Mitigation Scheme Research Articles

ADAM: An Adaptive DDoS Attack Mitigation Scheme in Software-Defined Cyber-Physical System

With the widespread innovation of the Internet of Things (IoT), Software-Defined Networking (SDN), and Cloud Computing, Cyber-Physical System (CPS) have been developed and widely adopted to facilitate our daily life and economy. In particular, modern society heavily relies on all kinds of CPSs, such as smart grids, and transportation systems. So the shutdown of critical services can lead to serious consequences. Meanwhile, Distributed Denial-of-Service (DDoS) attacks are becoming a major threat to the internet-enabled CPSs due to their ease of execution and the devastation it causes to the target systems. In addition, since the constant updating of attack methods, there is an urgent need for a method to defend against both known and unknown DDoS attacks. In this paper, we present an adaptive DDoS attack mitigation (ADAM) scheme to detect and mitigate DDoS attacks in Software-Defined CPSs. By combining information entropy and unsupervised anomaly detection methods, ADAM can not only automatically determine the current state, but also adaptively identify suspicious features which are thereafter used to mitigate DDoS attacks in a more precise way. We also propose a pipeline filtering mechanism to accurately drop attack traffic, and this method can be implemented in existing SDN networks without additional devices required. Unlike most of the classification-based DDoS mitigation scenarios, we aim to mitigate a wide spectrum of DDoS attacks without defining attack characteristics in advance. Namely, the main goal of ADAM is to effectively and adaptively defend against DDoS attacks that are constantly updating. Real data-driven experimental results show that ADAM has an average mitigation accuracy of 99.13% under high-intensity DDoS attacks. Compared with similar work, our method reduces the false positive rate by 35% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 59%.

Low-Latency Communication Using Delay-Aware Relays Against Reactive Adversaries

This work addresses a reactive jamming attack on the low-latency messages of a victim, wherein the jammer deploys countermeasure detection mechanisms to change its strategy. We highlight that the existing schemes against reactive jammers use relays with instantaneous full-duplex (FD) radios to evade the attack. However, due to the limitation of the radio architecture of the FD helper, instantaneous forwarding may not be possible in practice, thereby leading to increased decoding complexity at the destination and a high detection probability at the adversary. Pointing at this drawback, we propose a delay-aware cooperative framework wherein the victim seeks assistance from a delay-aware FD helper to forward its messages to the destination within the latency constraints. In particular, we first model the processing delay at the helper based on its hardware architecture, and then propose two low-complexity mitigation schemes, wherein the victim and the helper share their uplink frequencies using appropriate energy-splitting factors. For both the schemes, we solve the optimization problems of computing the near-optimal energy-splitting factors that minimize the joint error rates at the destination. Finally, through analytical and simulation results, we show that the proposed schemes facilitate the victim in evading the jamming attack whilst deceiving the reactive adversary.

Exergy analysis and particle swarm optimization of clean energy router based on a solar‐thermal‐assisted advanced adiabatic compressed air energy storage system

AbstractThe clean Energy router based on advanced adiabatic compressed air energy storage (AA‐CAES) has the characteristics of large capacity, high efficiency and zero carbon emission which are an effective mitigation scheme for the integration of renewables and peak‐shaving and a new clean energy technology for storing energy in the world. A novel solar‐thermal‐assisted AA‐CAES (ST‐AA‐CAES) is proposed in this paper, integrating variable thermal energy storage to improve the system electric to electric (E2E) and round‐trip efficiency (RTE). The efficiency and exergy evaluation of ST‐AA‐CAES are carried out to determine the performance of ST‐AA ‐CAES. The results illustrate that E2E, RTE, and exergy efficiency can reach 56.4%, 95.5%, and 55.9%, respectively. Meanwhile, the details of exergy efficiency and destruction of each subsystem are demonstrated. Particle swarm optimization algorithm is applied to analyse the economy of optimally integrated energy systems which has the advantages of high accuracy, convenient implementation and fast convergence. The system can be applied in abundant solar energy resources area with high efficiency and multi‐energy supply capability.

