Distributed Network Autoscaling With Hardware-Independent App Deployment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network solutions are inflexible due to proprietary hardware and software, limiting network operators' ability to add new features or capabilities, leading to time-consuming and resource-intensive standardization processes.
Innovation Solution
A Distributed Software Defined Network (dSDN) architecture that enables secure and flexible programmability across networks, allowing for the deployment of distributed applications through a virtual fabric, with lifecycle management and authentication, using a programmable network device and cloud device powered by a sandboxing operating system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If proprietary hardware and software are used in existing network solutions, then network infrastructure can be provided by vendors, but network operators cannot add new customized features or capabilities without time-consuming standardization processes
Solution Approach 1:
The network application is divided into multiple container images that can be independently deployed and managed. Each container image represents a modular unit of functionality that can be added, updated, or removed without affecting the entire network infrastructure, enabling rapid customization without lengthy standardization processes
Solution Approach 2:
The network device is designed to host multiple different network applications through containerization technology, making it capable of performing various network functions through software rather than requiring dedicated hardware for each function. This universal platform allows network operators to deploy customized features by simply loading appropriate container images
2Adaptability or versatility
If distributed applications are deployed across network devices and cloud devices, then network functionality and scalability are enhanced, but system complexity increases
Solution Approach 1:
A container management system acts as an intermediary layer between the distributed applications and the underlying hardware infrastructure. This management system handles deployment, configuration, monitoring, and lifecycle management of container images across network devices and cloud devices, abstracting away the complexity from operators while enabling distributed deployment
Solution Approach 2:
Container images are copied and distributed across multiple network devices and cloud devices, creating consistent replicated instances of applications. This copying mechanism enables scalable deployment while maintaining system consistency through centralized image management and version control
3Productivity
If network applications are upgraded, then new features and improvements are deployed, but operational interruptions may occur
Solution Approach 1:
Container images are prepared, validated, and staged in advance before deployment to network devices. The management system performs pre-checks and preparations, allowing upgrades to be applied atomically or in a controlled sequence that minimizes service disruption and maintains operational reliability during feature deployment
Data Source
AI summary
Techniques are disclosed for automatically adjusting the number of application instances in a distributed software-defined network based on dynamic resource usage. A distributed resource service (dRS) monitors usage metrics such as CPU utilization, memory usage, or request rate associated with fxDeviceApp and fxCloudApp components of a distributed application. When usage exceeds or falls below defined thresholds, the dRS initiates deployment or removal of execution environments—such as containers or virtual machines—hosting the respective application components. Secure communication tunnels are established between the newly deployed instances and other components using a virtual messaging fabric, and routing data in a flow information base is updated accordingly. The system supports zone-based and component-specific scaling, policy-governed traffic assignment through switch controllers, and enforcement of security and access control through cryptographically signed identities and validated certificates. These capabilities enable adaptive, policy-driven autoscaling of applications across distributed network and cloud infrastructure.


