Short name: DeepRL4MEC
Long name: Deep Reinforcement Learning for MPEG DASH segments’ dynamic assignment in MEC environments
Call Stage 1: F4Fp-SME-COD1 (see call details)
Proposal number: F4Fp-SME-COD200428-04
SUMMARY REMARKS & TESTBEDS
The computing resources withinMobile Edge Computing (MEC) application servers are limited. For example, a given servermight beCPU-stressed while servicing many clients. Within thisCall, we shallextend our prototype to further improve clients’performanceby implementing and validatingtwo new features: (I)we will rewrite parts ofour code in order to undertake mapping decisions per each client MPEG DASH segment, not for the whole MPEG DASH file. This way,we willbedecidingat a much faster scalethan our current implementation, following more closely the changes that occur in the MEC environment;and,(II) to lower the training time of our models, we shall employ GPUs.