Intelligent Cooperative Web Caching Policies for Media Objects Based on J48 Decision Tree and Naïve Bayes Supervised Machine Learning Algorithms in Structured Peer-to-Peer Systems

Ibrahim, Hamidah; Yasin, Waheed; Udzir, Nur Izura; Hamid, Nor Asilah Wati Abdul

doi:10.32890/jict2016.15.2.5

“…The normalized frequencies and duration can be easily derived using the Eqns. (10,11,15,16). The distance metrics for the interest interval is given by: Current web page access frequency K…”

Section: Multiple Factor Distance Measuresmentioning

confidence: 99%

“…Web object frequency, web objects + internal request regularity, recency, web object distribution based on sliding window are some of the features that suit best for this purpose. Collaborative caching [15] in structured peer to peer systems combined with intelligent prediction algorithms are useful in boosting the performance of web proxy cache and produces the best accuracy than traditional algorithms like LRU, LFU, etc. Moreover, this structured system uses hap map functions to locate peers and shared data references which enable them to give less latency and load balancing properties.…”

Section: Introductionmentioning

confidence: 99%

An Improved Web Caching System With Locally Normalized User Intervals

Vaithinathan¹,

Benadit

²

,

Parthiban

³

et al. 2021

IEEE Access

2

0

View full text Add to dashboard Cite

Caching is one of the most promising areas in the field of future internet architecture like Information-centric Networking, Software Defined Networking, and IoT. In Web caching, most of the web content is readily available across the network, even if the webserver is not reachable. Several existing traditional caching methods and cache replacement strategies are evaluated based on the metrics like hit ratio and byte hit Ratio. However, these metrics have not been improved over the period because of the traditional caching policies. So, in this paper, we have used an intelligent function like locally normalized intervals of page visit, website duration, users' interest between user groups is proposed. These intervals are combined with multiple distance metrics like Manhattan, squared Euclidean, and 3-,4-,5-norm Minkowski. In order to obtain significant common user navigation patterns, the clustering relation between the users using different intervals and distances is thoroughly analyzed. These patterns are successfully coupled with greedy web cache replacement strategies to improve the efficiency of the proposed web cache system. Particularly for improving the caching metrics more, we used an AI-based intelligent approach like Random Forest classifier to boost the prefetch buffer performance and achieves the maximum hit rate of 0.89, 0.90, and byte hit rate of 0.87, 0.89 for Greedy Dual Size Frequency and Weighted Greedy Dual Size Frequency algorithms, respectively. Our experiments show good hit/byte hit rates than the frequently used algorithms like least recently used and least frequently used.

show abstract

“…Though it works well, however, features are selected manually in training machine learning techniques. Ibrahim, Yasin [16] proposed co-operation between J48 classifier and LRU to improve the performance of LRU and avoid cache pollution problem. The simulation results show that intelligent algorithms performance is better than LRU.…”

Section: Related Workmentioning

confidence: 99%

Intelligent Cooperative Adaptive Weight Ranking Policy via dynamic aging based on NB and J48 classifiers

Al-Qudah

¹

,

Olanrewaju

²

,

Azman

³

2017

IJEEI

0

View full text Add to dashboard Cite

The increased usage of World Wide Web leads to increase in network traffic and create a bottleneck over the internet performance. For most people, the accessing speed or the response time is the most critical factor when using the internet. Reducing response time was done by using web proxy cache technique that storing a copy of pages between client and server sides. If requested pages are cached in the proxy, there is no need to access the server. But, the cache size is limited, so cache replacement algorithms are used to remove pages from the cache when it is full. On the other hand, the conventional algorithms for replacement such as Least Recently Use (LRU), First in First Out (FIFO), Least Frequently Use (LFU), Randomised Policy, etc. may discard essential pages just before use. Furthermore, using conventional algorithms cannot be well optimized since it requires some decision to evict intelligently before a page is replaced. Hence, this paper proposes an integration of Adaptive Weight Ranking Policy (AWRP) with intelligent classifiers (NB-AWRP-DA and J48-AWRP-DA) via dynamic aging factor. To enhance classifiers power of prediction before integrating them with AWRP, particle swarm optimization (PSO) automated wrapper feature selection methods are used to choose the best subset of features that are relevant and influence classifiers prediction accuracy. Experimental Result shows that NB-AWRP-DA enhances the performance of web proxy cache across multi proxy datasets by 4.

show abstract

“…Ibrahim, Yasin [16] proposed co-operation between J48 classifier and LRU to improve the performance of LRU and avoid cache pollution problem. The simulation results show that intelligent algorithms performance is better than LRU.…”

Section: Related Workmentioning

confidence: 99%

Intelligent Cooperative Adaptive Weight Ranking Policy via dynamic aging based on NB and J48 classifiers

Al-Qudah

¹

,

Olanrewaju

²

,

Azman

³

2017

IJEEI

2

0

View full text Add to dashboard Cite

The increased usage of World Wide Web leads to increase in network traffic and create a bottleneck over the internet performance. For most people, the accessing speed or the response time is the most critical factor when using the internet. Reducing response time was done by using web proxy cache technique that storing a copy of pages between client and server sides. If requested pages are cached in the proxy, there is no need to access the server. But, the cache size is limited, so cache replacement algorithms are used to remove pages from the cache when it is full. On the other hand, the conventional algorithms for replacement such as Least Recently Use (LRU), First in First Out (FIFO), Least Frequently Use (LFU), Randomised Policy, etc. may discard essential pages just before use. Furthermore, using conventional algorithms cannot be well optimized since it requires some decision to evict intelligently before a page is replaced. Hence, this paper proposes an integration of Adaptive Weight Ranking Policy (AWRP) with intelligent classifiers (NB-AWRP-DA and J48-AWRP-DA) via dynamic aging factor. To enhance classifiers power of prediction before integrating them with AWRP, particle swarm optimization (PSO) automated wrapper feature selection methods are used to choose the best subset of features that are relevant and influence classifiers prediction accuracy. Experimental Result shows that NB-AWRP-DA enhances the performance of web proxy cache across multi proxy datasets by 4.

show abstract

Intelligent Cooperative Web Caching Policies for Media Objects Based on J48 Decision Tree and Naïve Bayes Supervised Machine Learning Algorithms in Structured Peer-to-Peer Systems

Cited by 9 publications

References 26 publications

An Improved Web Caching System With Locally Normalized User Intervals

An Improved Web Caching System With Locally Normalized User Intervals

Intelligent Cooperative Adaptive Weight Ranking Policy via dynamic aging based on NB and J48 classifiers

Intelligent Cooperative Adaptive Weight Ranking Policy via dynamic aging based on NB and J48 classifiers

Contact Info

Product

Resources

About