ABSTRACT
Aiming at the problem that the load identification accuracy of non-intrusive load monitoring (NILM) is greatly affected by the power of loads and the number of background loads, a non-intrusive load identification method based on the current complex spectrum and support vector machine (SVM) is proposed. Through the high-frequency sampling of the load's voltage and current, the complex spectrum of the current is extracted by the fast Fourier transform (FFT), and the multi-class SVM load identification model is established and optimized to realize the non-intrusive load identification. The algorithm is verified using the PLAID datasets, and the load identification accuracy of the algorithm is compared with SVM classifiers based on total harmonic distortion rate (THD), harmonic component ratio and harmonic amplitude. The results of the experiments show that the proposed method not only improves the identification accuracy of low-power loads, but also has higher identification accuracy and better identification robustness of switching load in multi-load scenarios.
- Gopinath R, Kumar M, Prakash Chandra Joshua C, Energy management using non-intrusive load monitoring techniques – State-of-the-art and future research directions[J]. Sustainable Cities and Society, 2020, 62: 102411.Google ScholarCross Ref
- Bai Hongkun, Bu Feifei, Li Wenfeng, Non-intrusion Monitoring of Industrial Users Based on Composite Analysis Algorithm[J]. Henan Electric Power, 2021(S1): 43-47+113.Google Scholar
- Shi Yusong, Xu Qingshan, Zheng Jian. Non-intrusive Charging Identification Method for Electric Bicycles Based on Feature Selection and Incremental Learning[J]. Automation of Electric Power Systems, 2021, 45(07): 87-94.Google Scholar
- Nguyen M, Alshareef S, Gilani A, A novel feature extraction and classification algorithm based on power components using single-point monitoring for NILM[C]. 2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE), 2015: 37-40.Google Scholar
- Baets L D, Dhaene T, Deschrijver D, VI-Based Appliance Classification Using Aggregated Power Consumption Data[C]. 2018 IEEE International Conference on Smart Computing (SMARTCOMP), 2018: 179-186.Google Scholar
- Gillis J M, Morsi W G. A New Approach to Design New Orthogonal Wavelets Using Unsupervised Clustering Applied to Nonintrusive Load Monitoring[C]. 2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 2021: 1-7.Google Scholar
- Qi Bing, Dong Chao, Wu Xin, Non-intrusive Load Identification Method Based on DTW Algorithm and Steady-state Current Waveform [J]. Automation of Electric Power Systems, 2018, 42(3): 70-76.Google Scholar
- Wu Xin, Qi Bing, Han Lu, Fast non-intrusive load identification algorithm for resident load based on template filtering [J]. Automation of Electric Power Systems, 2017, 41(2): 135-141.Google Scholar
- Li Lingna, Shao Zijuan, Jin Yaodeng. Model of Non-intrusive Load Stamp Recognition Based on SVM [J]. Mathematics in Practice and Theory, 2019, 49(20): 200-208.Google Scholar
- Cai Gaocheng, Cheng Lijuan. Non-intrusive Load Identification Based a SVM [J]. Journal of Lingnan Normal University, 2018, 39(06): 40-45.Google Scholar
- Tu Jing, Zhou Ming, Song Xufan, Comparison of supervised learning-based non-intrusive load monitoring algorithms[J]. Electric Power Automation Equipment, 2018, 38(12): 128-134.Google Scholar
- Bouhouras A S, Vaggos M, Poulakis N, Load signatures enhancement via odd-order harmonic currents[C]. 2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC), 2016: 1-6.Google Scholar
- Bouhouras A S, Chatzisavvas K C, Panagiotou E, Load signatures development via harmonic current vectors[C]. 2017 52nd International Universities Power Engineering Conference (UPEC), 2017: 1-6.Google Scholar
- Zhan Hang, Zhu Hongwei, Zhu Lingjun. A cepstrum analysis based non-intrusive load monitoring method[J]. Electronic Technology, 2018, 47(05): 37-40.Google Scholar
- Ding Shifei, Qi Bingjuan, Tan Hongyan. An Overview on Theory and Algorithm of Support Vector Machines[J]. Journal of University of Electronic Science and Technology of China, 2011, 40(01): 2-10.Google Scholar
- Xu Xiaoming. SVM Parameter Optimization and Its Application in the Classification[D]. Dalian Maritime University, 2014.Google Scholar
- Li Song, Fu Yunfa, Chen Jian, Comparative research of identification of EEG induced by Motor imagery based on five kinds of parameters optimizing SVM[J]. Transducer and Microsystem Technologies, 2017, 36(04): 42-45+50.Google Scholar
- Ji Changming, Zhou Ting, Xiang Tengfei, Application of support vector machine based on grid search and cross validation in implicit stochastic dispatch of cascaded hydropower stations [J]. Electric Power Automation Equipment, 2014, 34(03): 125-131.Google Scholar
- Zheng Z, Chen H, Luo X. A Supervised Event-Based Non-Intrusive Load Monitoring for Non-Linear Appliances[J]. Sustainability, 2018, 10(4).Google Scholar
- Han Xiao. Non-intrusive load identification technology of residential users based on signal decomposition[D]. North China Electric Power University (Beijing), 2019.Google Scholar
Index Terms
- Non-Intrusive Load Identification Based on Complex Spectrum and Support Vector Machine
Recommendations
Multi-class Support Vector Machine (SVM) Classifiers -- An Application in Hypothyroid Detection and Classification
BIC-TA '11: Proceedings of the 2011 Sixth International Conference on Bio-Inspired Computing: Theories and ApplicationsThe paper presents a Multi-class Support Vector Machine classifier and its application to hypothyroid detection and classification. Support Vector Machines (SVM) have been well known method in the machine learning community for binary classification ...
Load Identification in Neural Networks for a Non-intrusive Monitoring of Industrial Electrical Loads
Computer Supported Cooperative Work in Design IVThis paper proposes the use of neural network classifiers to evaluate back propagation (BP) and learning vector quantization (LVQ) for feature selection of load identification in a non-intrusive load monitoring (NILM) system. To test the performance of ...
A new model of multi-class support vector machine with parameter υ
FSKD'09: Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1A new model of multi-class support vector machine with parameter v (v-MC-SVM) is proposed firstly based on v- SVM. Existence of optimal solutions and dual problem of v-MC-SVM are also given. Because the constraints of v- MC-SVM are too complicated, one-...
Comments