Adaptive Cloud-Native Service Chaining via Probabilistic Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cloud-native environments face challenges in dynamically and efficiently delivering services in an ordered manner, particularly in optimizing the transit of packets through service chains.
Innovation Solution
An intelligent routing engine determines the order of processing workloads in a service chain based on likelihoods that a packet will terminate or be modified at each workload, using a prediction engine and/or policy evaluation engine to optimize computational costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a static service chain order is used in cloud-native environments, then service delivery is simple to implement, but it cannot dynamically optimize packet transit efficiency
Solution Approach 1:
The patent implements dynamic service chain reconfiguration by enabling the service chain to adapt its structure and ordering based on real-time workload characteristics and performance requirements. The system transitions from static configuration to dynamic adjustment, allowing service functions to be reordered or reconfigured according to changing conditions, thereby optimizing packet transit efficiency while maintaining manageable complexity through automated control mechanisms.
2Loss of energy
If packets are processed through all service workloads in a fixed order, then service completeness is ensured, but computational costs increase due to unnecessary processing
Solution Approach 1:
The system performs preliminary analysis of packet characteristics and service chain requirements before actual packet processing. By pre-determining the optimal service ordering based on workload analysis and packet type, the system可以避免不必要的处理步骤，从而降低计算成本，同时通过预先规划确保服务处理的完整性。
Solution Approach 2:
The patent implements selective service processing where not all services are applied to every packet. Based on packet classification and service affinity analysis, the system applies only the necessary subset of services required for that specific packet type, reducing unnecessary computational overhead while maintaining required service completeness through intelligent filtering and selection mechanisms.
3Ease of operation
If service workloads are distributed across separate containers, then service isolation and modularity are improved, but dynamic ordered service delivery becomes more difficult to implement
Solution Approach 1:
The patent implements a universal service chain management system that can handle multiple containerized services across different isolation boundaries. The system provides multi-functional capabilities including service discovery, dynamic ordering, and coordinated execution across distributed containers, thereby maintaining service isolation and modularity while enabling automated dynamic service delivery through a unified control plane that orchestrates multiple independent service containers.
Data Source
AI summary
Techniques for a computing resource network to send a packet through a processing flow (e.g., a service chain) according to an order of processing workloads (e.g., services) included in the processing flow, configured as an optimized service chain. In some examples, the computing resource network may include a policy evaluation engine configured to determine the best probabilistic outcome of an order of routing between the services that results in the lowest computational costs based on the probability that a given packet will be terminated/modified at one of the earlier processing workloads in the service chain, a prediction engine configured to determine the order of the processing workloads included in the processing flow based on a policy and/or telemetry data associated with the processing workloads, and/or an intelligent routing engine configured to route a packet between the one or more processing workloads included in a processing flow according to the order.