About this Research Topic
The Artificial Intelligence (AI) and Machine Learning (ML) have attracted increasing research interests and are ubiquitously emerging at different levels within optical communication systems and networks. From physical signal transmission to networking, we have observed that the optical and wireless communication systems are becoming more and more complicated due to increasing data transmission speed, more dynamic and connections and more complicated use cases. With growing desirability for elastic services and software-defined systems & networks, network operators will need novel methods to manage their network operations.
AI and ML have shown promising results for optimization, prediction and identification in systems that exhibit nonlinear, dynamic and complex behaviors. This could offer operational advantages by using AI and ML in a range of applications in optical communication systems and networks. For instance, recently studies have shown ML algorithms can improve the transmission performance by non-linearity impairments compensation, which can potentially benefit different types of optical communications, such as visible-light communications, fibre-optics communication, wireless access, smart home and fibre-wireless converged systems. It has also been reported that ML can achieve better performance for quality-of-transmission estimation and optical performance monitoring compared with traditional optical signal processing. We have also seen promising results of using ML for pro-active virtual topology reconfiguration, efficient resource allocation, and scalable network automation for elastic optical networks.
Using more intelligent strategies for signal processing, system operating, performance monitoring and network optimizing is increasingly seen as successful applications for ML and AI in optics. The purpose of the research topic is to encourage studies and researches on novel applications in optical communication systems and networks.
Research topic include, but are not limited to the following:
• ML-based digital signal processing in the physical layer, such as non-linearity mitigation, signal modulation optimization, and performance improvements;
• ML-assisted signal performance monitoring, quality-of-transmission estimation, modulation identification and intelligent testing and measurement;
• Photonic neural network, and photonic neuromorphic computing;
• ML-based optical sensing, polarization tracking, SNR and OSNR sensing;
• ML in different optical communication systems, including fibre-optics, visible-light communications, wireless access, and fibre-wireless converged systems;
• AI&ML for optical networks, including intelligent operation and management, resource allocation, path configuration, failure management, and emerging service provisioning applications such as service function chaining and network slicing;
• ML/AI for heterogeneous optical networking paradigms, such as elastic optical networks, 5G transport networks, and optical datacentre networks;
• Review and survey articles on the current state of the art of ML applications in optics;
• ML/AI for home network, home monitoring and smart home applications.
AI and ML have shown promising results for optimization, prediction and identification in systems that exhibit nonlinear, dynamic and complex behaviors. This could offer operational advantages by using AI and ML in a range of applications in optical communication systems and networks. For instance, recently studies have shown ML algorithms can improve the transmission performance by non-linearity impairments compensation, which can potentially benefit different types of optical communications, such as visible-light communications, fibre-optics communication, wireless access, smart home and fibre-wireless converged systems. It has also been reported that ML can achieve better performance for quality-of-transmission estimation and optical performance monitoring compared with traditional optical signal processing. We have also seen promising results of using ML for pro-active virtual topology reconfiguration, efficient resource allocation, and scalable network automation for elastic optical networks.
Using more intelligent strategies for signal processing, system operating, performance monitoring and network optimizing is increasingly seen as successful applications for ML and AI in optics. The purpose of the research topic is to encourage studies and researches on novel applications in optical communication systems and networks.
Research topic include, but are not limited to the following:
• ML-based digital signal processing in the physical layer, such as non-linearity mitigation, signal modulation optimization, and performance improvements;
• ML-assisted signal performance monitoring, quality-of-transmission estimation, modulation identification and intelligent testing and measurement;
• Photonic neural network, and photonic neuromorphic computing;
• ML-based optical sensing, polarization tracking, SNR and OSNR sensing;
• ML in different optical communication systems, including fibre-optics, visible-light communications, wireless access, and fibre-wireless converged systems;
• AI&ML for optical networks, including intelligent operation and management, resource allocation, path configuration, failure management, and emerging service provisioning applications such as service function chaining and network slicing;
• ML/AI for heterogeneous optical networking paradigms, such as elastic optical networks, 5G transport networks, and optical datacentre networks;
• Review and survey articles on the current state of the art of ML applications in optics;
• ML/AI for home network, home monitoring and smart home applications.
Keywords: Artificial intelligence, Machine learning, Optical and wireless communication and networking, Optical performance monitoring, Signal processing, Elastic optical networks, Intelligent network operation, AIassisted failure identification
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
