Intelligent spectrum management and control framework based on spectrum knowledge graph

Abstract

The invention provides an intelligent spectrum management and control framework based on a spectrum knowledge graph. The framework comprises a map layer, a device layer and a scene layer. And the graph layer is a driving kernel of the intelligent spectrum management and control framework, namely a multi-domain associated spectrum knowledge graph. And the equipment layer is an execution unit of the intelligent frequency spectrum management and control framework and mainly refers to intelligent frequency equipment for configuring a frequency spectrum knowledge graph. And the scene layer is the application presentation of the intelligent spectrum management and control framework. And the intelligent frequency management center issues a frequency management task to the intelligent frequency equipment in the scene, and the intelligent frequency equipment realizes a given frequency spectrum management and control target and reports information to the intelligent frequency management center at the same time. And the intelligent frequency management center expands and perfects the spectrum knowledge graph according to diversified scenes and tasks. Modeling characterization of the multivariate relation in the spectrum space can be achieved, the intelligent level of spectrum management and control under the complex environment is improved, and the method becomes a new tool in the field of spectrum management and control in the future.

Description

technical field [0001] The invention belongs to the cognitive radio field of wireless communication technology, and specifically includes a spectrum knowledge graph and an intelligent spectrum control framework based on the spectrum knowledge graph. Background technique [0002] The electromagnetic spectrum is a family of electromagnetic waves arranged continuously according to the frequency of electromagnetic waves. It is an ideal medium for wireless information transmission and one of the main activities of human society in the information age and intelligence age. The frequency range of the electromagnetic spectrum is generally considered to be 3Hz to 3000GHz, while the frequency range of electromagnetic waves that humans can currently use is mainly concentrated in the range of 30Hz to 40GHz, and most of them are below 6GHz. The seemingly sufficient electromagnetic spectrum resources are actually important but scarce national strategic resources like water, forests, land,...

AI Technical Summary

Problems solved by technology

The current spectrum modeling and characterization methods are difficult to clarify the multivariate relationships among subjects in the spectrum space and the subjects are deeply influenced by factors and variables, lacking the refinement of systematic spectrum knowledge

[0007] Second, the spectrum control method is highly dependent on human experience, and it is difficult to achieve automated and intelligent spectrum control effects

The traditional spectrum control mode of static allocation relies on manual operation and personnel experience

In the dynamic collaborative intelligent spectrum management and control mode, although spectrum sensing, spectrum prediction, spectrum decision-making and other links have technical solutions for their different optimization goals, the input and output of intelligent algorithms between each link still rely on manual connection and supervision Many operating skills and practical experience are only stored in the brains of the frequency management personnel. The frequency equipment can neither understand the semantics of the data flowing in the spectrum cognitive loop, nor can it combine these skills and experiences on the basis of data calculations to think, and Spectrum sharing without automation

[0008] Third, the efficiency of spectrum control is low, and it is difficult to meet the requirements of precise and real-time spectrum control

Existing spectrum control methods mainly establish statistical models from spectrum data, and mine statistical rules to carry out spectrum prediction and spectrum decision-making. These model-driven methods have inherent contradictions that are difficult to reconcile, such as model complexity, accuracy, and resolvability.

Moreover, for different spectrum control scenarios, due to the lack of systematic spectrum knowledge, the generalization ability of existing models is not good

In addition, for a large number of optimization calculations in spectrum management and control, it is difficult to unify the format of diverse spectrum data, the computing power of spectrum management and control is limited, the results of spectrum prediction and spectrum decision-making are often lagging behind, and the timeliness is poor

Images