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).

Involvement of free-space optics in Raman distributed temperature sensing.

This Letter demonstrates the successful use of free-space optics (FSO) as a transition channel for an air segment in transmitting Raman backscattering signals for distributed temperature sensing (DTS). A barrier-free air segment link shaped by an FSO is part of the Raman-based DTS (RDTS) fiber optic transmission route. For this plan, the FSO enables delivery of the RDTS's pulse with the low-loss transmission over the air segment while also returning to the RDTS the varied Raman backscattered signals from the probing temperature variations for signal interpretation. The difference between various temperatures sensed and the referential air temperature remains nearly the same before and after passing the FSO. The viability of this technology provides a crucial basis for tackling the high expense of installing and repairing DTS cables and the challenges associated with doing so owing to topographical restrictions.

Integrated Sensor-Optics Communication System Using Bidirectional Fiber and FSO Channels and Hybrid Deep Learning Techniques.

This paper introduces a new bidirectional integration approach that combines fiber sensor/free space optics (FSO) communication using an intensity and wavelength division multiplexer (IWDM) techniques-based long-distance fiber Bragg grating (FBG) sensor strain-sensing system. By implementing coarse wavelength division multiplexing (CWDM), the system achieves the simultaneous transmission of optical communication and fiber optical sensor (FOS) sensing signals, resulting in a highly capable, flexible, and cost-effective solution. The proposed FSO transmission technique addresses complex fiber cable installation concerns with topographical limitations. This bidirectional structure ensures the reliability and stability of the long-distance FBG sensor system, supported by extensive research and experimentation. A hybrid stacked gated recurrent units and long short-term memory (SGRU-LSTM) model is proposed to enhance strain measurement accuracy by predicting and measuring the central wavelength of overlapped strain-sensing FBG sensor signals. The results demonstrate the superiority of the proposed model in peak wavelength detection accuracy. The primary benefit of integrating communication and sensing is the significant reduction in construction costs by eliminating the requirement for two individual fiber optic systems, as the integration allows for a single system to fulfill both functions, resulting in more efficient and cost-effective implementation. Overall, this paper contributes to advancing long-distance FBG sensor systems by integrating fiber sensor/FSO communication and deep learning techniques, improving transmission distance, multiplexing capacity, measurement accuracy, system survivability, and cost-effectiveness.

High Accuracy and Cost-Effective Fiber Optic Liquid Level Sensing System Based on Deep Neural Network.

In this paper, a novel liquid level sensing system is proposed to enhance the capacity of the sensing system, as well as reduce the cost and increase the sensing accuracy. The proposed sensing system can monitor the liquid level of several points at the same time in the sensing unit. Additionally, for cost efficiency, the proposed system employs only one sensor at each spot and all the sensors are multiplexed. In multiplexed systems, when changing the liquid level inside the container, the float position is changed and leads to an overlap or cross-talk between two sensors. To solve this overlap problem and to accurately predict the liquid level of each container, we proposed a deep neural network (DNN) approach to properly identify the water level. The performance of the proposed DNN model is evaluated via two different scenarios and the result proves that the proposed DNN model can accurately predict the liquid level of each point. Furthermore, when comparing the DNN model with the conventional machine learning schemes, including random forest (RF) and support vector machines (SVM), the DNN model exhibits the best performance.

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.

Design Reliable Bus Structure Distributed Fiber Bragg Grating Sensor Network Using Gated Recurrent Unit Network.

The focus of this paper was designing and demonstrating bus structure FBG sensor networks using intensity wavelength division multiplexing (IWDM) techniques and a gated recurrent unit (GRU) algorithm to increase the capability of multiplexing and the ability to detect Bragg wavelengths with greater accuracy. Several Fiber Bragg grating (FBG) sensors are coupled with power ratios of 90:10 and 80:10, respectively in the suggested experimental setup. We used the latest IWDM multiplexing technique for the proposed scheme, as the IWDM system increases the number of sensors and allows us to alleviate the limited operational region drawback of conventional wavelength division multiplexing (WDM). However, IWDM has a crosstalk problem that causes high-sensor signal measurement errors. Thus, we proposed the GRU model to overcome this crosstalk or overlapping problem by converting the spectral detection problem into a regression problem and considered the sequence of spectral features as input. By feeding this sequential spectrum dataset into the GRU model, we trained the GRU system until we achieved optimal efficiency. Consequently, the well-trained GRU model quickly and accurately identifies the Bragg wavelength of each FBG from the overlapping spectra. The Bragg wavelength detection performance of our proposed GRU model is tested or validated using different numbers of FBG sensors, such as 3-FBG, 5-FBG, 7-FBG, and 10-FBG, separately. As a result, the experiment result proves that the well-trained GRU model accurately identifies each FBG Bragg wavelength, and even the number of FBG sensors increase, as well as the spectra of FBGs, which are partially or fully overlapped. Therefore, to boost the detection efficiency, reliability, and to increase the multiplexing capabilities of FBG sensor networks, the proposed sensor system is better than the other previously proposed methods.

