Abstract As a result of the rapid increase in smart-metre popularity, a large volume of smart electricity data has been generated. The underlying information contained within such data sets is very helpful and useful to businesses and power companies. However, effective mining of this valuable knowledge is challenging for both industry and academia. Current research mainly focuses on application of statistical analyses to available smart electricity data rather than construction of an advanced learning system. This paper reports development of an intelligent system to identify electricity patterns within industrial electricity data. The core component of this novel identification system is the I-nice- α clustering algorithm, which is a variant of the I-nice algorithm. I-nice- α utilises kernel density estimation technology and the minimum mean discrepancy to optimise the cluster number and determine the cluster centres, respectively, of the target data. Our theoretical analysis proves that I-nice- α has lower computational complexity than I-nice. We also compare I-nice- α with I-nice and four other standard clustering algorithms (i.e., the Gaussian mixture model (GMM), density-based spatial clustering of applications with noise (DBSCAN), the fuzzy c-means (FCM) algorithm, and balanced iterative reducing and clustering using hierarchies (BIRCH)), based on 15 benchmark data sets and electricity consumption data. The experiment results show that I-nice- α achieves superior clustering performance; thus, the feasibility and effectiveness of the improved algorithm are demonstrated. In addition, hierarchical (i.e., daily and annual) electricity patterns are determined by analysing industrial electricity data with I-nice- α ; this result elucidates the production organism and power assignment. Thus, the proposed electricity pattern identification system has considerable potential application among power companies and businesses.

中文翻译：

---

基于改进I-nice算法的新型电模式识别系统

摘要 随着智能电表的快速普及，产生了大量的智能用电数据。这些数据集中包含的基础信息对企业和电力公司非常有帮助和有用。然而，有效挖掘这些有价值的知识对工业界和学术界来说都具有挑战性。当前的研究主要集中在对可用智能电力数据进行统计分析的应用，而不是构建先进的学习系统。本文报告了一种智能系统的开发，用于识别工业电力数据中的电力模式。这种新型识别系统的核心组件是 I-nice-α 聚类算法，它是 I-nice 算法的变体。I-nice-α利用核密度估计技术和最小均值差异来优化聚类数并分别确定目标数据的聚类中心。我们的理论分析证明 I-nice-α 的计算复杂度低于 I-nice。我们还将 I-nice-α 与 I-nice 和其他四种标准聚类算法（即高斯混合模型 (GMM)、基于密度的噪声应用空间聚类 (DBSCAN)、模糊 c 均值 (FCM)算法，以及使用层次结构 (BIRCH) 的平衡迭代减少和聚类），基于 15 个基准数据集和电力消耗数据。实验结果表明，I-nice-α实现了优越的聚类性能；从而证明了改进算法的可行性和有效性。此外，分层（即，日和年）用电模式是通过用 I-nice-α 分析工业用电数据来确定的；这一结果阐明了生产有机体和权力分配。因此，所提出的电力模式识别系统在电力公司和企业中具有相当大的潜在应用。