The rapid expansion of global cloud infrastructures and increasing network traffic volume and dynamicity have led to a rise in research on developing scalable and resilient Traffic Engineering (TE) solutions for Wide Area Networks (WANs). Despite recent advancements, striking the right balance between network availability, computational complexity, and resource utilization remains a significant challenge.This paper presents empirical findings that highlight the inherent traffic demand imbalance and link utilization heterogeneity that current TE solutions have overlooked. We then define two new performance metrics, namely critical link set and network criticality, that jointly represent these heterogeneities. We further introduce an efficient extension to the tunnel-based resilient TE algorithm to be adaptive to traffic profiles. An extensive simulation study on representative WAN topologies demonstrates the substantial performance enhancements achieved by our holistic solution approach.

Developing a distributed controller system for pro-duction software defined networks (SDN) requires substantial en-gineering effort to satisfy the stringent performance, adaptability, availability and security requirements that are well beyond the basic function development. The softwarization nature of SDN provides the opportunity to leverage the recent advancements in software engineering and system automation. In this paper we present our recent work to develop and deploy a wide-area SDN control framework prototype towards production deployment and operation. We primarily focus on three critical areas (1) enhancement of the software functions and the substrate virtualization configurations to fully support advanced connection services and fault tolerance in both data plane and control plane (2) a high-fidelity testing pipeline con-sisting of unit tests emulation and a testbed and (3) a continuous integration and continuous deployment (CI/CD) pipeline. Our experience proved that the presented environment and process greatly increased the software quality and development efficiency which would ultimately lead to a reliable and continuous deploy-ment and automation of the targeted production SDN network.

Many scientific research communities and institutions are adopting the cloud as a primary platform to support their computing needs. Rapid adoption of the cloud for scientific computing is a result of the simplicity with which an individual researcher can obtain large amounts of customized compute and storage resources. At the same time, most public cloud providers have rolled out many advanced networking services. Many of these services, like their compute services, are simple to access by any cloud user (e.g. routing between regions and private networking spaces within a cloud). However, it is not possible for most researchers to access expensive low-level, externally facing cloud network services without complicated support by campus IT staff, as well as national and regional network providers. This paper describes how to use Chameleon, ExoGENI, and Internet2's Cloud Connect service to deploy research experiments that use AWS Direct Connect without requiring a privately owned Direct Connect endpoint or support from local campus IT staff.