Characterizing and mitigating coherent errors in a trapped ion quantum processor using hidden inverses

Quantum computing testbeds exhibit high-fidelity quantum control over small collections of qubits, enabling performance of precise, repeatable operations followed by measurements. Currently, these noisy intermediate-scale devices can support a sufficient number of sequential operations prior to decoherence such that near term algorithms can be performed with proximate accuracy (like chemical accuracy for quantum chemistry problems). While the results of these algorithms are imperfect, these imperfections can help bootstrap quantum computer testbed development. Demonstrations of these algorithms over the past few years, coupled with the idea that imperfect algorithm performance can be caused by several dominant noise sources in the quantum processor, which can be measured and calibrated during algorithm execution or in post-processing, has led to the use of noise mitigation to improve typical computational results. Conversely, benchmark algorithms coupled with noise mitigation can help diagnose the nature of the noise, whether systematic or purely random. Here, we outline the use of coherent noise mitigation techniques as a characterization tool in trapped-ion testbeds. We perform model-fitting of the noisy data to determine the noise source based on realistic physics focused noise models and demonstrate that systematic noise amplification coupled with error mitigation schemes provides useful data for noise model deduction. Further, in order to connect lower level noise model details with application specific performance of near term algorithms, we experimentally construct the loss landscape of a variational algorithm under various injected noise sources coupled with error mitigation techniques. This type of connection enables application-aware hardware codesign, in which the most important noise sources in specific applications, like quantum chemistry, become foci of improvement in subsequent hardware generations.

Forecasting and Mitigating Rockfall based on Lidar Monitoring: A Case Study from Colorado

It is well-established that precursor movement that precedes large rockfalls can be detected by monitoring using repeated laser scanning (i.e., lidar), but there is a lack of documented cases that illustrate the practical application of this technology to forecast and help prevent large rockfalls along transportation corridors. In this paper, we present a case study in which routine lidar monitoring allowed a large (∼30 m3, ∼1050 ft3) moving block of rock to be detected before failure. Analysis of the lidar data allowed for historical movement to be evaluated, time to failure to be estimated, and quantification of the geometric and structural data necessary to design an effective mitigation scheme. The block movement was interpreted to be associated primarily with a planar sliding mechanism, and a limit equilibrium analysis was conducted to evaluate potential reinforcement schemes. Ultimately, a mesh and pattern bolt reinforcement system was installed. During rockbolt tensioning, PVC extensometers installed by the contractor showed closure of the fracture at the back of the block.

A Data Mining/ANFIS and Adaptive Control for Detection and Mitigation of Attacks on DC MGs

The integration of information and communication technologies (ICTs) has provided modern smart grids, such as direct current (DC) microgrids (MGs), with various advantages, e.g., the possibility of large-scale integration of renewable energy sources and complex control schemes. This extensive deployment of ICTs, however, makes DC MGs prone to a variety of cyber threats, e.g., false data injection (FDI) attacks. On this basis, this paper develops online detection and mitigation schemes to counter FDI attacks against DC MGs. Initially, in the offline training of the detection scheme, the density-based spatial clustering of applications with noise (DBSCAN) method is used for extracting prescriptive features of DC MG measurements and clustering them in healthy and under-attack operations under several uncertainties in DC MG operations. These features are used to train an adaptive network-based fuzzy inference system (ANFIS) architecture for the online identification of FDI attacks. Afterward, the trained ANFIS is used to detect FDI attacks and obtain the attack vectors benefiting from the real-time measurements estimated by an optimal state observer. Finally, an adaptive model predictive controller (AMPC) is developed to update the power-sharing commands—and mitigate the FDI attack—using the ANFIS’s obtained attack vectors. The effectiveness of the proposed framework is evaluated for several realistic FDI attack scenarios and different uncertainties. To show the scalability of the proposed detection and mitigation methods, a DC MG with eight converters is also studied in the presence of FDI attacks and uncertainties using real-time simulations.

Partitional Collaborative Mitigation Strategy of Distribution Network Harmonics Based on Distributed Model Predictive Control

Dispersed harmonic control makes a critical guarantee for safe and stable operation of distribution networks. However, conventional point-to-point local control method has limitations. In addition, harmonic current injection has volatility and time-variability, and the residual capacity (RC) of multi-functional grid-connected inverter (MFGCI) employed for auxiliary harmonic compensation is uncertain, which challenges mitigation decision-making. In this study, a grid-side distributed mitigation strategy based on distributed model predictive control (DMPC) is proposed. Firstly, the voltage distortion observation node is selected based on node clustering, and sensitivity analysis of harmonic mitigation for observation nodes is conducted to divide the whole network into multiple control areas. Secondly, for global optimal of voltage distortion, the long time scale distributed optimization model for mitigation parameters orienting partitional coordination is established. Finally, a rolling optimization model based on DMPC for correction of conductance parameters is developed from regional autonomy perspective. The results show that: (1) Distributed mitigation scheme can improve the total harmonic distortion of voltage (THDV) of the whole network node; (2) Compared with control references, the corrected parameters can reduce the decision deviation and further lower the THDV by about 2%; (3) In multi-uncertain scenarios, multi-time-scale optimization can alleviate the uncertainty in harmonic control.

