Error vector magnitude (EVM) has proven to be one of the optical performance monitoring metrics providing the quantitative estimation of error statistics. However, the EVM estimation efficiency has not been fully exploited in terms of complexity and energy consumption. Therefore, in this paper, we explore two deep-learning-based EVM estimation schemes. The first scheme exploits convolutional neural networks (CNNs) to extract EVM information from images of the constellation diagram in the in-phase/quadrature (IQ) complex plane or amplitude histograms (AHs). The second scheme relies on feedforward neural networks (FFNNs) extracting features from a vectorized representation of AHs. In both cases, we use short sequences of 32 Gbaud m-ary quadrature amplitude modulation (mQAM) signals captured before or after a carrier phase recovery. The impacts of the sequence length, neural network structure, and data set representation on the EVM estimation accuracy as well as the model training time are thoroughly studied. Furthermore, we validate the performance of the proposed schemes using the experimental implementation of 28 Gbaud 64QAM signals. We achieve a mean absolute estimation error below 0.15%, with short signals consisting of only 100 symbols per IQ cluster. Considering the estimation accuracy, the implementation complexity, and the potential energy savings, the proposed CNN- and FFNN-based schemes can be used to perform time-sensitive and accurate EVM estimation for mQAM signal quality monitoring purposes.

We propose a fast and accurate signal quality monitoring scheme that uses convolutional neural networks for error vector magnitude (EVM) estimation in coherent optical communications. We build a regression model to extract EVM information from complex signal constellation diagrams using a small number of received symbols. For the additive-white-Gaussian-noise-impaired channel, the proposed EVM estimation scheme shows a normalized mean absolute estimation error of 3.7% for quadrature phase-shift keying, 2.2% for 16-Ary quadrature amplitude modulation (16QAM), and 1.1% for 64QAM signals, requiring only 100 symbols per constellation cluster in each observation period. Therefore, it can be used as a low-complexity alternative to conventional bit-error-rate estimation, enabling solutions for intelligent optical performance monitoring. 

The deployment of new 5G wireless interfaces based on massive multiantenna transmission and beamforming is expected to have a significant impact on the complexity and power consumption of the transport network. This paper analyzes the energy performance of four radio access network (RAN) architectures, each one utilizing a different option for splitting the baseband processing functions. The radio segment is based on Long-Term Evolution (LTE) and 5G radio access technologies. The transport segment is based on optical wavelength division multiplexing, where coherent and direct detection transmissions are considered. The energy consumption of each RAN architecture is weighted against i) the benefits for the radio segment as a function of the level of centralization of the baseband processing functions and ii) the power consumption levels needed to accommodate the capacity generated at each base station. Results show that, with LTE radio interfaces, the energy consumption of the transport network amounts to only a few percent of the overall network power consumption. As a result, fully centralized LTE radio architectures are a viable option, with energy savings of at least 27% compared with conventional distributed architectures. On the other hand, with advanced 5G radio interfaces, centralized architectures, if not carefully designed, might become impractical due to the excessive energy consumption of the transport network (i.e., as a result of the huge capacity to be accommodated). This aspect can be mitigated via a careful joint design of the radio and the transport network (i.e., leveraging on appropriate optical transmission techniques and compromising where needed on the radio network performance).

Increasing bandwidth demand drives the need for next-generation optical access (NGOA) networks that can meet future end-user service requirements. This paper gives an overview of NGOA solutions, the enabling optical access network technologies, architecture principles, and related economics and business models. NGOA requirements (including peak and sustainable data rate, reach, cost, node consolidation, and open access) are proposed, and the different solutions are compared against such requirements in different scenarios (in terms of population density and system migration). Unsurprisingly, it is found that different solutions are best suited for different scenarios. The conclusions drawn from such findings allow us to formulate recommendations in terms of technology, strategy, and policy. The paper is based on the main results of the European FP7 OASE Integrated Project that ran between January 1, 2010 and February 28, 2013. 

The fifth generation (5G) mobile communications system is envisioned to serve various mission-critical services such as industrial automation, cloud robotics, and safety-critical vehicular communications. To satisfy the stringent end-to-end latency requirement of these services, fog computing has been regarded as a promising technology to be integrated into 5G networks, in which computing, storage, and network functions are provisioned close to end users, thus significantly reducing the latency caused in transport networks. However, in the context of fog-computing-enabled 5G networks, the high mobility feature of users brings critical challenges to satisfy the stringent quality of service requirements. To address this issue, service migration, which transmits the associated services from the current fog server to the target one to follow the users' travel trace and keep the service continuity, has been considered. However, service migration cannot always be completed immediately and may lead to a situation where users experience a loss of service access. In this regard, low-latency service migration plays a key role to reduce the negative effects on services being migrated. In this paper, the factors that affect the performance of service migration are analyzed. To enable low-latency service migration, three main enabling technologies are reviewed, including migration strategies, low-latency, and high-capacity mobile backhaul network design, and adaptive resource allocation. Based on a summary of the reviewed technologies, we conclude that dynamic resource allocation is the worthiest one to research. Therefore, we carry out a use case, where reinforcement learning (RL) is adopted for autonomous bandwidth allocation in support of low-latency service migration in a dynamic traffic environment and evaluate its performance compared to two benchmarks. The simulation demonstrates that the RL-based algorithm is able to self-adapt to a dynamic traffic environment and gets converged performance, which has an obviously smaller impact on non-migration traffic than the two benchmarks while keeping the migration success probability high. Meanwhile, unlike the benchmarks, the RL-based method shows performance fluctuations before getting converged, which may cause unstable system performance. It calls for future research on advanced smart policies that can get convergence quickly, particularly for handling the migration of latency-sensitive services in 5G transport networks. 

