TTSA: An Effective Scheduling Approach for Delay Bounded Tasks in Hybrid Clouds

Area of Science:

• Computer Science
• Cloud Computing
• Operations Research

Background:

• Organizations increasingly use cloud data centers (CDCs) for applications and global services.
• Scheduling delay-bounded tasks cost-effectively in private CDCs is challenging due to task arrival uncertainty.
• Hybrid cloud environments with temporally diverse energy and execution prices present unique cost optimization problems.

Purpose of the Study:

• To address the cost minimization challenge for private CDCs in hybrid cloud environments.
• To propose an effective task scheduling algorithm that considers temporal price variations.
• To ensure delay-bounded tasks are scheduled without exceeding their specified latency limits.

Main Methods:

• A novel temporal task scheduling algorithm (TTSA) is proposed.
• The cost minimization problem is formulated as a mixed integer linear program.
• A hybrid simulated annealing-particle swarm optimization approach is used to solve the optimization problem.

Main Results:

• TTSA effectively dispatches tasks between private and public clouds.
• Experimental results show TTSA outperforms existing methods in cost reduction and throughput increase.
• The proposed scheduling strategy meets all task delay bounds.

Conclusions:

• TTSA offers an efficient solution for cost-effective task scheduling in hybrid CDCs.
• The algorithm successfully balances cost minimization with meeting strict delay constraints.
• This approach is valuable for organizations seeking to optimize cloud resource utilization and reduce operational expenses.