4 results about "Large scale network" patented technology

The application discloses a kind of based on nesting block genetic's super large scale network operation method and system, the method includes: obtaining asset network data, constructs infrastructure operation planning physical mathematical model;With the parent individual representing different complete cycle planning scheme, constraint-aware annual plan exchange crossover is carried out;Asset block and nesting;Block maintenance strategy exchange and hierarchical variation between blocks;Block level linear programming guided adaptive optimization.The system includes: including physical modeling module, annual plan exchange crossover module, block nesting module, sub-block processing module and adaptive optimization module.Through using the application, the calculation bottleneck under the scale of huge assets can be solved, and an efficient and scalable decision support scheme is provided for the fine management of complex infrastructure systems such as roads and bridges.The application can be widely applied in the technical field of infrastructure management.

The invention discloses a super-large scale network security feature library loading method based on remote memory access, which relates to the field of network security, and comprises the following steps: acquiring a network security feature library and network security monitoring equipment; constructing a far-end memory access cluster formed by combining a plurality of computing nodes, and configuring a local memory access module and a far-end memory access module; performing logic division on the network security feature data in the network security feature library to obtain logic fragments and mapping the logic fragments into corresponding computing nodes; acquiring operation monitoring data corresponding to the network security feature library and the network security monitoring equipment; respectively performing access scheduling analysis on the network security monitoring equipment and dynamic expansion analysis on the network security feature library according to the obtained operation monitoring data, and generating dynamic adjustment information; performing self-adaptive adjustment on the access identification process of each computing node according to the obtained dynamic adjustment information; according to the invention, the timeliness and flexibility of the loading process are improved.

The invention discloses a multi-element scene-oriented network unit abnormal flow detection method, which belongs to the technical field of computer networks, and comprises the following steps of: calculating multi-dimensional flow behavior characteristics in a multi-element scene based on super-large-scale network communication metadata in a complex network environment, evaluating the historical behavior fluctuation condition of each network unit, and calculating the abnormal flow of each network unit. The departure degree of current data and historical fluctuation is compared, comprehensive scoring is carried out in combination with the abnormal degree of the multi-dimensional label, and abnormal traffic behavior recommendation is achieved; the system comprises five steps of network flow meta-datamation, multi-element scene division, statistical feature extraction, abnormal index calculation and comprehensive scoring. Based on large-scale network traffic metadata, a plurality of behavior scenes are set, the fluctuation condition of a characteristic curve is calculated according to historical traffic behavior data of a network unit, historical behavior habits of different individuals are observed, a multi-dimensional anomaly label system is constructed, and finally, the traffic anomaly condition of the network unit is comprehensively evaluated. And discovery and early warning of abnormal network behaviors are realized.

The user interface with independent scrolling layers described herein provides improved visibility of the network topology of networks, including for complex and large scale networks. In one example, a computing system outputs, for display at a display device, a user interface including icons arranged in multiple layers. Each of the icons corresponds to a network element of the network elements of the network system, and each of the layers corresponds to a topological layer of the network system. Based at least in part on the indication of the user input, the system modifies the arrangement by performing a geometric translation of a first one of the icons arranged in a first one or more of the layers without performing a geometric translation of a second icon arranged in a second one or more of the layers. The system outputs, for display at a display device, a user interface including the modified representation.