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.

Hybrid CATV/MMW/BB lightwave transmission system based on fiber-wired/fiber-wireless/fiber-VLLC integrations.

A hybrid lightwave transmission system for cable television (CATV)/millimeter-wave (MMW)/baseband (BB) signal transmission based on fiber-wired/fiber-wireless/fiber-visible laser light communication (VLLC) integrations is proposed and demonstrated. For down-link transmission, the light is intensity-modulated with 50-550 MHz CATV signal and optically promoted from 25 GHz radio frequency (RF) signal to 10 Gbps/50 GHz and 20 Gbps/100 GHz MMW data signals based on fiber-wired and fiber-wireless integrations. Good performances of carrier-to-noise ratio (CNR), composite second-order (CSO), composite triple-beat (CTB), and bit error rate (BER) are obtained over a 40-km single-mode fiber (SMF) and a 10-m RF wireless transport. For up-link transmission, the light is successfully intensity-remodulated with 5-Gbps BB data stream based on fiber-VLLC integration. Good BER performance is achieved over a 40-km SMF and a 10-m free-space VLLC transport. Such a hybrid CATV/MMW/BB lightwave transmission system is an attractive alternative, it gives the benefits of a communication link for broader bandwidth and higher transmission rate.

Hybrid wireless-over-fiber transmission system based on multiple injection-locked FP LDs.

A hybrid wireless-over-fiber (WoF) transmission system based on multiple injection-locked Fabry-Perot laser diodes (FP LDs) is proposed and experimentally demonstrated. Unlike the traditional hybrid WoF transmission systems that require multiple distributed feedback (DFB) LDs to support different kinds of services, the proposed system employs multiple injection-locked FP LDs to provide different kinds of applications. Such a hybrid WoF transmission system delivers downstream intensity-modulated 20-GHz microwave (MW)/60-GHz millimeter-wave (MMW)/550-MHz cable television (CATV) signals and upstream phase-remodulated 20-GHz MW signal. Excellent bit error rate (BER), carrier-to-noise ratio (CNR), composite second-order (CSO), and composite triple-beat (CTB) are observed over a 40-km single-mode fiber (SMF) and a 4-m radio frequency (RF) wireless transport. Such a hybrid WoF transmission system has practical applications for fiber-wireless convergence to provide broadband integrated services, including telecommunication, data communication, and CATV services.

20-Gbps optical LiFi transport system.

A 20-Gbps optical light-based WiFi (LiFi) transport system employing vertical-cavity surface-emitting laser (VCSEL) and external light injection technique with 16-quadrature amplitude modulation (QAM)-orthogonal frequency-division multiplexing (OFDM) modulating signal is proposed. Good bit error rate (BER) performance and clear constellation map are achieved in our proposed optical LiFi transport systems. An optical LiFi transport system, delivering 16-QAM-OFDM signal over a 6-m free-space link, with a data rate of 20 Gbps, is successfully demonstrated. Such a 20-Gbps optical LiFi transport system provides the advantage of a free-space communication link for high data rates, which can accelerate the visible laser light communication (VLLC) deployment.

Employing injection-locked FP LDs to set up a hybrid CATV/MW/MMW WDM light wave transmission system.

A hybrid cable television (CATV)/microwave (MW)/millimeter-wave (MMW) wavelength-division-multiplexing (WDM) light wave transmission system based on injection-locked Fabry-Perot laser diodes (FP LDs) is proposed and demonstrated. Different from conventional hybrid WDM light wave transmission systems, which need wavelength-selected distributed feedback laser diodes to support various services, the proposed systems employ injection-locked FP LDs to provide multiple applications. Over a 40 km single-mode fiber transport, impressive performances of carrier-to-noise ratio/composite second-order/composite triple-beat/bit error rate are obtained for 550 MHz CATV/20 GHz MW/40 GHz MMW/60 GHz MMW signal transmissions. Such a hybrid WDM light wave transmission system would be attractive for fiber links to provide broadband integrated services.