Fog computing is expected to be integrated with communication infrastructure, giving rise to the con­cept of fog-enhanced radio access networks (FeRANs) to support various mission-critical applications. Such archi­tecture brings computation capabilities closer to end users, thereby reducing the communication latency to access ser­vices. In the context of FeRAN, service migration is needed to tackle limited resources in a single fog node and to pro­vide continuous service for mobile end users. To support service migration, high capacity and low latency are required in mobile backhaul networks. Passive optical net­works can be a promising solution for such mobile back-haul, in which bandwidth is shared by both migration traffic and that which is not associated with service migra­tion. In this paper, we propose a bandwidth slicing mecha­nism, in which the bandwidth can be provisioned to the migration traffic and non-migration traffic dynamically and effectively to meet their different delay requirements. Simulation results verify that the proposed delay-aware bandwidth slicing scheme can handle the migration traffic properly, i.e., sending it within a required time threshold, while limiting the impact of the migration traffic on the latency and jitter of the non-migration traffic, particularly that with high priority.

Evolution of optical access networks promises to bring higher bandwidth to more customers. However, this evolution toward so-called next generation optical access (NGOA) networks also introduces additional challenges that operators and/or vendors have to address: how to properly estimate and compare different NGOA architectures and their evolutionary paths in terms of their economics. Calculating the total cost of ownership (TCO) for NGOA networks is a very complex target as it needs to involve good knowledge of the technology, the existing network infrastructure, and any migration-related processes. In this paper a complete methodology is presented for evaluating the TCO of the migration toward a NGOA network. It contains a detailed description of which key aspects have to be considered, which processes they affect, and how they are translated into costs in a logical manner. Finally, it also shows how this methodology has been applied to particular selected cases and how it gives a detailed view of all costs involved in migration. This approach opens up opportunities to cooperate in techno-economic research using it as a base. Both operators and vendors can also utilize this approach to get a useful economic background of their future investments and potential sales.

In this paper, we  report on a gigabit capacity fiber-wireless system that enables smooth integration between high-speed wireless networks and dense wavelength-division-multiplexing   (DWDM) access   net- works. By employing a centralized optical frequency comb, both the wireline the wireless services for each DWDM user can be_x000D_ simultaneously supported. Besides, each base- bchannel can be transparently upconverted to multiple radio-frequency (RF) bands  for different  wireless stan- dards, which can be flexibly filtered at the end user to select the on-demRF band, depending on the wireless applications. For demonstration, we   transmit a 2.5 Gbit/s signal through the proposed system successfully achieve  a  bit-error-rate  (BER) performance  well below the 7%  overhead forward error correction limit of   the BER of 2×10-3 for both the wireline the wireless signals in the 60 GHz bafter 25 km single-mode fiber plus up to 6 m  wireless distance._x000D_

In this paper, we report on a gigabit capacity fiber-wireless system that enables smooth integration between high-speed wireless networks and dense wavelength-division-multiplexing (DWDM) access networks. By employing a centralized optical frequency comb, both the wireline and the wireless services for each DWDM user can be simultaneously supported. Besides, each baseband channel can be transparently upconverted to multiple radio-frequency (RF) bands for different wireless standards, which can be flexibly filtered at the end user to select the on-demand RF band, depending on the wireless applications. For demonstration, we transmit a 2.5 Gbit/s signal through the proposed system and successfully achieve a bit-error-rate (BER) performance well below the 7% overhead forward error correction limit of the BER of 2 x 10(-3) for both the wireline and the wireless signals in the 60 GHz band after 25 km single-mode fiber plus up to 6 m wireless distance.

With the advent of 5G, fixed wireless access (FWA) has emerged as a promising candidate for rolling out fixed broadband services. By means of radio simulations, we define a 5G radio deployment scenario for FWA that can meet the service requirements of future fixed broadband access. Different transport requirements imposed by different radio access network (RAN) split options are considered and a broad range of optical transport technologies/systems to support the FWA scenario is analyzed. For higher-layer RAN split options, we find that conventional 10G passive optical networks (XG-PONs) and coarse wavelength-division multiplexing (CWDM) technologies are the most cost effective. CWDM provides improved support for low-latency services while XG-PON facilitates future migration to fiber to the home. For lower-layer RAN splits, point-to-point (PtP) fiber or PtP-WDM is required. In the considered scenario, CWDM and PtP technologies are found to be the most cost effective.

We introduce a new transponder type for optical networks called an autonomous intelligent transponder (AIT). It is capable of autonomously adapting transmission parameters to the quality of the link over which it is transmitting. This concept fills one of the main gaps toward the realization of flexible, aware optical networks. We present experimental results to validate the AIT concept as part of a field trial in Telia Carrier's live optical European backbone network. 

Active optical networks (AONs) have been one of the most deployed fiber access solutions in Europe. However, with the increasing traffic demand, the capacity of the existing AONs is becoming insufficient. For the legacy AONs, there are two major variants of architectures, namely, point-to-point and active star. Considering the different characteristics of these two AON architectures, this paper proposes and analyzes several migration paths toward next-generation optical access (NGOA) networks offering a minimum 300 Mbit/s sustainable bit rate and 1 Gbit/s peak bit rate to every end customer. Furthermore, this paper provides detailed descriptions of the network cost modeling and the processes for AON migration. The total cost of ownership (TCO) is evaluated for the proposed migration paths, taking into account different migration starting times, customer penetration, node consolidation, and business roles in the fiber access networks. The migration from AON to NGOA can be economically feasible. The results indicate that a network provider plays a key business role and is responsible for the major part of the TCO for AON migration. Moreover, performing node consolidation during AON migration can be beneficial from a cost point of view, especially in rural areas.