Designing new methods for DAG scheduling problem for cloud computing

Objective:- Designing new methods for DAG scheduling problem for cloud computing.

Abstract:-

It is a scheduling layer in a spark which implements stage-oriented scheduling. It converts logical execution plan to a physical execution plan. When an action is called, spark directly strikes to DAG scheduler. It executes the tasks those are submitted to the scheduler.

The objective of DAG scheduling is to minimize the overall program finish-time by proper allocation of the tasks to the processors and arrangement of execution sequencing of the tasks. Scheduling is done in such a manner that the precedence constraints among the program tasks are preserved. The overall finish-time of a parallel program is commonly called the schedule length or make span. Some variations to this goal have been suggested. For example, some researchers proposed algorithms to minimize the mean flow-time or mean finish-time, which is the average of the finish-times of all the program tasks [25], [110]. The significance of the mean finish-time criterion is that minimizing it in the final schedule leads to the reduction of the mean number of unfinished tasks at each point in the schedule. Some other algorithms try to reduce the setup costs of the parallel processors [159]. We focus on algorithms that minimize the schedule length.

INTRODUCTION:-

The Cloud is a huge, interconnected system of Powerful servers that provides businesses and individuals with services [1] The concept (Cloud Computing) refers to the ability for online users to share resources offered by the service provider. Without needing to buy expensive hardware, to leverage the high-service provider's capabilities[2]. The main goal of the cloud computing model is to allow users to share resources and data, Software as a service (SaaS), application as a service (PaaS), and infrastructure as a service (IaaS). As the number of cloud users has grown in recent years, the number of tasks that must be managed propositionally has increased, necessitating task scheduling[3]. methodology is based on Reinforcement learning

RELATED WORK:-

The task scheduling algorithm's main goal is to ensure that tasks are completed as efficiently as possible. List scheduling algorithms are used in the task scheduling process. In list scheduling algorithms, there are two distinct phases. The first phase entails determining the tasks' priority, and the second phase entails assigning tasks to the processor in the order determined[3], They will be discussed as follow. In 2017 (Wei et al.)[4] t has been proposed a task scheduling algorithm based on Q-learning and the mutual value function (QS).

Workflow model:-

A directed acyclic graph, G=(V,E), represents an application, with V representing the set of v tasks and E representing the set of e edges between the tasks. Each edge (imp) E represents a precedence constraint, requiring task to finish before task can begin.

Data is a v×v matrix of communication data, with indicating the amount of data to be transmitted from task to task . DAG scheduling object: node tasks are assigned object resources that must satisfy a chronological order constraint in order to reduce the total time to completion.

Components of proposed algorithm:-

RL, MDP, and the Q-learning algorithm

Proposed Scheduling Algorithm:- Input: DAG all Tasks.

Output: The make span.

Procedure:

1: Create DAG for all tasks.

2: Set gamma parameter, environment rewards in matrix R. 3: Initialize matrix Q to zero.

4: Repeat for each episode. 5: Select an initial state.

6: While the goal state not reached Do.

7: Select possible actions for the current state. 8: Go to the next state.

9: Get maximum Q value with E.g. (6). 10: Set next state as a current state. 11:Update Q(state, action) with E.g. (6).

12: Obtain tasks order according to updated Q-table.

13: Map task to the processor which have the minimum execution time. 14: Calculate the make span.

15: Until no longer changes in make span

Conclusion:-

Existing scheduling algorithms focused on the time. The main goal of these schedulers is to reduce the overall Make span of the workflow. Gaps in current workflow scheduling strategies in the cloud environments were studied in this thesis, and an effective scheduling method for workflow management in the cloud setting was proposed based on the gap analysis. It has b even determined that the current scheme is effective enough to make the best use of the available resources. There are two stages to the algorithm design theor