Experimental evaluation of digitally verifiable photonic computing for blockchain and cryptocurrency

As blockchain technology and cryptocurrency become increasingly mainstream, photonic computing has emerged as an efficient hardware platform that reduces ever-increasing energy costs required to verify transactions in decentralized cryptonetworks. To reduce sensitivity of these verifications to photonic hardware error, we propose and experimentally demonstrate a cryptographic scheme, LightHash, that implements robust, low-bit precision matrix multiplication in programmable silicon photonic networks. We demonstrate an error mitigation scheme to reduce error by averaging computation across circuits, and simulate energy-efficiency-error trade-offs for large circuit sizes. We conclude that our error-resistant and efficient hardware solution can potentially generate a new market for decentralized photonic blockchain.

A Deep Reinforcement Learning-based DDoS Attack Mitigation Scheme for Securing Big Data in Fog-Assisted Cloud Environment

A Deep Reinforcement Learning-based DDoS Attack Mitigation Scheme for Securing Big Data in Fog-Assisted Cloud Environment

LCDT-M: Log-Cluster DDoS Tree Mitigation Framework Using SDN in the Cloud Environment

In the cloud computing platform, DDoS (Distributed Denial-of-service) attacks are one of the most commonly occurring attacks. Research studies on DDoS mitigation rarely considered the data shift problem in real-time implementation. Concurrently, existing studies have attempted to perform DDoS attack detection. Nevertheless, they have been deficient regarding the detection rate. Hence, the proposed study proposes a novel DDoS mitigation scheme using LCDT-M (Log-Cluster DDoS Tree Mitigation) framework for the hybrid cloud environment. LCDT-M detects and mitigates DDoS attacks in the Software-Defined Network (SDN) based cloud environment. The LCDT-M comprises three algorithms: GFS (Greedy Feature Selection), TLMC (Two Log Mean Clustering), and DM (Detection-Mitigation) based on DT (Decision Tree) to optimize the detection of DDoS attacks along with mitigation in SDN. The study simulated the defined cloud environment and considered the data shift problem during the real-time implementation. As a result, the proposed architecture achieved an accuracy of about 99.83%, confirming its superior performance.

Detection and Prevention of SIP REGISTER Injection Attack on a VoLTE Network

Recent technological advances have indicated widespread use of Voice Over Long-Term Evolution (VoLTE) networks based on developing 5G networks. Despite its ease of design and deployment, VoLTE is vulnerable to many sorts of attacks at the control plane's Session Initiation Protocol (SIP), which exchanges signaling messages for calls via starting call setups, management, and termination. These SIP attacks may take the form of modified SIP messages that force the SIP devices to restart, or they may take the form of flooding the SIP devices with invite messages, register requests that cause the device to run out of memory, and denying genuine users access to the device. These attacks are commonly known as Distributed Denial of Service (DDoS) attacks. The SIP register injection attack, which might be injected during the commencement step by SIP equipped devices (SIP smartphones), prior to setting up the Secured Internet Protocol (IPsec) tunnel for the remaining SIP sessions, is of particular relevance, due to its characteristics of exhausting the available bandwidth, memory, and CPU resources, resulting in SIP device failure. Consequently, there is a need to address this difficulty by building an SIP register injection attack detection and mitigation technique. Prior to being processed by the Proxy Call Session Control Function. The proposed scheme verifies each initial register request from User Equipment (UE) at the home network of Internet Protocol Multimedia Subsystems (IMS) and compares it to the incoming SIP register request pattern with those stored on the scheme's table (P-CSCF). The proposed technique detects and drops every SIP register request with an abnormal pattern that is associated with an attack. The method proved promising with detection accuracy of over 96.67 percent, which is a solid potential as a preliminary setup towards the creation of a robust Real-time SIP detection and mitigation scheme for 5G networks.

