Browsing by Subject "Cloud Computing,"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Self managed cloud computing and edge computing system using deep reinforcement learning(Pulchowk Campus, 2021-09) Shakya, SushilIn order to tackle the latency problems in sensitive applications implemented in IoT devices, the edge computing came into existence. On top of that, the idea of a mobile edge computing (MEC) network, in which such computationally heavy activities are computed in many edge servers deployed adjacent to mobile devices, has recently gained popularity. Unlike cloud server, the edge device has a nite computation capacity and it can't handle massive computation tasks. There needs to be a smart task o oading scheme in order to decide whether to execute the task in the local device itself, or o oad it to the edge device and process there or again send it further to the cloud server for processing. Also the algorithm should be able to utilize the available network bandwidth e ciently. The optimization of joint o oading decision and bandwidth allocation in a multi user, multi task, multi server environment can be formulated as a mixed integer non linear programming problem (MINLP) in MEC to preserve energy and maintain quality of service for wireless devices. MINLP is a NP-hard problem and the time complexity to solve it grows exponentially. In this research work, the power of deep learning and reinforcement learning has been applied to solve this MINLP problem under a fraction of a second which makes it suitable for real world usage. Further an end to end integrated edge and cloud computing system has been proposed that switches from one to another whenever required, and leverages the bene ts of both paradigm.Item Task Prioritization and Scheduling of Fog Computing Model in Healthcare Systems(Pulchowk Campus, 2021-09) Pahari, PrakritiHealth-related applications are one of the most sensitive areas which should be delivered on time e ciently. For the storage and processing of enormous health data, Cloud Computing could not be e cient as Cloud Data Centers take a large time to process and send back the results. The new paradigm, called Fog Computing is applicable in cases like these. In this research, we utilize the sample time-critical healthcare system where the IoT sensors' data is divided into critical and normal tasks where critical tasks are prioritized over normal patients' data. To address their management, Fog Computing is used at the edge of the network. In this paper, a new fog-cloud-based algorithm called Prioritized Latency Aware Energy E cient Algorithm (PLAEE) is developed by utilizing the existing algorithms in the fog system and also by process optimization of the core evaluation metrics, latency, and energy usage. This algorithm shows superiority to the existing algorithms in terms of performance metrics. The experimentation is performed using Blood Pressure data collected from the University of Piraeus. In terms of response time, the PLAEE is performing 36.40%, 14.82%, 14.70%, and 6.03% better than Cloud only, Edge-wards, Resource Aware, and SCATTER Algorithm respectively. In terms of Energy Consumption, the PLAEE is performing 23.85%, 14.96%, 10.84%, and 2.83% better than Cloud only, Edge-wards, Resource Aware, and SCATTER Algorithm respectively. Almost 98% of critical data are placed in the FNs according to the Tasks Managed value calculated where 91.70%, 6.28%, and 2.01% of Critical Tasks are placed in FZ1, FZ2, and CDC respectively