Estimating Feasible Power Output Boundaries of CHP Units by Mining Extreme Power Values from Historical Operation Data Sequence.

Saved in:

Bibliographic Details
Title:	Estimating Feasible Power Output Boundaries of CHP Units by Mining Extreme Power Values from Historical Operation Data Sequence.
Authors:	Du, Hongfei¹ Du_9011@163.com, Jin, Tao¹ JingT_7805@163.com, Jia, Fengsheng¹ Jiafs_9011@163.com, Cong, Lin¹ Congl_8209@163.com
Source:	Engineering Letters. May2026, Vol. 34 Issue 5, p1579-1588. 10p.
Subjects:	K-means clustering, Piecewise linear approximation, Data mining, Electric power system control, Trigeneration (Energy), Electric power system management
Abstract:	With substantial amounts of renewable energies being integrated into power grids, combined heat and power (CHP) units are required to regulate their power outputs to compensate for power fluctuations caused by renewable energies. The feasible power output boundaries are important indices, which indicate the regulative capacities of CHP units. This paper proposes a method to estimate the feasible power output boundaries. The proposed method comprises both an offline stage and an online stage. During the offline stage, the operating conditions of the mass flow rate of extraction steam are identified through the K-means algorithm. Subsequently, the stable power output data segments corresponding to each operating condition are determined via the piecewise linear representation algorithm. Lastly, the power output boundaries of each operating condition are regarded as the maximum and minimum mean values of the stable power output data segments. During the online stage, the current operating condition is determined by finding the minimum Euclidean distance between the mass flow rate of extraction steam to each center of the operating conditions, and then the power output boundaries of the current operating condition are regarded as the estimates of the feasible power output boundaries. To determine the operating conditions via the K-means algorithm in an unsupervised manner, an optimal clustering number determination algorithm is formulated. An industrial example is provided to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]
	Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	With substantial amounts of renewable energies being integrated into power grids, combined heat and power (CHP) units are required to regulate their power outputs to compensate for power fluctuations caused by renewable energies. The feasible power output boundaries are important indices, which indicate the regulative capacities of CHP units. This paper proposes a method to estimate the feasible power output boundaries. The proposed method comprises both an offline stage and an online stage. During the offline stage, the operating conditions of the mass flow rate of extraction steam are identified through the K-means algorithm. Subsequently, the stable power output data segments corresponding to each operating condition are determined via the piecewise linear representation algorithm. Lastly, the power output boundaries of each operating condition are regarded as the maximum and minimum mean values of the stable power output data segments. During the online stage, the current operating condition is determined by finding the minimum Euclidean distance between the mass flow rate of extraction steam to each center of the operating conditions, and then the power output boundaries of the current operating condition are regarded as the estimates of the feasible power output boundaries. To determine the operating conditions via the K-means algorithm in an unsupervised manner, an optimal clustering number determination algorithm is formulated. An industrial example is provided to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]
ISSN:	1816093X