The existing wireless-optical switching units comprise spatial light modulators (SLM) and micro-electromechanical systems (MEMS), which steer the beam from a server port in a certain rack to another rack, establishing an inter-rack communication link. Nevertheless, this uni-cast communication approach results in a limited switching capacity. Fortunately, our passive reflective meta-surfaces (RMSs) demonstrate excellent beam-splitting capabilities, that is, after an incident light is reflected by our RMS, a pair of reflected beams can be simultaneously formed. In this paper, we further design a transmissive meta-surface (TMS), and after one incident light transmits through the TMS, N beams can be formed. Each of the N beams is subsequently reflected by the corresponding RMS, and ultimately, we can obtain 2×N beams. As a result, it significantly enhances the switching capacity of data centers (DCs). Simulation results validate the one-to-four (N=4) beam-splitting capacity of our TMS, with the insertion loss being as low as 0.5dB, efficiently being cascaded with RMS.

The three-dimensional Network-on-Chips (3D NoCs) has become a mature multi-core interconnection architecture in recent years. However, the traditional electrical lines have very limited bandwidth and high energy consumption, making the photonic interconnection promising for future 3D Optical NoCs (ONoCs). Since existing solutions cannot well guarantee the fault-tolerant ability of 3D ONoCs, in this paper, we propose a reliable optical router (OR) structure which sacrifices less redundancy to obtain more restore paths. Moreover, by using our fault-tolerant routing algorithm, the restore path can be found inside the disabled OR under the deadlock-free condition, i.e., fault-node reuse. Experimental results show that the proposed approach outperforms the previous related works by maximum 81.1 percent and 33.0 percent on average for throughput performance under different synthetic and real traffic patterns. It can improve the system average optical signal to noise ratio (OSNR) performance by maximum 26.92 percent and 12.57 percent on average, and it can improve the average energy consumption performance by 0.3 percent to 15.2 percent under different topology types/sizes, failure rates, OR structures, and payload packet sizes.

Optical switching has been investigated for a long time, as a possible effective solution to overcome the limitations of power consumption, footprint and scalability in data center networks (DCNs). However, with the increasing DC traffic and narrow channel spacing between wavelengths for optical interconnects, traditional single-mode and multi-waveguide optical switching solutions have encountered bandwidth bottlenecks. To this end, we propose a 2×2 silicon-based on-chip optical switching architecture compatible with hybrid wavelength-andmode division multiplexing (WDM-MDM), and it is found experimentally that the proposed design increases the bandwidth 8× times with low crosstalk.

The automated diagnosis helps us better understand the complex landscape of diseases, leading to more effective, early and reliable medical diagnosis and therapy. The human-machine interactions in healthcare delivery relying on automated cyber-physical systems (ACPSs) play an important role in the automated diagnosis. Currently, the multicore accelerator used for ACPS has utilized the network-on-chip (NoC) for personalized healthcare. However, the discrete cores based on NoC are affected by limited computation speed, since the data have to pass through an electrical interconnect. In this paper, we propose a novel optical NoC (ONoC) solution of designing discrete cores to quickly understand biomarkers for early detecting abnormal pathophysiology, such as the deviation from the protein's native state. We analyze the performance of our ONoC-based ACPS accelerator for personalized healthcare by virtue of the tested proteins widely adopted in the lattice protein model. Our mathematical analysis and simulation results demonstrate that: 1) the chip area becomes smaller than a traditional design, which makes the personalized healthcare product more convenient; 2) the computation speed is promoted, resulting in the rapid understanding of biomarkers; and 3) we improve the data transmission reliability through accurately capturing the photonic effect so that desirable human-machine interactions can be guaranteed. Note to Practitioners-We design an on-chip hardware accelerator for automated diagnosis and personalized healthcare by predicting biological protein folding. The simulation results based on the lattice protein model can well guide the practitioners to design a more convenient and reliable product quickly detecting the biomarker, such as the deviation from the protein's native state.

