Intelligent Optical Cable Resource Management Based on ACO-RF Method

With the continuous development of power communication networks, the management and maintenance of optical cable resources, as a critical infrastructure of power communication, have become increasingly complex. To ensure the stability and reliability of the power communication network, the management of optical cable resources is of paramount importance. In this paper, Optical time domain reflectometry (OTDR) technology is employed to obtain the fiber core inspection data, and artificial intelligence techniques are applied to extract features and train models on the fiber core inspection data, outputting key information such as fiber core length, attenuation, junction box location, and others. Experimental results demonstrate that the proposed ant colony optimization of random forests (ACO-RF) algorithm outperforms decision trees(DT), random forest (RF), and K-nearest neighbors (KNN) algorithms in terms of accuracy, specificity, recall, and F1 score. The ACO-RF-based optical cable resource management method proposed in this paper offers significant guidance for future optical cable resource management, and it also provides valuable references for resource management strategies in power grids.