Flood Sedimentology for Future Floods Mitigation in North Luwu, Sulawesi, Indonesia

A sedimentological study after the flash floods that hit North Luwu on July 13, 2020, has been carried out on three affected rivers, namely the Masamba River, the Radda River, and the Binuang River. The study aims to determine the sedimentological impact of the 2020 flash flood disaster, including sedimentation rate, annual bedload sediment volume, and total sediments, which will be used as a reference for future mitigation consideration. The study is based on fieldwork for data collection and laboratory analysis. The results of field measurements and laboratory analysis are then processed by calculating the sedimentation rate at the annual discharge, the bedload sediment volume, and the total estimated sediment accumulated by the flash flood. Sedimentation rate analysis was performed using the Ackers-White formula, and flood delineation was processed using HEC-RAS software. The climatological data from the climatology station at Andi Djemma Airport were used to calculate the river discharge. It is estimated that the volume of bedload sediment in the Binuang River is 16,194,168 m3/year, that of the Masamba River is 7,852,061 m3/year, and that of the Radda River is 4,003,011 m3/year. The volume of sediment brought by flash flood sedimentation in the Radda River is 9,141,608.39 m3, while that in the Masamba River is 55,131,761.29 m3, and that in the Binuang River is 136,838,603.61 m3. The total estimated sedimentation generated by the flash flood on the three rivers on July 13, 2020, is 222,476,966 m3. Based on the study, zonation for vulnerability levels is designed for a future mitigation scheme. The zonation can be classified into three zones: 1) the highly affected zone; 2) the moderately affected zone; and 3) the least affected zone, with special purposes in each zone. It is strongly recommended that future disaster settlement and infrastructure reconstruction policies be based on this zone to reduce disaster risk. Doi: 10.28991/CEJ-2023-09-04-011 Full Text: PDF

Distance-Based Elliptical Circumnavigation Control for Non-Holonomic Robots With Event-Triggered Unknown System Dynamics Estimators

How to efficiently collect multi-dimensional information of traffic accidents with high dangers has triggered intensive concerns in intelligent transportation community. This paper provides a viable and continuous observation solution using low-budgeted mobile robots. At the kinematic level, a relative position estimator utilizing available distance data is constructed with an exponential error convergence, removing the dependency of using global position. To proceed, resorting to estimation results, an elliptical encircling guidance rule with a time-varying radius is established to preserve circumnavigation concerning targets. At the kinetic level, a new fuel-saving uncertainty mitigation scheme, i.e., event-triggered unknown system dynamics estimators (ETUSDEs) with the feature of a reduced transmission load and a concise structure are respectively developed in velocity and angular rate subsystems to reconstruct uncertainties with a prescribed decaying rate, where event-triggering conditions are enforced to schedule updating frequency of actuators and measurements in an aperiodic manner instead of a fixed time interval. Then, an event-triggered robust kinetic control protocol is synthesized to achieve an accurate command tracking without incurring Zeno behaviors. Finally, the convergence of entire system is illustrated through input-to-state stable (ISS) criterion. Simulation results are delivered to testify the effectiveness of proposed method.

Geographic variation in organic carbon storage by seagrass beds

AbstractSince seagrasses are efficient sinks for marine organic carbon, there is growing interest in incorporating seagrass protection and restoration into climate mitigation schemes, that is, offering credit for accumulated carbon to offset carbon dioxide emissions. However, patterns and drivers of organic carbon storage by seagrasses are not well resolved, especially at scales relevant to management decisions. Here, we quantified geographic variation in standing stocks of sedimentary organic carbon (Mg Corg ha−1) associated with seagrasses along the northern Florida Gulf Coast using field surveys and sediment cores. We measured plant biomass, organic carbon, and sediment composition in each core. Using a multivariate modeling approach, we evaluated the relative importance of ecological, physical, oceanographic, and seascape drivers, developing the first spatially explicit predictions of seagrass‐associated carbon stocks for this region. Applying model predictions to confirmed seagrass beds and potential recovery areas, we also estimated the carbon storage value of potential seagrass conservation and restoration as the resulting stock enhancement value per hectare of seagrass (Δ Mg Corg ha−1). We found that organic carbon stored by seagrass sediments varied considerably across this region, with stocks significantly increasing with seagrass cover, proximity to oyster reefs, and distance from river outlets, highlighting potential synergies for coordinated management. We also found that current seagrass beds could offer nearly double the carbon storage value of potential recovery areas, emphasizing the importance of conservation as well as restoration. Our results have important implications for management, restoration, and understanding biogeographic patterns of seagrass ecosystem services.

