Abstract: Embodiments of the present invention relate to an approach for reconfiguring interrelationships between components of virtual computing networks (e.g., a grid computing network, a local area network (LAN), a cloud computing network, etc.). In a typical embodiment, a set of information pertaining to a set of components associated with a virtual computing network is received in a computer memory medium or the like. Based on the set of information, a graphical representation (e.g., hierarchical tree) depicting the set of interrelationships between the set of components is generated. When a failure in the virtual computing network is detected, at least one of the set of interrelationships between the set of components is reconfigured based on the graphical representation and the set of rules to address the failure.
Type:
Application
Filed:
February 28, 2012
Publication date:
August 29, 2013
Applicant:
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventors:
Charles S. Lingafelt, James W. Murray, James T. Swantek, James S. Worley
Abstract: Methods and apparatuses are disclosed for seamlessly combining an access ring aggregation network, e.g., a G.8032 network, and a core network, e.g., a Multi-Protocol Label Switching (MPLS) network. A link status is monitored between an interworking node and at least one peer node in a first network at an interface between the first network and a second network. Connectivity is maintained between the interworking node and the other interworking node(s) via the second network. Communications between the first and second networks are supported via at least one of the interworking nodes. Ring communications are supported among the interworking node, the other interworking node(s), and the peer node(s). End-to-end integration of two disparate networks according to presently disclosed techniques provides network designers and customers with flexibility in designing, operating, and maintaining networks.
Abstract: An Iso-Parallel UPS system may combine the system redundancy, isolation and fault-limiting properties of isolated-redundant systems, with the ability to spread system load evenly across all modules like paralleled systems. This system may have the following features: (1) the critical load can be divided into two or more portions, and each portion may be individually fault tolerant, i.e., any electrical fault on a critical load will affect only the load in that portion—other portions of the critical load can remain connected and operating; (2) the critical load can be shared among all modules within the configuration, and all modules may be equally loaded, or nearly equally loaded—there is no designated redundant unit; and (3) any module can be taken out for maintenance without impacting the critical load.