Energy consumption for web page loading comprises energy for downloading resources and for rendering the page. SPDY is a networking protocol that aims to reduce the networking latency by multiplexing connections and compressing headers [1]. On a mobile browser, network round-trip time and resource loading times are the major causes of delay [3]. Therefore, multiplexing results in fewer round-trips, which have an impact on the page load time. Modern browsers, such as Chrome and Firefox, already support this protocol. Google has additional infrastructure support, i.e. SPDY proxy, which compresses web elements, specifically images [4]. Therefore, SPDY proxies could also become a more permanent part of the web [2]. 

In this thesis, we first study how SPDY/QUIC performs on Android platform. We measure the page download time on Samsung Galaxy S3 4G when SPDY enabled and disabled in Chrome browser, and the energy consumption of the mobile device using WiFi, 3G (HSPA) and 4G (LTE) networks. We will look for a different approach in resource downloading than the traditional browsers and then apply the mechanism to reduce the page loading time and energy consumption. 

Our initial results is published in Mobicom'2015 as a poster[5]. We want to take the work in the next level. The whole work can be divided into three phases. In the first step, a simple downloader or proxy will be developed which will look for different types of requires as soon as it begins to receive the data from the webserver. The resource finding and downloading will be done in parallel using a number of threads. The second phase involves maintain a list of resources for every webpage. Such resource list generation can be done using crawling the web or can be collected from the mobile devices. Once we have such list of resources, the application can download the resource using different policies in the third step. One policy is that allowing the browser to download the first few resources and the application or proxy downloads the remaining sources. Such policies can be defined based on the situation of the client.

[5] Mohammad A. Hoque, Sasu Tarkoma, and Tuikku Anttila. 2015. Poster: Extremely Parallel Resource Pre-Fetching for Energy Optimized Mobile Web Browsing. In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking (MobiCom '15). ACM, New York, NY, USA, 236-238. DOI=10.1145/2789168.2795167