Non-local contribution from small scales in galaxy–galaxy lensing: comparison of mitigation schemes

ABSTRACT Recent cosmological analyses with large-scale structure and weak lensing measurements, usually referred to as 3 × 2pt, had to discard a lot of signal to noise from small scales due to our inability to accurately model non-linearities and baryonic effects. Galaxy–galaxy lensing, or the position–shear correlation between lens and source galaxies, is one of the three two-point correlation functions that are included in such analyses, usually estimated with the mean tangential shear. However, tangential shear measurements at a given angular scale θ or physical scale R carry information from all scales below that, forcing the scale cuts applied in real data to be significantly larger than the scale at which theoretical uncertainties become problematic. Recently, there have been a few independent efforts that aim to mitigate the non-locality of the galaxy–galaxy lensing signal. Here, we perform a comparison of the different methods, including the Y-transformation, the point-mass marginalization methodology, and the annular differential surface density statistic. We do the comparison at the cosmological constraints level in a combined galaxy clustering and galaxy–galaxy lensing analysis. We find that all the estimators yield equivalent cosmological results assuming a simulated Rubin Observatory Legacy Survey of Space and Time (LSST) Year 1 like set-up and also when applied to DES Y3 data. With the LSST Y1 set-up, we find that the mitigation schemes yield ∼1.3 times more constraining S8 results than applying larger scale cuts without using any mitigation scheme.

Digital-filter-aided crosstalk-mitigation for a high spatial resolution AWGR-based 2D IR beam-steered indoor optical wireless communication system.

The growing demand for wireless connectivity is attracting interest in optical wireless communication (OWC) technique. In this paper, a filter-aided crosstalk mitigation scheme, employing digital Nyquist filters, is proposed to eliminate the trade-off between the spatial resolution and the channel capacity for the AWGR-based 2D infrared beam-steered indoor OWC system. By shaping the transmitted signal for narrow spectral occupancy, the inter-channel crosstalk resulting from the imperfect AWGR filtering can be avoided, which enables a denser AWGR grid. In addition, the spectral-efficient signal reduces the bandwidth requirement of the AWGR, which allows a low-complexity AWGR design. Thirdly, the proposed method is not sensitive to the wavelength misalignment between AWGRs and lasers, which relaxes the design of high wavelength stability lasers. Moreover, the proposed method is cost-efficient as we can make use of the mature DSP technique without additional optical components. The 20-Gbit/s data rate OWC capacity using PAM4 format has been experimentally demonstrated over a 6-GHz bandwidth-limited AWGR-based 1.1-m free-space link. The experimental results show the feasibility and effectiveness of the proposed method. By combining our proposed method with the polarization orthogonality technique, a promising capacity per beam of 40 Gbit/s is potentially attainable.

Stochastic Rational Method for Estimation of Flood Peak Uncertainty in Arid Basins: Comparison between Monte Carlo and First Order Second Moment Methods with a Case Study in Southwest Saudi Arabia

The flood peak is commonly estimated using the rational method for the design of hydraulic structures. The method is mainly used in a deterministic context. However, there is often uncertainty in flood predictions, which should be incorporated in the design of mitigation schemes. This research proposes a methodology to cope with uncertainty in the rational method via the application of a stochastic framework. Data from 158 storms, recorded in the period 1984–1987 in 19 subbasins in the southwestern part of Saudi Arabia, were used to implement the proposed methodology. A tri-variate log-normal probability density function was used to model the joint relationship between the rational method parameters. The model considered the parameters as random variables. The uncertainty in the rainstorms was represented by intensity or depth; the uncertainty in basin delineation (due to the use of different digital elevation model resolution) was represented by the basin area; and the uncertainty in the land use/land cover was represented by the runoff coefficient. The Monte Carlo method was used to generate realizations of the peak flow and runoff volume with 95% and 99% confidence levels from the input parameters. Although the correlation between the parameters was weak, the model was capable of simulating the rational model parameters and estimating the peak flow and runoff volume relatively well, and the generated realizations fell within the confidence levels, except for a few marginal cases. The model can be used to generate peak flows and the associated confidence limits in ungauged basins from the statistics of the input parameters using the equations developed in this study.

