检索结果-内蒙古大学图书馆

Machine Learning-Additional Decision Constraints for Improved MILP Day-Ahead unit commitment Method

IEEE ACCESS 2023年 11卷 111976-111990页

作者： Shekeew, Mohamed Ibrahim Abdelaziz Venkatesh, Bala Toronto Metropolitan Univ Dept Elect Comp & Biomed Engn Toronto ON M5B 2K3 Canada Toronto Metropolitan Univ Ctr Urban Energy Toronto ON M5B 2K3 Canada

This paper introduces a two-stage (offline and online) artificial neural network (ann) driven constraint creator model to improve the computational quality of day-ahead unit commitment (DAUC) in power systems. The DAUC is crucial for planning 24-hour operations and complex bid clearing through mixed-integer linear programs (MILP). However, slow convergence is common due to system complexity. Machine learning (ML) based methods have been used to enhance MILP-DAUC. Nonetheless, they can lead to sub-optimality and infeasibility. To overcome these challenges, (1) this paper proposes in the offline stage the ann-generators subset (AGS) that can predict part of the optimal MILP-DAUC decisions using an ann model. Online, only ML-generated decisions of AGS are used to form the ann-driven constraints to enhance the main MILP-DAUC, forming the proposed ann-MILP-DAUC method. (2) A feasibility handling process is proposed to retain the infeasible ML states to be optimized by the main MILP-DAUC formulation. (3) The proposed model issues an artificial factor that provides the percentage of generators accurately predicted and used as an ML training performance metric. The ann model was trained using optimal MILP-DAUC solutions. Test results on IEEE 14-bus and 118-bus systems reported solution time reductions of 61.43% and 70.1%, respectively. Larger Polish 2383-bus, 3012-bus, and Ontario systems reported time reductions in the range of 33% compared with the main MILP-DAUC method using MOSEK (TM), a commercial solver. No degradation in the optimal solution was observed for all test systems, and the proposed method provides a lower-objective solution for the same running time, leading to better solutions.

关键词： ann-driven constraints generator ann-constrained unit commitment mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：