The peer-to-peer energy trading has been achieved among nodes in industrial Internet of Things. To establish a secure private market, some meaningful works propose the concept of the energy chain, where one block is added in a linear and chronological order once the trading pair of nodes (buyer and seller) has a valid transaction verified by data audit (e.g., a hash value). Since the buyer applies virtual coins from the credit bank to buy others' surplus energy, a considerable credit utility is obtained if all nodes are encouraged to meet local power loads out of self-interest. However, such frequent transactions have huge operational overhead, including a long chain maintaining many blocks and an expensive energy transportation cost between trading pairs. To solve these challenging issues, our method enables nodes to satisfy their power loads through local stored energy (self-sufficiency), before participating as sellers if they still have considerable surplus electricity. Without transactions made by some self-sufficient nodes, the operational overhead can be mitigated in a more secure environment. Taking the classic Internet of energy as a case study, we demonstrate the effectiveness of our solutions, and it can achieve a good tradeoff between credit utility and operational overhead.

Performing virtualization can further improve the infrastructure utilization of Inter-Data-Center Optical Networks (IDCONs). In virtualized IDCONs, a service requestor subscribes one lightpath for transferring the virtual machine to the specific server in the destination DC. However, the infrastructure overload leads to the denial of services. Thus, we design a novel service degradability (well-intentioned service degradation) framework, in order to minimize the number of service requirements declined by overloads, resulting in the maximal utility of the IDCON provider. We mathematically formulate the problem and determine the most appropriate degradation degree based on microeconomic theory. For heuristic algorithms, the availability-aware bandwidth degradability policy is invoked once there is the optical backbone overload; while for the server overload in DCs, the application-specific virtual machine degradability policy is considered. Finally, the simulation results demonstrate the effectiveness of our heuristic algorithms, and the optimal combination of degradation coefficients is achieved by microeconomic theory and LINGO.

Nowadays, owing to the advantages of high bandwidth and low power consumption, the wired optical network-on-chip (W-ONoC) has emerged as a high-performance on-chip communication solution. However, the W-ONoC suffers from increased latency and limited scalability since the multi-hop data transmission is frequently performed in wired structures. In addition, several problems such as photoelectric conversion and thermal sensitivity pose challenges to the design of WONoCs. In this paper, we develop a novel on-chip communication architecture based on free-space optics (FSO), and leverage a suite of emerging devices. The proposed architecture eliminates the power loss caused by the waveguide and microring resonator previously deployed in W-ONoCs, and the transmission latency is also reduced through simplifying the packet switching. Moreover, compared with the traditional single-layer FSO NoC, our 3D FSO NoC further decreases the number of consumed lasers and power. Extensive simulation results demonstrate the aforementioned advantages of our solution.

Due to the heterogeneous and resource-constrained characters of Internet of Things (IoT), how to guarantee ubiquitous network connectivity is challenging. Although LTE cellular technology is the most promising solution to provide network connectivity in IoTs, information diffusion by cellular network not only occupies its saturating bandwidth, but also costs additional fees. Recently, NarrowBand-IoT (NB-IoT), introduced by 3GPP, is designed for low-power massive devices, which intends to refarm wireless spectrum and increase network coverage. For the sake of providing high link connectivity and capacity, we stimulate effective cooperations among user equipments (UEs), and propose a social-aware group formation framework to allocate resource blocks (RBs) effectively following an in-band NB-IoT solution. Specifically, we first introduce a social-aware multihop device-to-device (D2D) communication scheme to upload information toward the eNodeB within an LTE, so that a logical cooperative D2D topology can be established. Then, we formulate the D2D group formation as a scheduling optimization problem for RB allocation, which selects the feasible partition for the UEs by jointly considering relay method selection and spectrum reuse for NB-IoTs. Since the formulated optimization problem has a high computational complexity, we design a novel heuristic with a comprehensive consideration of power control and relay selection. Performance evaluations based on synthetic and real trace simulations manifest that the presented method can significantly increase link connectivity, link capacity, network throughput, and energy efficiency comparing with the existing solutions.

