[Paper Review] From Traditional Adaptive Data Caching to Adaptive Context Caching: A Survey

Shakthi Weerasinghe, Arkady Zaslavsky+4 more|arXiv (Cornell University)|Nov 21, 2022

Caching and Content Delivery7 citations

TL;DR

This paper proposes adaptive context caching as a solution to improve performance and quality of service (QoS) in context-aware Internet of Things (IoT) systems, where transient, heterogeneous, and variable context queries strain existing caching mechanisms. By surveying state-of-the-art adaptive data caching techniques, the authors formalize adaptive context caching, define its core requirements, and identify optimal design principles for real-time, cost-efficient context delivery in dynamic environments.

ABSTRACT

Context information is in demand more than ever with the rapid increase in the number of context-aware Internet of Things applications developed worldwide. Research in context and context-awareness is being conducted to broaden its applicability in light of many practical and technical challenges. One of the challenges is improving performance when responding to a large number of context queries. Context Management Platforms that infer and deliver context to applications measure this problem using Quality of Service (QoS) parameters. Although caching is a proven way to improve QoS, transiency of context and features such as variability and heterogeneity of context queries pose an additional real-time cost management problem. This paper presents a critical survey of the state-of-the-art in adaptive data caching with the objective of developing a body of knowledge in cost- and performance-efficient adaptive caching strategies. We comprehensively survey a large number of research publications and evaluate, compare, and contrast different techniques, policies, approaches, and schemes in adaptive caching. Our critical analysis is motivated by the focus on adaptively caching context as a core research problem. A formal definition for adaptive context caching is then proposed, followed by identified features and requirements of a well-designed, objective optimal adaptive context caching strategy.

Motivation & Objective

• Address the growing performance bottleneck in context-aware IoT applications due to high volumes of dynamic context queries.
• Identify limitations in traditional adaptive data caching when applied to context data, particularly due to context transience and query variability.
• Propose a formal definition and framework for adaptive context caching as a distinct research problem.
• Establish key features and requirements for an optimal, objective, and cost-efficient adaptive context caching strategy.
• Provide a comprehensive, critical survey of existing adaptive caching techniques to inform future research and system design in context management.

Proposed method

• Conduct a systematic survey of 100+ research publications on adaptive data caching in distributed and IoT systems.
• Categorize and compare caching techniques, policies, and schemes based on adaptability, context awareness, and QoS optimization.
• Formalize adaptive context caching as a new paradigm, distinguishing it from traditional data caching through context-specific properties.
• Introduce a conceptual model for adaptive context caching that accounts for context transience, query heterogeneity, and real-time cost management.
• Analyze and synthesize design principles for optimal caching strategies, emphasizing dynamic adaptation to context access patterns and system constraints.
• Use a comparative evaluation framework to contrast existing approaches in terms of performance, scalability, and adaptability to context dynamics.

Experimental results

Research questions

• RQ1 How do traditional adaptive data caching techniques fall short in handling the unique characteristics of context data, such as transience and variability?
• RQ2 What are the essential features and requirements for an optimal, cost-efficient adaptive context caching strategy in dynamic IoT environments?
• RQ3 How can caching policies be adapted to prioritize context data based on relevance, urgency, and access patterns in real time?
• RQ4 What are the key differences between adaptive data caching and adaptive context caching, and why is a new formalism necessary?
• RQ5 What design principles and evaluation criteria can guide the development of next-generation context-aware caching systems?

Key findings

• Traditional adaptive data caching is insufficient for context-aware systems due to the transient and highly variable nature of context data.
• Adaptive context caching must account for context-specific properties such as time sensitivity, spatial relevance, and user intent to ensure QoS.
• A formal definition of adaptive context caching is essential to unify research and guide system design, distinguishing it from general data caching.
• The most effective strategies combine dynamic policy adaptation with real-time monitoring of context access patterns and system load.
• Existing caching schemes often lack support for heterogeneous query types and context types, leading to suboptimal performance in practice.
• The survey identifies a clear research gap in objective, measurable optimization of context caching, calling for standardized evaluation benchmarks and metrics.