This paper proposes DeepRMSA, a deep reinforcement learning framework for routing, modulation and spectrum assignment (RMSA) in elastic optical networks (EONs). DeepRMSA learns the correct online RMSA policies by parameterizing the policies with deep neural networks (DNNs) that can sense complex EON states. The DNNs are trained with experiences of dynamic lightpath provisioning. We first modify the asynchronous advantage actor-critic algorithm and present an episode-based training mechanism for DeepRMSA, namely, DeepRMSA-EP. DeepRMSA-EP divides the dynamic provisioning process into multiple episodes (each containing the servicing of a fixed number of lightpath requests) and performs training by the end of each episode. The optimization target of DeepRMSA-EP at each step of servicing a request is to maximize the cumulative reward within the rest of the episode. Thus, we obviate the need for estimating the rewards related to unknown future states. To overcome the instability issue in the training of DeepRMSA-EP due to the oscillations of cumulative rewards, we further propose a window-based flexible training mechanism, i.e., DeepRMSA-FLX. DeepRMSA-FLX attempts to smooth out the oscillations by defining the optimization scope at each step as a sliding window, and ensuring that the cumulative rewards always include rewards from a fixed number of requests. Evaluations with the two sample topologies show that DeepRMSA-FLX can effectively stabilize the training while achieving blocking probability reductions of more than 20.3% and 14.3%, when compared with the baselines.

No abstract

No abstract

No abstract

Development of terahertz (THz) sources, detectors, and optical components has been an active area of research across the globe. The interest in THz optoelectronics is driven by the various applications they have enabled, such as ultrawide‐band communication systems, air‐ and space‐borne astronomy, atmospheric monitoring, small‐scale radar, airport security scanners, ultrafast nanodevices, and biomedical imaging and sensing. Here, the aim is to provide a comprehensive review of THz bandpass metamaterials focusing on several areas. First, the design fundamentals and geometrical patterns of THz bandpass metamaterials are summarized. Second, fabrication methods of THz bandpass metamaterials are reviewed, including typical micro‐ and nanofabrication techniques and laser micromachining techniques. More importantly, different engineering methods are reviewed for tuning and modulation of the THz transmission resonance for these metamaterials. Both passive and active modulation methods are included in this discussion; the passive method involves changes in the geometrical pattern of the filter material, and the active method performs in situ modulation of properties by applying an external physical field. Finally, the potential applications and prospects for future research of THz bandpass metamaterials are discussed.