Optical 16-QAM-52-OFDM transmission at 4 Gbit/s by directly modulating a coherently injection-locked colorless laser diode.

Coherently injection-locked and directly modulated weak-resonant-cavity laser diode (WRC-FPLD) for back-to-back optical 16-quadrature-amplitude-modulation (QAM) and 52-subcarrier orthogonal frequency division multiplexing (OFDM) transmission with maximum bit rate up to 4 Gbit/s at carrier frequency of 2.5 GHz is demonstrated. The WRC-FPLD transmitter source is a specific design with very weak-resonant longitudinal modes to preserve its broadband gain spectral characteristics for serving as a colorless WDM-PON transmitter. Under coherent injection-locking, the relative-intensity noise (RIN) of the injection-locked WRC-FPLD can be suppressed to ?105 dBc/Hz and the error vector magnitude of the received optical OFDM data is greatly reduced with the amplitude error suppressed down 5.5%. Such a coherently injection-locked single-mode WRC-FPLD can perform both the back-to-back and the 25-km-SMF 16-QAM-52-OFDM transmissions with a symbol rate of 20-MSa/s in each OFDM subcarrier. After coherent injection locking, the BER of the back-to-back transmitted 16-QAM-52-OFDM data is reduced to 2.5 × 10(-5) at receiving power of ?10 dBm. After propagating along a 25-km-long SMF, a receiving power sensitivity of ?7.5 dBm is required to obtain a lowest BER of 2.5 × 10(-5), and a power penalty of 2.7 dB is observed when comparing with the back-to-back transmission.

A hybrid CATV/OFDM long-reach passive optical network architecture.

A hybrid CATV/OFDM long-reach PON architecture is proposed and experimentally demonstrated. By multiplexing the OFDM and CATV signals in different frequency bands, the overall network structure is simplified and the available bandwidth for the OFDM signals is increased. Furthermore, by carefully adjusting the driving voltage of the employed CATV transmitter, the overall transmission performance can be optimized by eliminating a large amount of unwanted distortions. Unlike the current fiber optical CATV transport system in which the CATV signals need to be amplified in every 30 ~40 km transmission span, the proposed architecture has successfully extended the transmission span to 60 km. This can practically remove the needs of electrical power provisioning and monitoring between the central office (CO) and each local exchange (LE). Good transmission performances of carrier-to-noise ratio (CNR), composite second-order (CSO), composite triple beat (CTB) and bit error rate (BER) were obtained for the transmitted CATV and OFDM signals. All of these experimental results prove the practice and efficiency of the proposed architecture in providing simplicity and extended reach services to customers.

RoF transport systems with OSNR enhanced multi-band optical carrier generator.

A combination of an economic multi-band optical carrier generator and a novel optical signal to noise ratio (OSNR) enhancement circuit is proposed and demonstrated for radio over fiber (RoF) transport systems. Different from normal RoF transport systems which a central station (CS) needs multiple dedicate wavelength laser diodes (LDs) to support various base stations (BSs), the proposed scheme can employ a single LD to provide multiple optical carriers for various BSs. To verify this scheme, 8 coherent optical carriers are firstly generated using a single LD and a local oscillator (LO). Subsequently, their OSNR values are optimized by the developed OSNR enhancement circuit. An up to 15 dB OSNR enlargement in those optical carriers is experimentally achieved. To demonstrate the practice of the proposal, a pair of those optical carriers is employed to experimentally achieve frequency up-conversion process in a RoF transport system. Clear eye diagram and error free transmission reveal that with a proper carrier selector the proposed scheme can be employed to support multiple RoF transmissions. Furthermore, this proposal also presents a high possibility to achieve 60 GHz RoF transmission using a 10 GHz LO, a LD and a low frequency external modulator.

Hybrid CATV/16-QAM OFDM in-building networks over SMF and GI-POF transport.

