Predicting the traffic in metro and access networks has a significant influence on expanding and upgrading the network. However, the intricate temporal and spatial correlations in such networks are affected by the users' behaviour and geographic characteristics. Consequently, predicting network traffic in metro or access networks faces significant challenges. To enhance the accuracy of this prediction, this paper explores a spatio-temporal approach to predicting traffic, based on a transformer model. This model effectively captures the temporal correlations in the traffic through a multi-head attention mechanism, learning long-term correlations resulting from the behaviour of the users of the individual nodes. Additionally, it acquires the spatial correlations of the traffic through a graph convolutional layer to capture short-term bursty correlations between users. Unlike previous single-point predictions, we optimize the model to make collaborative predictions for all the network nodes. Through parameter optimization, the improved model accurately predicts network traffic in small-scale regions. We implemented simulations using OMNET++ and predicted the traffic in various scenarios. Concurrently, we validated the proposed method with real network traffic based on operator measurements, achieving a prediction accuracy of 98.49%.

In this paper, a new technique for generation of ultra-wide and flattened optical frequency comb (OFC) based on serial cascading of a phase modulator and dual-driven Lithium-Niobate Mach Zehnder modulator (DD-LiNbO3-MZM) is proposed. Over 60 carriers were generated by carefully adjusting the RF switching voltage (RFSV) of the DD-LiNbO3-MZM and the signal frequency of the sinusoidal wave (RF) source. A low power amplified RF source with a signal driving power of ~16.9dBm is applied, and the power of CW laser is kept at 3dBm. The frequency spacing (FS) is kept at 20GHz for generating the maximum number of carriers. Nonetheless, the scheme is also tested for the FSs of 64GHz, and 32GHz. Each scenario is examined in simulation environment and the main outcomes are highlighted. The proposed scheme is comparatively simple and the FS varies with the applied RF source on the modulators. The achieved OFC lines have a tone-to-noise ratio (TNR) of over ~45dB with an undesired side mode suppression ratio of approximately 20dB. The comb lines are almost flat with a varying power deviation of around 0dB-6dB which is optimized to nearly ~0.12dB. Furthermore, the impact of the RFSV on the generated number of carriers is studied in detail. The scheme is analyzed in terms of cost efficiency, power deviations, TNR, optical signal to noise ratio, and number of achieved comb lines.

An optimized principal component-based phase estimation (OPCPE) algorithm is proposed for probabilistically shaped (PS) square-quadrature amplitude modulation (QAM) systems. The optimization method is based on mirroring and partially scaling the received constellation. Numerical simulation validation shows that the proposed phase recovery algorithm outperforms the well-known blind phase search (BPS) algorithm at low signal-to-noise ratio (SNR) and solves the incompatibility between principal component-based phase estimation (PCPE) and PS at high SNR. It's worth mentioning that the proposed algorithm retains the advantages of low cycle slip rate (CSR) and low computational complexity of PCPE. Furthermore, the performance of a hybrid implementation combining the proposed algorithm and BPS is also investigated. When the shaping parameter for a PS-64QAM system is 0.05, the proposed simple and hybrid methods can achieve performance improvements around 0.34-dB and 0.61-dB respectively benchmarking the widely used two-stage BPS (2S-BPS), considering the 0.8 normalized generalized mutual information (NGMI) threshold. To the best of our knowledge, this is the first time to robustly apply PCPE algorithm to PS systems, and the proposed design has stable NGMI performance, strong cycle slip tolerance and low computational complexity, which makes it a suitable candidate for practical probabilistically-shaped transmissions.

Routing and wavelength assignment (RWA) determine the quality of service (QoS) such as blocking probability and delay in wavelength division multiplexing (WDM) satellite optical network, whose topology is time-varying due to the highspeed mobility between satellite orbits. This paper introduces an ant colony optimization with adaptive load balance small window strategy under hop number loose constraint (ACO-ALB-SWSHNLC) which has highly robust to solving the RWA issue in the dynamic topology of the satellite optical network. In our proposed algorithm, an adaptive small window strategy and hop number loose constraint are proposed to improve the convergence speed and reduce the number of node hops by limiting its convergence area adaptively through the load in the window. The pheromone evaporation rate is controlled by wavelength usage between the links in the window to balance the load. The result shows that, compared to other ACO algorithms, ACO-ALB-SWSHNLC can effectively reduce blocking probability. In addition, good convergence speed and communication delay are maintained as well.

In a typical 10G-Passive Optical Network (XG-PON), the propagation delay between the Optical Network Unit (ONU) and Optical Line Terminal (OLT) is about 0.3 ms. With a frame size of 125 μs, this amounts to three frames of data in the upstream and three frames of data in the downstream. Assuming no processing delays, the grants for any bandwidth requests reach the ONU after six frames in this request-grant cycle. Often, during this six-frame delay, the queue situation is changed drastically, as much, more data would arrive in the queue. As a result, the queued data that is delayed loses its significance due to its real-time nature. Unfortunately, almost all dynamic bandwidth allocation (DBA) algorithms follow this request-grant cycle and hence lacking in their performance. This paper introduces a novel approach for bandwidth allocation, called Demand Forecasting DBA (DF-DBA), which predicts ONU’s future demands by statistical modelling of the demand patterns and tends to fulfil the predicted demands just in time, which results in reduced delay. Simulation results indicate that the proposed technique out-performs previous DBAs, such as GigaPON access network (GIANT) and round robin (RR) employing the request-grant cycle in terms of Throughput and Packet delivery ratio (PDR). Circular buffers are introduced in statistical predictions, which produce the least delay for this novel DF-DBA. This paper, hence, opens up a new horizon of research in which researchers may come up with better statistical models to brew better and better results for Passive optical networks.

The satellite-assisted Internet of Things (IoT) communication is considered a key component of the 6G network, and low Earth orbit (LEO) satellite is the leading choice of IoT-related satellites due to its minimum delay. Hybrid requests, including immediate reservation (IR) and advanced reservation (AR) services in LEO satellite netoworks cause the occurrence of resource fragments (RFrags), which adversely affect the network performance. To alleviate the degradation of network performance caused by resource fragmentation, a routing, wavelength, and time-slots assignment algorithm, which is named elastic resource allocation algorithm based on the dispersion degree (ERA-DD), is proposed in this article. Possible resource fragmentation types are analyzed and a fragmentation description named dispersion degree (DD) is designed. In the DD, the number of free resource blocks is accurately described by the state jumps (SJs) of adjacent resource slots, and the numerical relationship between SJs and free resource blocks is proposed and proved. Besides, restrictions on the selection priority of candidate schemes in the ERA-DD algorithm are analyzed. Finally, the traffic blocking rate, the wavelength utilization, the average communication delay, and the average initial delay are evaluated by simulation. The results demonstrate that RFrags are more fully utilized compared with the maximum total link spectrum consecutiveness (MTLSC) algorithm. The traffic blocking rate can be reduced by 32.5% and wavelength utilization can be increased by 1.6%.