Constellation diagrams for spectrum anomaly detection in optical networks

Accurate and efficient anomaly detection is a key enabler for the cognitive management of optical networks, but traditional anomaly detection algorithms are computationally complex and do not scale well with the amount of monitoring data. Therefore, this dataset enables research on new optical spectrum anomaly detection schemes that exploit computer vision and deep unsupervised learning to perform optical network monitoring relying only on constellation diagrams of received signals. A scheme implemented over this dataset achieves 100% detection accuracy even without prior knowledge of the anomalies. Furthermore, operation with encoded images of constellation diagrams reduces the runtime by up to 200 times. Further research can focus on the efficiency of the algorithms, as well as exploit new ML algorithms, anomaly identification, etc.

精确高效的异常检测是光学网络认知管理的关键推动力，然而，传统的异常检测算法在计算复杂性方面较高，且难以随着监控数据的量级进行扩展。因此，本数据集旨在促进针对新型光学频谱异常检测方案的研究，这些方案利用计算机视觉与深度无监督学习技术，在仅依赖接收信号星座图的情况下实现对光学网络的监控。在此数据集上实施的一种方案，即便在没有先验异常知识的前提下，也实现了100%的检测精度。此外，对星座图编码图像的处理能够将运行时间降低高达200倍。进一步的研究可以聚焦于算法的效率，以及探索新的机器学习算法、异常识别等。