A hybrid CATV/16-QAM OFDM in-building network over a combination of single-mode fiber (SMF) and graded-index plastic optical fiber (GI-POF) transport is proposed and experimentally demonstrated with good qualities of service. In this system, a 1556 nm optical signal is directly transmitted along with two fiber spans (20-km SMF + 25-m GI-POF). Without using any wavelength conversion or bridge circuit between SMF and POF connection, error free transmissions with sufficient low bit error rate (BER) values are achieved for 2.5 Gbps/2.5 GHz and 5 Gbps/2.5 GHz OFDM signals; as well as good performances of carrier-to-noise ratio (CNR), composite second-order (CSO), and composite triple beat (CTB) are obtained for CATV one. This proposed network reveals an outstanding one with economy and convenience to be installed.

Hybrid cable television and orthogonal-frequency-division-multiplexing transport system basing on single wavelength polarization and amplitude remodulation schemes.

A hybrid community antenna television (CATV) and orthogonal-frequency-division-multiplexing (OFDM) transport system is proposed and experimentally demonstrated to transmit multiple CATV channels and bi-directional radio frequency signals on a single optical carrier. By polarization remodulating an optical CATV signal with downstream OFDM signals and then amplitude remodulating upstream OFDM signals with the hybrid CATV/OFDM signals, this architecture can efficiently utilize only one optical carrier to support optical analog/digital CATV transmission and bi-directional wireless broadband services for each client. Good experimental results prove that this architecture provides a proper wavelength utilization scheme for future multiwavelength optical transport systems.

Simplified radio-over-fiber transport systems with a low-cost multiband light source.

In this Letter, low-cost radio-over-fiber (ROF) transport systems are proposed and experimentally demonstrated. By utilizing a laser diode (LD) and a local oscillator (LO) to generate coherent multiband optical carriers, as well as a self-composed wavelength selector to separate every two carriers for different ROF transport systems, no any other dedicated LD or electrical frequency upconverting circuit/process is needed in the central station (CS). Compared with current ROF systems, the required numbers of LDs, LOs, and mixers in a CS are significantly reduced. Reducing the number of components not only can simplify the network structure but can also reduce the volume and complexity of the relative logistics. To demonstrate the practice of the proposed ROF transport systems, clear eye diagrams and error-free transmission performance are experimentally presented.

Direct CATV modulation and phase remodulated radio-over-fiber transport system.

A novel transport system, with directly modulating community antenna television (CATV) signal downstream and phase-remodulating radio-over-fiber (ROF) signal upstream, is proposed and experimentally demonstrated. By modulating multi-carriers CATV signal in amplitude domain and ROF signal in phase domain, a single optical wavelength is able to serve these two applications simultaneous. To be the first system of communicating CATV signal downstream and phase remodulating radio signal upstream, the performances of transmitting CATV and radio signals over 20 km single-mode fiber (SMF) were experimentally verified. Good performances of carrier-to-noise ratio (CNR), composite second-order (CSO), and composite triple beat (CTB) were obtained for CATV applications as well as high extinction ration (ER) and low bit error rate (BER) values were measured for ROF transmission.

A Full duplex radio-over-fiber linkwith Multi-level OFDM signal via a single-electrode MZM and wavelength reuse with aRSOA.

This work demonstrates the feasibility of a full duplex Radio-over-fiber (RoF) link employing multi-level OFDM signal via a single-electrode Mach-Zehnder modulator and wavelength reuse for uplink utilizing a reflective semiconductor optical amplifier (RSOA). A High spectral efficiency 5-Gb/s 16-QAM OFDM signal with frequency multiplication for the RoF downstream link is demonstrated, and negligible penalty is achieved after 25-km standard single mode fiber transmission. Furthermore, wavelength reuse for a 1.25-Gb/s OOK signal via a RSOA for the upstream link is also demonstrated with a receiver penalty of less than 0.5 dB following 25-km SMF transmission.

Reliable fiber sensor system with star-ring-bus architecture.

This work presents a novel star-ring-bus sensor system and demonstrates its effectiveness. The main trunk of the proposed sensor system is a star topology and the sensing branches comprise a series of bus subnets. Any weakness in the reliability of the sensor system is overcome by adding remote nodes and switches to the ring and bus subnets. To construct the proposed star-ring-bus sensor system, a fiber ring laser scheme is used to improve the signal-to-noise ratio of the sensor system. The proposed system increases the reliability and capacity of fiber sensor systems.