SCALABILITY OF VIDEO TRANSCODING ON A CLOUDCOMPUTINGPLATFORM
Amini-Alaoui, Mohamed (2018)
Amini-Alaoui, Mohamed
Åbo Akademi
2018
Julkaisu on tekijänoikeussäännösten alainen. Teosta voi lukea ja tulostaa henkilökohtaista käyttöä varten. Käyttö kaupallisiin tarkoituksiin on kielletty.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2018111448092
https://urn.fi/URN:NBN:fi-fe2018111448092
Tiivistelmä
Millions of videos are being shared between users every day; these videos have different formats and codecs and are being played in different platforms with different apps. The need to convert these videos into a format that could be read in every platform and could be used by any user is the key, and this is where transcoding comes into play. The operation of video transcoding demands a large amount of computing power, thus a source of computing resources which are ready at all times to be used, scalable, and reliable is necessary to achieve the goal. Therefore, cloud computing is worth examining as a prominent candidate to be considered as the platform for video transcoding.
This thesis work includes a presentation of cloud computing and its features, explaining the pros and cons of using it, as well as elaborating on the topic of the overheads related to this technology. Related work has been taken into consideration by presenting the outcomes of a study concerning the management of performance overhead of virtual machines in cloud computing. The experiment and its setup are explained in details, and the result of the thesis work is presented at the end with figures showing the execution time of each step used of the script. The script is based on FFMPEG libraries for the transcoding, and the open-stack based cloud computing platform chosen for this experiment is cPouta from SCS ―Center for Science‖. Further discussions and future work is given at the last chapter of the thesis work.
This thesis work includes a presentation of cloud computing and its features, explaining the pros and cons of using it, as well as elaborating on the topic of the overheads related to this technology. Related work has been taken into consideration by presenting the outcomes of a study concerning the management of performance overhead of virtual machines in cloud computing. The experiment and its setup are explained in details, and the result of the thesis work is presented at the end with figures showing the execution time of each step used of the script. The script is based on FFMPEG libraries for the transcoding, and the open-stack based cloud computing platform chosen for this experiment is cPouta from SCS ―Center for Science‖. Further discussions and future work is given at the last chapter of the thesis work.