**6. Conclusions**

In this paper, we propose a novel electricity theft detection scheme based on TextCNN. We innovatively formulated the electricity data into two-dimensional time-series in order to capture the intraday and daily correlations of electricity consumption data. Then, we discussed the relationship between DNN, CNN and TextCNN, and explained why TextCNN is the most suitable classifier for our purposes, considering both the e fficiency and e ffectiveness. Additionally, in order to balance the electricity consumption dataset, we proposed a data augmentation method. We conducted extensive experiments on di fferent realistic datasets to prove the e ffectiveness of the proposed scheme, including the residential and industrial datasets from a province in China and the public Irish residential dataset. The experimental results show that the proposed method outperforms other methods, such as LR, SVM, DNN and 1D CNN. At the same time, we analyzed the importance and e ffectiveness of data augmentation.

**Author Contributions:** Conceptualization and methodology, X.F. and H.H.; software, Z.L. and Y.Y.; validation, W.G., H.Q. and H.F.; writing, H.H., Z.L., Y.Y. and C.Y.; supervision and project administration, X.F., H.Q., H.F. and Y.D. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research was funded by Project Supported by the China Southern Power Grid Corporation, gran<sup>t</sup> number GDKJXM20185800.

**Conflicts of Interest:** The authors declare no conflict of interest.
