About: Link aggregation is a research topic. Over the lifetime, 735 publications have been published within this topic receiving 8061 citations. The topic is also known as: port trunking & link bundling.
TL;DR: A communications network switch as mentioned in this paper is a method and apparatus for balancing the loading of aggregated network links of the trunk, thereby increasing the data transmission rate through the trunk by using a load balancing unit.
Abstract: A communications network switch includes a plurality of network ports for transmitting and receiving packets to and from network nodes via network links, each of the packets having a destination address and a source address, the switch being operative to communicate with at least one trunking network device via at least one trunk formed by a plurality of aggregated network links. The communications network switch provides a method and apparatus for balancing the loading of aggregated network links of the trunk, thereby increasing the data transmission rate through the trunk. The switch includes: a packet buffer for temporarily storing a packet received at a source port of the network ports, the packet having a source address value, and a destination address value indicating a destination node that is communicatively coupled with the switch via a data path including a trunk; a packet routing unit for determining a destination trunked port associated with the packet, the destination trunked port including a subset of the plurality of network ports, the destination trunked port being coupled to the destination node via the data path; and load balancing unit for selecting a destination port associated with the packet from the subset of network ports; whereby transmission loading of the aggregated network links of the trunk is balanced. In varying embodiments, the load balancing unit is operative to select destination ports from the subsets of network ports as a function of source port ID values, source addresses, and destination addresses.
TL;DR: The hybrid WiFi-VLC system is proposed, which outperforms the conventional WiFi for crowded environments in terms of throughput and Web page loading time, and the further improved performance of the aggregated system when considering the blocking duration and the distance between the access point and the user device is demonstrated.
Abstract: Visible light communication (VLC) has wide unlicensed bandwidth, enables communication in radiofrequency-sensitive environments, realizes energy-efficient data transmission, and has the potential to boost the capacity ofwireless access networks through spatial reuse. On the other hand, WiFi provides more coverage than VLC and does not suffer from the likelihood of blockage due to the line-of-sight requirement of VLC. In order to take the advantages of both WiFi and VLC, we propose and implement two heterogeneous systems with Internet access. One is the hybrid WiFi–VLC system, utilizing a unidirectional VLC channel as the downlink and reserving the WiFi backchannel as the uplink. The asymmetric solution resolves the optical uplink challenges and benefits from the full-duplex communication based on VLC. To further enhance the robustness and increase throughput, the other system is presented, in which we aggregate WiFi and VLC in parallel by leveraging the bonding technique in the Linux operating system. We also theoretically prove the superiority of the aggregated system in terms of average system delay. Online experiment results reveal that the hybrid system outperforms the conventional WiFi for crowded environments in terms of throughput and Web page loading time, and also demonstrate the further improved performance of the aggregated system when considering the blocking duration and the distance between the access point and the user device.
TL;DR: In this paper, an aggregation parameter is exchanged between a node and its neighbor to agree on a negotiated parameter and the resource data is then exchanged between them and the contents of the database of each node are updated with resource data of its neighbor.
Abstract: In a hierarchical network, an aggregation parameter is exchanged between a node and its neighbor to agree on a negotiated parameter. A set of physical links between them are aggregated into a logical link according to the negotiated parameter and resource data of the logical link is stored in a database of each node. The resource data is then exchanged between them and the contents of the database of each node are updated with resource data of its neighbor. To optimize the link aggregation, an operating performance of the logical link is evaluated by the node using traffic data from the network, and the negotiated parameter is updated according to the detected operating performance. The updated aggregation parameter of the node is exchanged with its neighbor to agree on a negotiated updated parameter which is used to aggregate the physical links into the logical link.
TL;DR: In this article, an extension of a Link Aggregation Protocol (LAP) over the network allows current Ethernet point-to-point LAPs to operate across a Metropolitan Area Network (MAN).
Abstract: An extension of a Link Aggregation Protocol (LAP) over the network allows current Ethernet point-to-point LAPs to operate across a Metropolitan Area Network (MAN). A maximum disjoint path algorithm allows selection of a plurality of alternative end-to-end physical routes between two data terminals. These physical routes share a minimum number of nodes and physical links. End-to-end logical links are then formed by a plurality of successive physical links between nodes containing protocol compatible devices, the physical links being selected based on their physical characteristics such as bandwidth and delay. Multiple logical links can be provisioned, without dedicating, between any two data terminals over the network. The logical links provide the virtual point-to-point links that the edge LAP devices require. The extension of LAP/s over the network provides increased availability because a network failure can now be propagated to the edge of the network to allow the edge LAP devices to quickly react to the failure.
TL;DR: In this paper, the first and second network devices are associated with a link aggregation group (LAG) and the LAG is deactivated by the first network device in response to detecting the configuration problem.
Abstract: A method includes detecting, by a first network device, a configuration problem at a second network device, where the first and second network devices are associated with a link aggregation group (LAG) coupling the first and second network devices. The method also includes de-activating, by the first network device, one or more links in the LAG in response to detecting the configuration problem. The method further comprises maintaining at least one of the links in the LAG as an active link and allowing traffic to be forwarded on the active link in the LAG.