Cache Size Estimation for ICN Routers Using Request Entropy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In information centric networks (ICNs), determining an optimal cache size for cache routers is challenging due to varying request patterns and content popularity, which affects the efficiency of content delivery and Quality of Experience (QoE).
Innovation Solution
A method and system for estimating cache size in ICNs by determining the average rate of incoming requests, probability of request occurrence, and entropy of requests, using a tri-state Markov model to derive relations between cache hits and misses, and adjusting cache size based on user-defined probabilities and request patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cache size is increased to improve content delivery efficiency, then cache hit probability increases, but device complexity and memory resource consumption increase
Solution Approach 1:
The patent implements dynamic cache size adjustment by continuously monitoring cache hit/miss ratios and request patterns. The cache router adapts its cache size in real-time based on observed traffic characteristics, transitioning from static to dynamic configuration. This allows the system to optimize cache hit probability while avoiding excessive memory allocation during low-traffic periods.
Solution Approach 2:
The system changes key parameters including cache size, time interval duration, and probability thresholds based on observed request patterns. By dynamically adjusting these parameters rather than fixing them, the system resolves the contradiction between maintaining high cache hit probability and avoiding excessive cache size allocation.
2Loss of time
If cache size is increased to reduce content access delays, then Quality of Experience improves, but loss of substance increases due to cached content occupying memory
Solution Approach 1:
The patent applies partial action by caching only the most frequently requested content items rather than pre-caching all possible content. The system identifies and caches content based on observed request probabilities, allocating memory resources proportionally to actual demand. This avoids wasting memory on content that would not be accessed anyway.
Solution Approach 2:
The cache router autonomously monitors its own performance metrics (hit/miss ratios, request patterns) and automatically adjusts its caching strategy without external intervention. This self-service mechanism ensures memory resources are continuously optimized based on actual usage patterns, preventing both over-allocation and under-allocation of cache memory.
3Adaptability or versatility
If cache size is dynamically adjusted to adapt to changing traffic patterns, then adaptability improves, but device complexity increases due to monitoring and adjustment mechanisms
Solution Approach 1:
The system implements feedback loops where cache performance metrics (hit/miss ratios, request inter-arrival times) are continuously monitored and fed back to the cache management module. This feedback drives automatic adjustments to cache size and replacement policies, enabling adaptability through a relatively simple closed-loop control mechanism rather than complex predictive algorithms.
Solution Approach 2:
The cache router performs self-monitoring and self-adjustment of its cache configuration. By embedding the monitoring and adjustment logic directly within the cache router itself, the system achieves adaptability without requiring external control systems, reducing overall device complexity while maintaining high adaptability to changing traffic conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A technique for estimating cache size for cache routers (108A-N/200) in information centric networks (ICNs) (102) is disclosed. In an example, an average rate of incoming requests and a probability of occurrence of each request at a cache router (108A-N/200) in a predefined time interval is determined. Further, a relation between cache hit and cache miss with and without replacement is derived based on the probability of occurrence of each request. Furthermore, an entropy of the requests is computed based on the probability of occurrence of each request. Moreover, a diversity index of the requests is calculated based on the entropy and average rate of the requests. A cache size for the cache router (108A-N/200) is then estimated based on a user defined probability of cache hit, average rate of the requests, diversity index of the requests and relation between the cache hit and cache miss with and without replacement.