Implementation of a Neural Network Proxy Cache Replacement Strategy in the Squid Proxy Server

Part of the SpringerBriefs in Computer Science book series (BRIEFSCOMPUTER)


As the Internet has become a more central aspect for information technology, so have concerns with supplying enough bandwidth and serving web requests to end users in an appropriate time frame. Web caching was introduced in the 1990s to help decrease network traffic, lessen user perceived lag, and reduce loads on origin servers by storing copies of web objects on servers closer to end users as opposed to forwarding all requests to the origin servers. Since web caches have limited space, web caches must effectively decide which objects are worth caching or replacing for other objects. This problem is known as cache replacement. We used neural networks to solve this problem and proposed the neural network proxy cache replacement (NNPCR) method. The goal of this research is to implement NNPCR in a real environment like Squid proxy server. In order to do so, we propose an improved strategy of NNPCR referred to as NNPCR-2. We show how the improved model can be trained with up to twelve times more data and gain a 5–10 % increase in correct classification ratio (CCR) than in NNPCR. We implemented NNPCR-2 in Squid proxy server and compared it with four other cache replacement strategies. In this chapter, we use 84 times more data than NNPCR was tested against and present exhaustive test results for NNPCR-2 with different trace files and neural network structures. Our results demonstrate that NNPCR-2 made important, balanced decisions in relation to the hit rate and byte-hit rate; the two performance metrics most commonly used to measure the performance of web proxy caches.


NNPCR-2 Neural network proxy cache replacement (NNPCR) Web proxies Proxy caching Neural networks Hit rate Byte-hit rate Trace file IRCache Squid Sliding window Hidden node Learning rate 


  1. 1.
    M.F. Arlitt, L. Cherkasova, J. Dilley, R.J. Friedrich, T.Y. Jin Evaluating content management techniques for web proxy caches. ACM SIGMETRICS Perform. Eval. Rev. 27, 3–11 (2000) (4 Mar)Google Scholar
  2. 2.
    J. Dilley, M. Arlitt, S. Perret, Enhancement and Validation of Squid’s Cache Replacement Policy, Internet Systems and Applications Laboratory, HP Laboratories, Palo Alto, California, HPL-1999–69. May 1999Google Scholar
  3. 3.
    I. Tatarinov, An Efficient LFU-like Policy for Web Caches, Tech. Rep. NDSU-CSORTR-98-01, (Computer Science Department, North Dakota State University, Wahpeton, 1998)Google Scholar
  4. 4.
    C.C. Aggarwal, J.L. Wolf, P.S. Yu, Caching on the World Wide Web. IEEE Trans. Knowledge. Data Eng 11, 94–107 (1999)CrossRefGoogle Scholar
  5. 5.
    S. Romano, H. ElAarag, A quantitative study of recency and frequency-based cache replacement strategies. Communication and Networking Simulation Symposium (CNS2008), Spring Simulation Multiconference, Ottawa, pp 70–78 (2008)Google Scholar
  6. 6.
    IRCache Home, Available at
  7. 7.
    R.D. Reed, R.J. Marks, Neural Smithing, Supervised Learning in Feedforward Artificial Neural Networks (The MIT Press, Massachusetts, 1999), pp. 1–53Google Scholar
  8. 8.
    GNU Wget, Available at
  9. 9.
    H. ElAarag, S. Romano, Improvement of the Neural Network Proxy Cache Replacement Strategy, Communication and Networking Simulation Symposium (CNS2009), Spring Simulation Multiconference, San Diego, CA, 22–27 Mar 2009Google Scholar

Copyright information

© Hala ElAarag 2013

Authors and Affiliations

  1. 1.Department of Math and Computer ScienceStetson UniversityDeLandUSA

Personalised recommendations