Reinforcement learning-based adaptive beam alignment in a photodiode-integrated array antenna module.

We successfully demonstrated an intelligent adaptive beam alignment scheme using a reinforcement learning (RL) algorithm integrated with an 8 × 8 photonic array antenna operating in the 40 GHz millimeter wave (MMW) band. In our proposed scheme, the three key elements of RL: state, action, and reward, are represented as the phase values in the photonic array antenna, phase changes with specified steps, and an obtained error vector magnitude (EVM) value, respectively. Furthermore, thanks to the Q-table, the RL agent can effectively choose the most suitable action based on its prior experiences. As a result, the proposed scheme autonomously achieves the best EVM performance by determining the optimal phase. In this Letter, we verify the capability of the proposed scheme in single- and multiple-user scenarios and experimentally demonstrate the performance of beam alignment to the user's location optimized by the RL algorithm. The achieved results always meet the signal quality requirement specified by the 3rd Generation Partnership Project (3GPP) criterion for 64-QAM orthogonal frequency division multiplexing (OFDM).

Reinforcement learning for W-band radio-over-fiber system using a polarization modulator.

Reinforcement learning (RL) is applied to improve the performance of the polarization modulator (PolM)-based W-band radio-over-fiber (RoF) system in this Letter. By controlling the polarization angle of the dual-wavelength laser source in the PolM-based scheme, the RF response can be easily modified and therefore it hugely increases the available bandwidth in the RoF system. In the proposed RL scheme, the state is described as the value of the angle from the polarization controller (PC). We use changing the angle of the polarizer (P) as the actions of the RL agent to optimize the frequency response. The agent also receives a reward from the system and learns from the environment and previous experience. Moreover, the reward is the value of error vector magnitude at each state. Therefore, the proposed scheme of RL is implemented and demonstrated in a multi-channel RoF system, and the results show that an RL agent provides an effective intelligent technique to obtain the best quality of data transmission.

Using a Machine Learning Algorithm Integrated with Data De-Noising Techniques to Optimize the Multipoint Sensor Network.

In this paper, for an intensity wavelength division multiplexing (IWDM)-based multipoint fiber Bragg grating (FBG) sensor network, an effective strain sensing signal measurement method, called a long short-term memory (LSTM) machine learning algorithm, integrated with data de-noising techniques is proposed. These are considered extremely accurate for the prediction of very complex problems. Four ports of an optical coupler with distinct output power ratios of 70%, 60%, 40%, and 30% have been used in the proposed distributed IWDM-based FBG sensor network to connect a number of FBG sensors for strain sensing. In an IWDM-based FBG sensor network, distinct power ratios of coupler ports can contain distinct powers or intensities. However, unstable output power in the sensor system due to random noise, harsh environments, aging of the equipment, or other environmental factors can introduce fluctuations and noise to the spectra of the FBGs, which makes it hard to distinguish the sensing signals of FBGs from the noise signals. As a result, noise reduction and signal processing methods play a significant role in enhancing the capability of strain sensing. Thus, to reduce the noise, to improve the signal-to-noise ratio, and to accurately measure the sensing signal of FBGs, we proposed a long short-term memory (LSTM) deep learning algorithm integrated with discrete waveform transform (DWT) data smoother (de-noising) techniques. The DWT data de-noising methods are important techniques for analyzing and de-noising the sensor signals, and it further improves the strain sensing signal measurement accuracy of the LSTM model. Thus, after de-noising the sensor data, these data are fed into the LSTM model to measure the sensing signal of each FBG. The experimental results prove that the integration of LSTM with the DWT data de-noising technique achieved better sensing signal measurement accuracy, even in noisy data or environments. Therefore, the proposed IWDM-based FBG sensor network can accurately sense the signal of strain, even in bad or noisy environments; can increase the number of FBG sensors multiplexed in the sensor system; and can enhance the capacity of the sensor system.