrated network (SAGIN) is the development trend of the future communication networks, and it can cope with various complex environments and tasks in the future communication environment. When sudden public events and natural disasters occurs, ground communication facilities may be damaged and cannot meet the communication needs in emergency scenarios. The Space-Air-Ground integrated three-dimensional and heterogeneous network enables flexible deployment and rapid networking. In this paper, we study the routing algorithm in a software defined SAGIN to optimize the load balancing in the communication network. First, considering the characteristics of dynamic topology changes in real time, we propose a new Software Defined Network (SDN) model for the SAGIN, which promotes a high network flexibility. Basing on such model, we present a new load balancing dynamic routing algorithm, namely Load Balancing Algorithm Based on Multi-dimensional Resources and Energy (LBMRE-OLSR). The multi-dimensional resources and energy consumption are considered in the new routing algorithm. The simulation experiments show that the proposed algorithm efficiently reduce end-to-end delays and packet loss rate.

In position-based routing algorithms for ad-hoc networks, the nodes use the geographical information to make the routing decisions. Recent research in this field primarily addresses such routing algorithms in two dimensional space (2D). However, in real applications, nodes may be distributed in 3D space. In this paper we extend previous randomized routing algorithms from 2D space to 3D space, and we propose two new position-based routing algorithms that combine randomized AB3D routing algorithms with a deterministic CFace (coordinate face) algorithm. The first algorithm AB3D-CFace(1)-AB3D starts with AB3D routing algorithm until a local minimum is reached. The algorithm then switches to CFace routing using one projected coordinate. IfCFace(l) enters a loop, the algorithm switches back to AB3D. The second algorithm AB3D-CFace(3) starts with AB3D, until a local minimum is reached. The algorithm then permanently switches to CFace routing using three projected coordinates, in order. We evaluate our mechanisms and compare them with the current routing algorithms. The simulation results show the significant improvement in delivery rate over pure AB3D randomized routing (97% compared to 70%) and reduction in path dilation (up to 50%) over pure CFace algorithm.

We study end-to-end delay performance of different routing algorithms in networks with random failures. Specifically, we compare delay performances of differential backlog (DB) and shortest path (SP) routing algorithms and show that DB routing outperforms SP routing in terms of throughput when the network is heavily loaded and/or the failure rate is high while SP routing achieves better delay performance in the low load regime. Then, we investigate delay performance of a hybrid routing algorithm that combines principles of both SP and DB routing algorithms and show that it outperforms both of these routing algorithms. Finally, we demonstrate improvements in delay performance of DB routing through the use of a digital fountain approach which was originally proposed for multicast applications. In addition, our results show that there exists an optimal coding rate where digital fountain based DB routing achieves minimum end-to-end delay. To the best of our knowledge, this is the first work which investigates delay performance of DB routing and its enhanced versions for networks with link failures.

The load balanced coding-aware multipath routing algorithm may have the problems of high load node forwarding routing request message leading to a waste of bandwidth resources during routing discovery and the coding gain only considers the number of coded flows that can’t make the path actual coding gain optimal. To solve these problems, a coding-aware and congestion aware multipath routing algorithm in wireless mesh networks (CACAMA) by proposed in this paper. By introducing two mechanisms of congestion aware based coding-aware routing metrics and congestion aware mechanisms, the CACAMA algorithm has obvious advantages in reducing packet loss rate and improving network throughput. Simulation results show that, compared with LCMR, the performance of CACAMA algorithm has been improved in terms of packet loss rate, network throughput and end to end delay.

Most works about all-optical circuit-switched WDM networks considers a shortest path algorithm for fixed routing, like the Dijkstra’ algorithm. However, recently, two new algorithms, searching for better load balancing and presenting superior performance than Dijkstra´s when submitted to an uniform traffic load, were proposed, the Restricted Routing Technique (RRT) and the Best among the Shortest Routes - (BSR). This work evaluates the performance of these algorithms under a non-uniform traffic load. For each topology studied were observed specific characteristics of the impact of the non-uniform traffic load for each routing algorithm. Overall, performance evaluation results showed that the algorithm BSR achieves for all topologies studied superior performance in terms of blocking probability and fairness.

Load balancing-based hierarchical routing algorithm for wireless multimedia sensor networks

The routing algorithm based on a single routing metric parameter is difficult to meet the Quality of Services (QoS) requirements of multi-source data flows in the software-defined factory heterogeneous network, resulting in link congestion and waste of network resources. To solve the problem, this paper proposes a QoS optimization method for software-defined factory heterogeneous networks based on the double deep Q network (DDQN). First, a QoS optimization architecture is proposed for software-defined factory heterogeneous networks, and the optimization function for network latency and load balancing is established. Then, the DDQN algorithm is used to obtain the optimal paths of multi-source data flows, and the optimal path is uniformly issued by the software-defined network controller. Experiments showed that the proposed algorithm has good convergence and generalizability. Compared with the existing algorithms, it outperforms in network latency, network jitter, and network throughput, improving network load balancing and routing efficiency. This research is able to provide a solution to the QoS optimization and dynamic traffic scheduling in smart heterogeneous networks and provide a technical reference point for realizing customized smart factories.

The performance of satellite networks largely depends on their routing algorithm. Existing routing algorithms for satellite networks usually are not quite adaptive or have the disadvantage of a large consumption in both computation and storage resources. In this paper, we propose a novel routing algorithm based on dynamic clustering for LEO satellite networks. By dynamic forming cluster of the satellite network, the routing algorithm is both adaptive, computational effective and need much less storage space. Simulation results show that our routing algorithm performs better and are more robust when the network topology changes.

In this paper a practical routing algorithm is proposed that increases the network throughput irrespective of the network traffic load. Its effectiveness is based on an efficient cost function which achieves a successful trade-off between the use of the minimum-hop routes and the application of the load-balancing concept. Moreover, it employs the known Trunk Reservation notion according to a probability that increases linearly with the traffic load. This results in an effective compromise of the performance of the algorithm between light and heavy traffic loads. Finally, its simplicity and its suitability for a real-time application render it as an efficient routing algorithm for ATM networks. Copyright © 1999 John Wiley & Sons, Ltd.