In sharing economy, people offer idle social resources to others in a sharing manner. Through community-based online platforms, the people offering services can earn commission while others can enjoy a better life via renting social resources. Consequently, the value-in-use of services is expectedly strengthened within the unit time, although the total amount of social resources remains constant. Influenced by sharing economy, some famous companies have developed intelligent systems to analyze the most appropriate coincidence between citizens' idle supply and renting demand from numerous data sets. However, the big data analysis of the optimal service-demand matching usually runs on the traditional multiprocessors equipped in intelligent systems, so-called “system-on-chip.” In this paper, we design a novel computer architecture - the accelerator based on optical network-on-chip (ONoC) - to further speed up the matching between citizens' offer and demand in sharing economy. Our ONoC-based accelerator is able to quickly calculate the optimal service-demand matching by processing computation tasks on parallel cores, i.e., task-core mapping. In addition, to improve the accelerator reliability, the assorted task-core mapping algorithm is also designed. The extensive simulation results based on real trace file demonstrate the effectiveness of our system and algorithm. Note to Practitioners - Sharing economy is of great importance for realizing green consumption and sustainable development in our human society. Sharing economy enterprise calls for intelligent system design for service-demand matching in the current big data era. In this paper, we design the accelerator based on ONoC to further speed up the matching between citizens' offer and demand in sharing economy. By processing computation tasks on parallel cores using our algorithm, the task-core mapping can be performed with high speed and reliability. The simulation results - based on the trace file of Amazon Mechanical Turk - can well guide the practitioners to design a more clever and reliable product by quickly calculating the optimal service-demand matching.

As an integrated environment deployed with wired and wireless infrastructures, the smart city heavily relies on the wireless-optical broadband access network. The information flows captured by indoor devices are sent to optical network units through front-end wireless mesh sensor networks (WMNs) and, finally, reach the optical line terminal for industrial/commercial decision making via the passive optical network backhaul. To reduce the backhaul bandwidth saturated by this conventional approach, edge devices are deployed at the front-end WMN to preprocess information flows. Based on collaborative edge computing, home users or factory workers customize their computing services as virtual networks embedded onto the common WMN. In this paper, we propose the green survivable virtual network embedding for the collaborative edge computing in smart cities. We mathematically formulate the problem and derive the corresponding bound. Extensive simulations with real traces demonstrate the algorithm effectiveness.

Internet of Things (IoT) devices have different operation principles, which weakens the data interoperability. Virtualization is an economic way of solving this problem. The data-collected by different vendors' sensors-share the same computing program encapsulated by the virtual machine (VM), so that the physical-layer difference can be hidden. To eliminate the extra cost and long delay of transferring VMs to the remote cloud, the edge device (ED) processes local VMs' requirements in prior. Hence, the sustainable strategy for recycling EDs is an important way to safeguard the network sustainability. To improve the recycling efficiency, most of the EDs should be upgraded simultaneously during one batch by migrating their local VMs to others for the service continuity. We investigate the least upgrade batch for recycling EDs in IoT networks. A two-step algorithm called minimized upgrade batch VM scheduling and bandwidth planning (MSBP) is designed to minimize the number of upgrade batches. As the frequent VM migration brings the bandwidth consumption and contention of trajectories, in our MSBP, two strategies: 1) shortest trajectory first and 2) least bandwidth utilization first (LBUF), are also considered. The simulation results show that: 1) MSBP has the optimal recycling efficiency (least number of upgrade batches) for EDs and 2) LBUF more effectively mitigates the negative impact of the path contention level on the recycling efficiency.

To make full use of space/air resources, a Space-Air Integrated Network (SAIN) which is a hierarchical network with satellites, airships and hovering Unmanned Aerial Vehicles (UAVs) is constructed. Nowadays, Free Space Optical (FSO) links have been widely applied in SAINs since they provide high-rate and large-capacity data transmission. Unfortunately, the FSO links across the atmosphere would perform badly in adverse weather. Besides, the limited number of transceivers brings bottlenecks of link capacity and node energy. To solve these problems, in this paper, we first propose an adaptive RF/FSO switching mechanism based on predictions of atmosphere conditions, so that the high- rate and large-capacity data transmission can be achieved while overcoming the negative influences of bad weathers. Moreover, under the limited number of transceivers, we design a Dynamic Energy & Traffic Balance (DETB) topology control algorithm. Except for transmit power, both residual bandwidth and energy are taken into account for obtaining an optimal topology dynamically. Finally, a hierarchical routing policy combined with our DETB algorithm is proposed. It has been proved that our method extends the network lifetime, and the network throughput remains stable.

