Artificial intelligence-driven task scheduling and assignment system using applications e.g. cloud computing, has reinforcement learning-based task assignment engine integrates quality learning and state-action-reward-state-action algorithms to optimize task allocation dynamically
	KRISHNARAJ N; KUMAR S
	2025-04-02
专利权人	KRISHNARAJ N (KRIS-Individual) ; KUMAR S (KUMA-Individual)
申请日期	2025-04-02
专利号	IN202541032559-A
成果简介	NOVELTY - The system has a task prioritization module for ranking tasks using ant colony optimization (ACO) based on urgency, resource demand, and execution constraints. A reinforcement learning (RL)-based task assignment engine integrates quality learning (Q-learning) and state-action-reward-state-action (SARSA) algorithms to optimize task allocation dynamically. A workload optimization mechanism balances task execution across available resources using Markov decision processes (MDP). A feedback learning system refines scheduling policies continuously based on execution outcomes, system latency, and workload distribution. A real-time monitoring and adaptation unit analyzes system performance and adjust scheduling strategies accordingly. USE - Artificial intelligence (AI)-driven task scheduling and assignment system using applications e.g. cloud computing, distributed systems and industrial workflow automation. ADVANTAGE - The system optimizes workload distribution and task execution efficiency, leverages ACO pheromone-based heuristic optimization to generate initial task schedules, ensures efficient allocation with minimal computational overhead and stable convergence in dynamic environments, enhances adaptability, execution speed, workload balancing and overall system performance, achieves feline scheduling decisions dynamically and enables long-term optimization. DESCRIPTION OF DRAWING(S) - The drawing shows a block diagram of the AI-driven task scheduling and assignment system.
IPC 分类号	G06F-009/48 ; G06F-009/50 ; G06N-020/00 ; G06N-003/006 ; G06Q-010/0631
国家	印度
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/13237
专题	中国科学院新疆生态与地理研究所
作者单位	1.KRISHNARAJ N (KRIS-Individual) 2.KUMAR S (KUMA-Individual)
推荐引用方式 GB/T 7714	KRISHNARAJ N,KUMAR S. Artificial intelligence-driven task scheduling and assignment system using applications e.g. cloud computing, has reinforcement learning-based task assignment engine integrates quality learning and state-action-reward-state-action algorithms to optimize task allocation dynamically. IN202541032559-A[P]. 2025.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。