UNIONS: The impact of systematic errors on weak-lensing peak counts

Context. The Ultraviolet Near-Infrared Optical Northern Survey (UNIONS) is an ongoing deep photometric multiband survey of the northern sky. As part of UNIONS, the Canada-France Imaging Survey (CFIS) provides r-band data, which we use to study weak-lensing peak counts for cosmological inference. Aims. We assess systematic effects for weak-lensing peak counts and their impact on cosmological parameters for the UNIONS survey. In particular, we present results on local calibration, metacalibration shear bias, baryonic feedback, the source galaxy redshift estimate, intrinsic alignment, and cluster member dilution. Methods. For each uncertainty and systematic effect, we describe our mitigation scheme and the impact on cosmological parameter constraints. We obtain constraints on cosmological parameters from Monte Carlo Markov chains using CFIS data and MassiveNuS N-body simulations as a model for peak counts statistics. Results. Depending on the calibration (local versus global, and the inclusion or not of the residual multiplicative shear bias), the mean matter density parameter, Ωm, can shift by up to −0.024 (−0.5σ). We also see that including baryonic corrections can shift Ωm by +0.027 (+0.5σ) with respect to the dark-matter-only simulations. Reducing the impact of the intrinsic alignment and cluster member dilution through signal-to-noise cuts leads to larger constraints. Finally, with a mean redshift uncertainty of Δz̄ = 0.03, we see that the shift in Ωm (+0.001, which corresponds to +0.02σ) is not significant. Conclusions. This paper investigates, for the first time with UNIONS weak-lensing data and peak counts, the impact of systematic effects. The value of Ωm is the most impacted and can shift by up to ∼0.03, which corresponds to 0.5σ depending on the choices for each systematics. We expect constraints to become more reliable with future (larger) data catalogs, for which the current pipeline will provide a starting point. The code used to obtain the results is available on GitHub.

Unequal clustering scheme for hotspot mitigation in IoT-enabled wireless sensor networks based on fire hawk optimization

Wireless sensor networks (WSNs) related to the Internet of Things (IoT) have shown incredible growth with technological advancements, offering a greater number of applications all over the world. Sensor nodes are deployed closer to the base station (BS) in some scenarios and held accountable for transmitting data from neighboring and own nodes against the BS and depletes energy. In the network, this problem is referred to as the "hotspot issue" and it may be fixed using procedures that use unequal clustering. In this study, a novel approach for IoT-assisted wireless sensor networks called the Fire Hawk Optimization-based Unequal Clustering Scheme for Hotspot Mitigation (FHOUCS-HSM) is developed. In the presented FHOUCS-HSM model, a first-order radio energy model has been utilized. The FHOUCS-HSM technique follows the foraging characteristics of whistling kites, black kites, and brown falcons. The design of the FHO algorithm for unequal clustering shows the novelty of the work. In addition to this, the FHOUCS-HSM model computes a fitness function for the use of uneven cluster size and the selection of cluster heads (CH). The comparative research highlights the advantages that the FHOUCS-HSM technique has over many models that are already in use.

A survey on machine learning schemes for fiber nonlinearity mitigation in radio over fiber system

Abstract The fifth generation is the most recent generation of communication needed for high data rates. High spectrum availability, low jitter, high reliability, minimal latency, and increased capacity are just a few benefits of 5th generation. Optical fiber supports the 5G network’s backhaul to meet the enhanced capacity and big data rate requirements. When the fiber is used as a propagation medium, a significant number of nonlinearities manifest. These nonlinearity effects in optical fiber communication are among the most detrimental to modern communication systems because it results in various modulator distortions like phase, harmonic, and intermodulation, distortion, adjoining channel noise, and many more undesirable consequences. The primary fiber nonlinear effects in the radio over fiber communication systems are the Kerr nonlinearity and scattering effects, which are caused by alterations in refractive index as a result of the signal. To overcome these limits, several strategies have been put forth. In particular, the nonlinearity during signal modulation, transmission, and detection has attracted a lot of study attention due to the complex physical layer restrictions in RoF systems. One such fascinating potential is machine learning (ML) methods. In this article, we look at recent advances in ML methods for RoF systems, notably those that use ML models to reduce various types of impairments and improve system performance.