This paper investigates the impact of wavelength/waveband convertors in hierarchical optical path networks. It shows that even if their costs are relatively high, hierarchical optical path networks can be cost effective over a wide traffic demand area.
We analyze cost reductions possible with the introduction of a waveband converter or both wavelength and waveband converters to hierarchical optical path networks. We propose network design algorithms that are based on multistage integer linear programming (ILP) or heuristics. Numerical experiments prove that by employing waveband converters or both waveband and wavelength converters, hierarchical optical path networks can be cost effective over wide traffic demand ranges and a broad converter cost range.
The emergence of fog computing has brought unprecedented opportunities to many fields, and it is now feasible to incorporate deep learning at the edge to facilitate the development of pervasive systems (e.g., autonomous driving and smart grids). In this paper, we present our preliminary research on a democratic learning scheme so that fog nodes could collaborate on the model training process even without the support of the cloud, which is urgently needed in the pervasive computing context. The main objective of this work is to utilize the deployed fog nodes to train a well-performed deep learning model together, even with the limited local data from each participant. Instead of relying on the cloud by default, we design a voting strategy so that a fog node could be elected as the coordinator based on both distance and computational power metrics to help expedite the training process. We then experiment the effectiveness of the scheme through a real-world, in-door fog deployment and verify the performance of the trained model through a human moving trajectory tracking use case.
Fog computing is an emerging architecture for bringing processing, storage, and control from the Cloud closer to the Things/Users. Fog has mostly been studied in the vertical continuum between the Things/Users and the Cloud to provide resources traditionally existing in the remote Cloud to the applications. This paper introduces ICN-Fog, a novel horizontal Fog-to-Fog layer enabled by Information-Centric Networking. ICN-Fog enriches applications with horizontal data transfer in the Fog layer, distributed processing among Fog nodes, and built-in mobility support thanks to the smart connectionless name-based Fog-to-Fog data communications. We explain the rationale behind our design and demonstrate the advantages of the proposed Fog architecture through two representative case studies.
We investigate a dynamic spectrum defragmentation scheme and a mitigation technique of bitrate dependent blocking rate for our recently proposed semi-flexible grid networks. The results verify the networks effectiveness compared with conventional flexible grid networks.
Wireless sensor networks (WSNs) are playing an increasingly important role in monitoring massive sensors to precisely detect anomalous phenomena, including anomalous events and sensor data faults. Prior studies preferred to dig the event anomaly (e.g., hotspots in a room), while sensor data faults were simply regarded as noise. Considering that different anomalies arise for different reasons, some substantial hidden problems such as internal sensor failures may be ignored. In this study, we propose an efficient data processing scheme using machine learning model with the objective of achieving satisfactory anomaly detection performance during WSN monitoring. Our proposal analyzes the difficulty of detecting different types of fault data and the influence of each type on event detection results. The machine learning model is adopted to analyze the sensor data correlation, to achieve satisfactory performance for both event detection and fault detection by analyzing the correlated sensor data. At each monitoring time during the data monitoring process, the trivial sensor data faults that might affect the event detection results are filtered out before executing event detection. Meanwhile, at much longer monitoring time intervals, random fault detection is performed to find potentially hidden failures of sensors. Numerical experiments conducted in a real WSN environment show that neural network model outperforms other machine learning models in anomaly detection, and the results by adopting neural network model verify the feasibility of our proposed scheme which attains acceptable performance in detecting both types of anomalies.
We propose a novel elastic optical path network where each specific bitrate signal uses its own dedicated fixed grid and a slot-width-edge anchor frequency. Numerical evaluations verify that the proposed networks can almost match the performance of conventional flexible grid networks, while allowing tunable filters to be used in a fixed grid system.
Building Energy Management System (BEMS) is a vital approach in constructing a global energy-efficient environment. It can be operated by analyzing data collected from sensors located in designated indoor areas. The key is to improve the data processing results while reducing the total data processing/communication volume required in the whole Internet of Things (IoT) networks as much as possible. In this work, a novel in-network self-learning algorithm for BEMS through a collaborative Fog platform is proposed. In particular, we devise an emerging Fog computing enabled IoT network architecture, where most of data can be processed in the Sensor-to-Fog and Fog-to-Fog layers. Data processing on Cloud is only required if anomalous sensor data are detected, and thus, the energy consumption due to heavy data processing on Cloud will be significantly reduced. The proposed algorithm makes the best use of Fog node capability to realize distributed data collection and processing. Via Fog-to-Fog connections, it can examine the sensor data by collecting them from different search ranges, whose values are meanwhile optimized. Numerical experiments conducted in a real indoor environment demonstrate that our algorithm achieve a high prediction accuracy for anomaly detection even with relatively small sensor data for processing. The effectiveness of Fog node placement is also verified. The overall scheme is expected to be a feasible solution to construct a cost-effective IoT network to minimize energy consumption while maximizing the indoor user's comfort, from the perspective of achieving a high prediction accuracy in BEMS data monitoring.
Building energy management systems (BEMSs) have been successfully adopted as key control units for modern structures to maintain energy efficiency and provide a comfortable thermal environment for occupants. Recent advances in information and communication technology toward "Industry 4.0" are enhancing the utility of BEMSs. However, challenges, such as how to process the exponentially growing amount of heterogeneous data generated in buildings, need to be addressed to realize "Building 4.0," which encompasses next-generation smart systems that provide user-centric services. In this article, we propose BEMS–Edge, a framework that integrates seamless, real-time information acquisition, transmission, interpretation, and action in intelligent BEMSs. The primary components, including the Internet of Things (IoT), cloud/edge computing, big data analytics, and artificial intelligence (AI), converge to create a data-driven edge computing fabric offering a range of benefits, such as real-time data analytics and cost savings. The effectiveness of BEMS–Edge is verified by an established, real-world BEMS testbed.
'/%3e%3c/defs%3e%3cpath fill='%23012169' d='M0 0h10080v5040H0z'/%3e%3cpath stroke='%23fff' stroke-width='.6' d='m0 0 6 3m0-3L0 3' clip-path='url(%23b)' transform='scale(840)'/%3e%3cpath stroke='%23e4002b' stroke-width='.4' d='m0 0 6 3m0-3L0 3' clip-path='url(%23c)' transform='scale(840)'/%3e%3cpath stroke='%23fff' stroke-width='840' d='M2520 0v2520M0 1260h5040'/%3e%3cpath stroke='%23e4002b' stroke-width='504' d='M2520 0v2520M0 1260h5040'/%3e%3cg fill='%23fff'%3e%3cuse xlink:href='%23d' x='2520' y='3780'/%3e%3cuse xlink:href='%23a' x='7560' y='4200'/%3e%3cuse xlink:href='%23a' x='6300' y='2205'/%3e%3cuse xlink:href='%23a' x='7560' y='840'/%3e%3cuse xlink:href='%23a' x='8680' y='1869'/%3e%3cuse xlink:href='%23e' x='8064' y='2730'/%3e%3c/g%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
