An Event Detection Approach Based on Improved CUSUM Algorithm and Kalman Filter

Fang, Kaijie; Huang, Yixuan; Huang, Qifeng; Yang, Shihai; Li, Zhixin; Cheng, Hanmiao

doi:10.1109/ei250167.2020.9346980

Cited by 13 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Throughout the experimental procedure, it is postulated that only a single load-switching event occurs at any given instance. The detection of these load-switching events is accomplished through the application of the Cumulative Sum Control Chart (CUSUM) algorithm [ 39 ], a prevalently employed methodology for identifying points of change.…”

Section: Resultsmentioning

confidence: 99%

Non-Intrusive Load Identification Based on Retrainable Siamese Network

Lu,

Kang,

Meng

et al. 2024

Sensors

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM) can identify each electrical load and its operating state in a household by using the voltage and current data measured at a single point on the bus, thereby behaving as a key technology for smart grid construction and effective energy consumption. The existing NILM methods mainly focus on the identification of pre-trained loads, which can achieve high identification accuracy and satisfying outcomes. However, unknown load identification is rarely involved among those methods and the scalability of NILM is still a crucial problem at the current stage. In light of this, we have proposed a non-intrusive load identification method based on a Siamese network, which can be retrained after the detection of an unknown load to increase the identification accuracy for unknown loads. The proposed Siamese network comprises a fixed convolutional neural network (CNN) and two retrainable back propagation (BP) networks. When an unknown load is detected, the low-dimensional features of its voltage–current (V-I) trajectory are extracted by using the fixed CNN model, and the BP networks are retrained online. The finetuning of BP network parameters through retraining can improve the representation ability of the network model; thus, a high accuracy of unknown load identification can be achieved by updating the Siamese network in real time. The public WHITED and PLAID datasets are used for the validation of the proposed method. Finally, the practicality and scalability of the method are demonstrated using a real-house environment test to prove the ability of online retraining on an embedded Linux system with STM32MP1 as the core.

show abstract

Section: Resultsmentioning

confidence: 99%

Non-Intrusive Load Identification Based on Retrainable Siamese Network

Lu,

Kang,

Meng

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Moreover, there are many event detection methods for NILM, such as generalized likelihood ratio (GLR) (Berges et al, 2011) and log-likelihood ratio (LLR) (Anderson et al, 2012a). In this study, a modified CUSUM algorithm (Fang et al, 2020) with a fast and accurate detection effect is adopted.…”

Section: V-△i Trajectory Of Electric Bicyclesmentioning

confidence: 99%

A Non-Intrusive Residential Electric Bicycle Load Monitoring Method Based on Hybrid Feature Bitmap and DeiT

et al. 2022

Self Cite

View full text Add to dashboard Cite

Taking into account energy management and fire safety, electric bicycles are one of the most significant household loads that require real-time sensing for nonintrusive load monitoring. V–I trajectories, power quantities, and harmonic characteristics are the basic selection in feature space for appliance identification. Based on the study of the charging mode of electric bicycles, this study expands the V–I trajectory into V-△I trajectory for gaining the load signature with multi appliances working simultaneously. We perform linear interpolation and pixelation to obtain a bitmap of the V-△I trajectory. Meanwhile, active and harmonic features are encoded and combined to form a hybrid feature bitmap, which is unique to compensate for the high harmonic feature loss caused by the pixelation of the V-△I trajectory. Furthermore, we trained the DeiT model on the self-built dataset and UK-DALE dataset and performed two experiments under single and superposition working conditions for electric bicycles. Our case results indicate that the DeiT model using hybrid feature bitmap offers better overall precision in the prediction of electric bicycles, against other deep convolutional neural networks.

show abstract

“…VERSATILITY: Some research results are only verified by using a single datas Because the results are not objective, it is difficult to prove that the proposed m could be applied to other datasets. Therefore, the proposed method was va using two public datasets, namely the Controlled On/Off Loads Library (COO and Plug Load Appliance Identification Dataset (PLAID) [10], and a private d In terms of versatility, the proposed method can be easily applied to other da • SIMPLICITY: The traditional CUSUM methods need to repeat the detection several times, which requires nest structures [11] or the assistance of hardware ment [12] to confirm the correctness of the identification results. The pr method does not require complex mathematical calculations because the fund tal slope and numerical comparison concepts can be easily implemented.…”

mentioning

confidence: 99%

“…In terms of versatility, the proposed method can be easily applied to other datasets. • SIMPLICITY: The traditional CUSUM methods need to repeat the detection of data several times, which requires nest structures [11] or the assistance of hardware equipment [12] to confirm the correctness of the identification results. The proposed method does not require complex mathematical calculations because the fundamental slope and numerical comparison concepts can be easily implemented.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Applying the Geometric Features of Cumulative Sums to the Development of Event Detection

Tsai,

Lin

2023

Energies

View full text Add to dashboard Cite

As a result of the severe energy shortage and the greenhouse effect, experts worldwide have been devoted to solving energy management problems. Smart grid construction is an essential technology for mastering energy allocation. Smart grids enable end users to adjust their energy consumption via incentive measures, reduce the frequency of power supply instability, and improve energy efficiency. Non-intrusive load monitoring (NILM) is a vital technology for smart grid construction. One of the fundamental steps of NILM is event detection. Proper event detection can increase the accuracy of load identification. Among traditional methods, especially the event detection method developed with the CUSUM method, although the accuracy is reasonable, the precision, recall, and f1 score are not relatively better. Thus, there is an opportunity to improve the performance of CUSUM. Additionally, many studies focus on the step-like event, but the long-transient event is often overlooked in event detection. Therefore, in this study, it was observed that when the transient current deviates from the steady-state current, the transient current can be regarded as a key indicator for event detection. With this observation, a method is proposed to convert the root mean square (RMS) current into a cumulative sum (CUSUM) diagram method and identify turning points representing events from the CUSUM geometry. Once the slope of the turning point has been determined, event detection is achieved. Compared with traditional methods, the proposed method is easy to implement, its recognition rate can reach around 98%, and the window length is reduced from 5 s to 3 s.

show abstract

An Event Detection Approach Based on Improved CUSUM Algorithm and Kalman Filter

Cited by 13 publications

References 9 publications

Non-Intrusive Load Identification Based on Retrainable Siamese Network

Non-Intrusive Load Identification Based on Retrainable Siamese Network

A Non-Intrusive Residential Electric Bicycle Load Monitoring Method Based on Hybrid Feature Bitmap and DeiT

Applying the Geometric Features of Cumulative Sums to the Development of Event Detection

Contact Info

Product

Resources

About