Dynamic WAN Optimizer Instance Scaling for Workload Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional network engineering becomes impractical as workloads become more mobile and dynamic, requiring new mechanisms to adapt network infrastructure to changing loads, with no one-size-fits-all solution for load balancing and WAN optimization.
Innovation Solution
A system that dynamically and automatically adjusts WAN optimizer instances based on monitored traffic patterns, resource utilization, and compression history, switching load balancing schemes and resource allocation to optimize performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional discrete network appliances are deployed with fixed sizing, then deployment simplicity is maintained, but adaptability to dynamic workloads deteriorates
Solution Approach 1:
The patent implements dynamic adaptation of network accelerator instances by continuously monitoring workload characteristics and automatically adjusting the number and configuration of accelerator instances. The system transitions from static fixed-size deployments to dynamic configurations that adapt to changing traffic patterns, compression requirements, and peer optimizer states, thereby resolving the contradiction between deployment simplicity and adaptability.
Solution Approach 2:
The system employs self-service mechanisms where the network accelerator automatically monitors its own performance metrics, compression history fragmentation, and workload characteristics, then autonomously adjusts its configuration without manual intervention. This self-adaptation capability allows the system to maintain optimal performance across varying workload conditions while preserving operational simplicity.
2Device complexity
If a fixed number of WAN optimizer instances are provisioned, then resource allocation is simplified, but compression ratio performance deteriorates under varying workloads
Solution Approach 1:
The patent implements feedback mechanisms that continuously monitor compression history fragmentation, workload characteristics, and peer optimizer states. Based on this feedback, the system dynamically adjusts the number and configuration of accelerator instances to maintain optimal compression ratios. The feedback loop enables the system to respond to changing conditions and prevent compression history fragmentation, thereby maintaining high compression performance without fixed resource allocation.
Solution Approach 2:
The system dynamically changes operational parameters including the number of accelerator instances, instance sizing, and load balancing configurations based on monitored workload characteristics. These parameter adjustments allow the system to optimize compression performance for different traffic patterns and compression requirements, resolving the contradiction between allocation simplicity and compression performance.
3Ease of operation
If load balancing distributes traffic evenly across all instances, then simplicity is maintained, but performance under asymmetric workloads deteriorates
Solution Approach 1:
The patent implements load balancing strategies that apply different distribution rules to different peer optimizers based on their individual characteristics, traffic patterns, and compression history states. Rather than uniform distribution, the system tailors load balancing behavior to local conditions at each peer optimizer, optimizing performance for asymmetric workloads while maintaining manageable complexity through automated decision-making.
4Measurement precision
If manual configuration and monitoring is used, then control precision is maintained, but automation level deteriorates
Solution Approach 1:
The system implements self-service automation where the network accelerator autonomously monitors workload characteristics, compression performance, and peer optimizer states with high precision. The automated system makes intelligent decisions about instance provisioning, configuration, and load balancing based on monitored metrics, eliminating the need for manual configuration while maintaining or exceeding the precision of manual monitoring through continuous automated measurement and analysis.
Data Source
AI summary
Systems and methods of the present solution provide a more optimal solution by dynamically and automatically reacting to changing network workload. A system that starts slowly, either by just examining traffic passively or by doing sub-optimal acceleration can learn over time, how many peer WAN optimizers are being serviced by an appliance, how much traffic is coming from each peer WAN optimizers, and the type of traffic being seen. Knowledge from this learning can serve to provide a better or improved baseline for the configuration of an appliance. In some embodiments, based on resources (e.g., CPU, Memory, Disk), the system from this knowledge may determine how many WAN optimization instances should be used and of what size, and how the load should be distributed across the instances of the WAN optimizer.