Today's Internet usage is changing from host-to-host communication to user-to-content interaction which proves a challenge for Internet Service Providers (ISPs). Repeated requests lead to transfers of large amounts of traffic containing the same content often over costly inter-ISP connections. Content Distribution Networks (CDNs) contribute to solving this issue, but do not directly address the problem. This thesis project explores how content based addressing could minimize inter-ISP traffic due to repeated requests for content by caching content within the ISP's network. We implemented CCNx 0.6.0 in a network testbed in order to simulate scenarios with multiple ISPs interconnected to each other. This testbed is used to illustrate how caching of popular content minimizes inter-ISP traffic as well as how content independence minimizes the effect of other network problems such as link failures and congestion. These tests shows that the large overhead of the CCNx implementation due to the additional headers brings a 16% performance reduction compared to Hypertext Transfer Protocol (HTTP) transfers. However, these tests also shows that the cost from the inter-ISP traffic of CCNx transfers are constant regardless of the number of repeated requests, due to content caching in the ISP's network. As soon as there is more than one request for the same content there is a gain in using CCNx rather than HTTP for content transfer. / Dagens användning av internet ändrar form från dator-till-dator kommunikation till användaretill- innehålls interaktion vilket innebär nya utmaningar för internetleverantörer vilka måste överföra stora mängder upprepade förfrågningar av innehåll via kostsamma länkar mellan internetleverantörer. Lösningar som innehållsdistribuerande nätverk (Content Distribution Network) hjälper idag till men addresserar inte kärnan av problemet. Det här examensarbetet undersöker hur innehållsbaserad addressering kan minimera mängden trafik mellan internetleverantörer genom att cachning, att lagra kopior av innehåll, i internetleverantörers nätverket. I det här examensarbetet implementerade vi CCNx 0.6.0 i en testbädd för att simulera scenarion med nätverk mellan internetleverantörer. Denna testbädd används för att illustrera hur cachning av populärt innehåll kan minimera trafik mellan internetleverantörer samt hur innehållets oberoende av plats även hjälper till med andra problem i nätverket såsom länkfel och stockning. Dessa test visar att CCNx implementationen har stor overhead information på grund av ytterligare, extra headers vilket medför en 16% reducering i prestanda jämfört med överföringar som använder Hypertext Transfer Protocol (HTTP). Vidare visar dessa tester även att kostnaden från trafik mellan internetleverantörer är konstant oberoende av antalet upprepade förfrågningar, på grund av cachning av innehåll i internetleverantörens nätverk. Så snart det finns fler än en begäran för samma innehåll finns det en vinst i att använda CCNx istället för HTTP för överföringar av innehåll.

Advantages of cache cooperation on edge cache networks serving dynamic web content were studied. Design of cooperative edge cache grid a large-scale cooperative edge cache network for delivering highly dynamic web content with varying server update frequencies was presented. A cache clouds-based architecture was proposed to promote low-cost cache cooperation in cooperative edge cache grid. An Internet landmarks-based scheme, called selective landmarks-based server-distance sensitive clustering scheme, for grouping edge caches into cooperative clouds was presented. Dynamic hashing technique for efficient, load-balanced, and reliable documents lookups and updates was presented. Utility-based scheme for cooperative document placement in cache clouds was proposed. The proposed architecture and techniques were evaluated through trace-based simulations using both real-world and synthetic traces. Results showed that the proposed techniques provide significant performance benefits. A framework for automatically detecting cache-effective fragments in dynamic web pages was presented. Two types of fragments in web pages, namely, shared fragments and lifetime-personalization fragments were identified and formally defined. A hierarchical fragment-aware web page model called the augmented-fragment tree model was proposed. An efficient algorithm to detect maximal fragments that are shared among multiple documents was proposed. A practical algorithm for detecting fragments based on their lifetime and personalization characteristics was designed. The proposed framework and algorithms were evaluated through experiments on real web sites. The effect of adopting the detected fragments on web-caches and origin-servers is experimentally studied.