An integrated space/air information network is a convergence of satellite communication networks in space regions and aircraft communication networks in air regions. It supports direct internal information interactions. Along with the extensive application of the integrated space/air information network especially in military fields, its routing problem becomes a key point of research. However, the existing routing algorithms are mainly designed for the space or air region separately and there is little study on the generalized routing for the integrated space/air information network. In this paper, we propose a Hybrid time-space Graph based Hierarchical Routing (HGHR) scheme for this integrated network. The hybrid time-space graph includes two subgraphs: a deterministic one and a semi-deterministic one. As satellite orbits are pre- known in the space region, we introduce a deterministic time-space subgraph. While each aircraft has a cyclic movement with the predictable contact probability and contact time in the air region, we construct a semi-deterministic time-space subgraph according to the prediction results of a discrete time homogeneous semi-Markov model. Simulation results show that HGHR has good performance in terms of data delivery ratio and end- to-end delay.

In a many-to-many session, a participant distributes and receives traffic flows to/from all others in the same session. It is desirable to achieve the high resource utilizations and low energy consumptions when we provision such sessions. In the Wavelength-Division-Multiplexing (WDM) optical network, traffic grooming has been widely applied as the key technology for the routing and aggregation of sessions due to the high resource utilizations. However, the current many-to-many grooming approaches, whether the lightpath circle or the hubbed light-tree, do not make effort on reducing energy consumptions of many-to-many sessions. In this paper, we formulate the “Green Routing and Aggregation of Many-to-Many Sessions (GRAMMS)” problem. For the problem solving, we propose a novel heuristic that applies a rational combination of lightpaths in green WDM optical networks. We further give an illustrative comparison between our heuristic and existing approaches in terms of energy savings. Extensive simulation results demonstrate that, compared to benchmark approaches, our heuristic can achieve much higher energy efficiency.

With the increasing of number of multimedia network applications, multi-cast services are becoming more and more popular. At the same time, the waveband switching technique is proposed to save ports and to reduce the cost of optical cross-connect. However, the existing multi-cast waveband grooming algorithms are mostly limited to single-domain optical networks. The size of optical backbones keeps enlarging, and the backbones are actually divided into multiple independent domains to provide the needed scalability and confidentiality. To solve these problems, the authors propose three heuristic algorithms: per-domain multi-cast grooming (PDMG), virtual topology multi-cast grooming (VTMG) and hierarchical multi-domain multi-cast grooming (HMMG). The main difference between these algorithms is that the inter-domain routing is performed in a different manner; in other words, the routings in PDMG, VTMG and HMMG are computed based on the domain-by-domain fixed routing table, the high layer in the aggregative virtual topology of multi-domains and the hierarchical integrated multi-cast auxiliary graph, respectively. For the intra-domain routing, the three algorithms employ the same method based on an intra-domain multi-cast integrated auxiliary graph. Simulation results show that compared with PDMG and VTMG, HMMG has the best performance in terms of the number of ports saved and the blocking probability.

Since current optical network is actually divided into multiple domains each of which has its own network provider for independent management, the development of multi-domain networks has become the trend of next-generation intelligent optical networks, and then the survivability has also become an important and challenging issue in fault-tolerant multi-domain optical networks. In this paper, we study protection algorithms in multi-domain optical networks and propose a new heuristic algorithm called multi-domain Hamiltonian cycle protection (MHCP) to tolerate the single-fiber link failure. In MHCP, we present the local Hamiltonian cycle (LHC) method based on the physical topology of each single-domain and the global Hamiltonian cycle (GHC) method based on the abstracted virtual topology of multi-domains to protect the intra-fiber link and inter-fiber link failures, respectively. We also present the link-cost formulas to encourage the load balancing and proper links selection for computing the working path of each connection request. Simulation results show that, compared with previous multi-domain protection algorithm, MHCP can obtain better performances in resource utilization ratio, blocking probability, and computation complexity.