۱- Introduction

۲- Related work

۳- Network architecture and problem description

۴- Heuristic algorithms and routing applications

۵- Experimental demonstration and results discussion

۶- Conclusion and future work

References

Abstract

With the increasing conflict between population growth and limited environmental resources, building intelligent and efficient data transmission networks is crucial to cleaner production in smart and sustainable cities. More and more people are eager to exchange all kinds of information in urban life through an efficient network. Therefore, designing a smart data distribution and transmission mechanism can not only improve people’s quality of life but also pave the way for reducing environmental pollution. Optical networks have been widely used in the core network due to high-capacity characteristics. However, in inter-data-center (Inter-DC) optical networks, the coexisted heterogeneous optical devices and multi-granularity network resources bring new challenges to network management and traffic scheduling. Recently, software-defined network (SDN) and network function virtualization (NFV) have been introduced to enable the unified control for improving network agility and automation. Thus for software-defined multi-granularity Inter-DC optical networks, we propose a list of online service provisioning strategies. Moreover, in terms of the network controller, the novel routing applications are also developed by extended OpenFlow protocol. Finally, we experimentally demonstrate the overall feasibility of proposed solutions in a semi-practical platform. Numerical simulations conducted to quantitatively evaluate the algorithm efficiency also verify the superiorities of improving spectrum efficiency and reducing service blocking probability.

Introduction

Cleaner production is a new and creative idea that continuously takes an overall preventive environmental strategy for production processes and products to reduce their potential hazards to humans and the environment (D. Mark et al. (2018); Y. Fan et al. (2018); H. Shahhosseini et al. (2018)). With the continuous development of human society, the future city will carry more and more people. The increase in population will increase the waste of resources and environmental pollution in cities. Smart cities use information and communication technologies to sense, analyze, and integrate key information in the core systems of urban operations, thereby responding intelligently to the various needs of human activities, aiming to promote sustainable urban development and reduce environmental pollution. Meanwhile, the rapid update of new technologies has injected a large amount of data into the network, especially in 5G (C. Wang et al. (2014)), Internet of Things (IoT) (P. Ramezani et al. (2017)) and smart phone applications (W. Hou et al. (2018a)). The birth of big data (L. Cui et al. (2016); W. Hou et al. (2017b)) further promotes the development of cloud computing (Y. Yin et al. (2017); L. Guo et al. (2018)) that provides users with a lot of computing resources at low investment. Especially, the combination of cloud computing and network function virtualization (NFV) have achieved temporal and spacial flexibilities of physical devices. However, as the size of server clusters continues to expand, cloud computing platforms consist of geographically dispersed data centers (DCs) (P. Lu et al. (2017); W. Hou et al. (2018b)) communicating with each other through fast and high-capacity optical networks. Inter-DC optical networks are equipped with heterogeneous devices and multigranularity resources, such as wavelength division multiplexing (WDM) and orthogonal frequency division multiplexing (OFDM) (L. Gong et al. (2014)). This paper focuses on designing efficient optical networks to serve data communication among data centers, aiming to explore solutions that contribute to smart and sustainable urban development.