Urban lighting system adjusting method and device based on width learning and storage medium

Abstract

The invention discloses an urban lighting system adjustment method and device based on width learning, and a storage medium. The method comprises the steps: obtaining the traffic flow, the vehicle speed value and the ambient brightness of a road surface below an intelligent street lamp through each sensor arranged on the street lamp, and taking the traffic flow, the vehicle speed value and the ambient brightness as initial data; performing feature extraction and node enhancement on the initial data in BLS width learning, and combining the initial data as a training extension value of the fuzzy neural network; constructing an FNN, optimizing a learning algorithm part of the FNN by applying a PSO in an offline learning stage of the FNN, obtaining an optimal initial solution of the network and obtaining an optimized improved neural network, and inputting a training extension value to train the improved neural network. Intelligent control over the brightness of the street lamps in the urban lighting system is achieved through the urban lighting system adjusting method.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method, device and storage medium for adjusting an urban lighting system based on breadth learning. Background technique [0002] Smart street lights have developed rapidly with infrastructure construction in recent years, but the control algorithms of existing smart street lights cannot fully fulfill the functional concepts in the concept of smart cities, that is, the so-called "smart" has not really landed. Especially in terms of software control systems, at present, urban road lighting control systems still mainly adopt two methods to realize the automation and energy-saving requirements of street lamp control. One is to adopt different street lamp switch control strategies; the other is to choose different street lamp remote control way of communication. [0003] At present, there are three main switch control strategies for street lamps: manual control, timing control a...

AI Technical Summary

Problems solved by technology

However, relying on the perception of single-point luminosity has great limitations. For example, in cloudy weather such as thunderclouds, the external light intensity may fluctuate unstablely. The threshold judgment control method may cause the controller to start frequently and cause the street lights to flicker. Affect the service life of the system and cause a bad social experience; in addition, sensor aging, dust accumulation or miscellaneous occlusion near street lights will also lead to inaccurate control

In addition, the above three mainstream switch control strategies have been unable to meet the smart city's fine control requirements for the urban lighting system, such as the inability to control the lighting system and roads to flexibly adjust to changes in road conditions such as traffic volume and speed in the area

Images