Non-intrusive load monitoring system performance over a range of low frequency sampling rates

Author(s):  
Bohao Huang ◽  
Mary Knox ◽  
Kyle Bradbury ◽  
Leslie M. Collins ◽  
Richard G. Newell
ACTA IMEKO ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 139
Author(s):  
Barbara Cannas ◽  
Sara Carcangiu ◽  
Daniele Carta ◽  
Alessandra Fanni ◽  
Carlo Muscas ◽  
...  

Non-Intrusive Load Monitoring (NILM) allows providing appliance-level electricity consumption information and decomposing the overall power consumption by using simple hardware (one sensor) with a suitable software. This paper presents a low-frequency NILM-based monitoring system suitable for a typical house. The proposed solution is a hybrid event-detection approach including an event-detection algorithm for devices with a finite number of states and an auxiliary algorithm for appliances characterized by complex patterns. The system was developed using data collected at households in Italy and tested also with data from BLUED, a widely used dataset of real-world power consumption data. Results show that the proposed approach works well in detecting and classifying what appliance is working and its consumption in complex household load dataset.


Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 442
Author(s):  
Marcin Jaraczewski ◽  
Ryszard Mielnik ◽  
Tomasz Gębarowski ◽  
Maciej Sułowicz

High requirements for power systems, and hence for electrical devices used in industrial processes, make it necessary to ensure adequate power quality. The main parameters of the power system include the rms-values of the current, voltage, and active and reactive power consumed by the loads. In previous articles, the authors investigated the use of low-frequency sampling to measure these parameters of the power system, showing that the method can be easily implemented in simple microcontrollers and PLCs. This article discusses the methods of measuring electrical quantities by devices with low computational efficiency and low sampling frequency up to 1 kHz. It is not obvious that the signal of 50–500 Hz can be processed using the sampling frequency of fs = 47.619 Hz because it defies the Nyquist–Shannon sampling theorem. This theorem states that a reconstruction of a sampled signal is only guaranteed possible for a bandlimit fmax < fs, where fmax is the maximum frequency of a sampled signal. Therefore, theoretically, neither 50 nor 500 Hz can be identified by such a low-frequency sampling. Although, it turns out that if we have a longer period of a stable multi-harmonic signal, which is band-limited (from the bottom and top), it allows us to map this band to the lower frequencies, thus it is possible to use the lower sampling ratio and still get enough precise information of its harmonics and rms value. The use of aliasing for measurement purposes is not often used because it is considered a harmful phenomenon. In our work, it has been used for measurement purposes with good results. The main advantage of this new method is that it achieves a balance between PLC processing power (which is moderate or low) and accuracy in calculating the most important electrical signal indicators such as power, RMS value and sinusoidal-signal distortion factor (e.g., THD). It can be achieved despite an aliasing effect that causes different frequencies to become indistinguishable. The result of the research is a proposal of error reduction in the low-frequency measurement method implemented on compact PLCs. Laboratory tests carried out on a Mitsubishi FX5 compact PLC controller confirmed the correctness of the proposed method of reducing the measurement error.


2021 ◽  
Vol 17 (3) ◽  
pp. 1-20
Author(s):  
Vanh Khuyen Nguyen ◽  
Wei Emma Zhang ◽  
Adnan Mahmood

Intrusive Load Monitoring (ILM) is a method to measure and collect the energy consumption data of individual appliances via smart plugs or smart sockets. A major challenge of ILM is automatic appliance identification, in which the system is able to determine automatically a label of the active appliance connected to the smart device. Existing ILM techniques depend on labels input by end-users and are usually under the supervised learning scheme. However, in reality, end-users labeling is laboriously rendering insufficient training data to fit the supervised learning models. In this work, we propose a semi-supervised learning (SSL) method that leverages rich signals from the unlabeled dataset and jointly learns the classification loss for the labeled dataset and the consistency training loss for unlabeled dataset. The samples fit into consistency learning are generated by a transformation that is built upon weighted versions of DTW Barycenter Averaging algorithm. The work is inspired by two recent advanced works in SSL in computer vision and combines the advantages of the two. We evaluate our method on the dataset collected from our developed Internet-of-Things based energy monitoring system in a smart home environment. We also examine the method’s performances on 10 benchmark datasets. As a result, the proposed method outperforms other methods on our smart appliance datasets and most of the benchmarks datasets, while it shows competitive results on the rest datasets.


2021 ◽  
Vol 13 (2) ◽  
pp. 693
Author(s):  
Elnaz Azizi ◽  
Mohammad T. H. Beheshti ◽  
Sadegh Bolouki

Nowadays, energy management aims to propose different strategies to utilize available energy resources, resulting in sustainability of energy systems and development of smart sustainable cities. As an effective approach toward energy management, non-intrusive load monitoring (NILM), aims to infer the power profiles of appliances from the aggregated power signal via purely analytical methods. Existing NILM methods are susceptible to various issues such as the noise and transient spikes of the power signal, overshoots at the mode transition times, close consumption values by different appliances, and unavailability of a large training dataset. This paper proposes a novel event-based NILM classification algorithm mitigating these issues. The proposed algorithm (i) filters power signals and accurately detects all events; (ii) extracts specific features of appliances, such as operation modes and their respective power intervals, from their power signals in the training dataset; and (iii) labels with high accuracy each detected event of the aggregated signal with an appliance mode transition. The algorithm is validated using REDD with the results showing its effectiveness to accurately disaggregate low-frequency measured data by existing smart meters.


Author(s):  
G Kalairassan ◽  
M Boopathi ◽  
Rijo Mathew Mohan

Author(s):  
Qiuzhan Zhou ◽  
Jiahui Wei ◽  
Mingyu Sun ◽  
Cong Wang ◽  
Jing Rong ◽  
...  

2012 ◽  
Vol 182-183 ◽  
pp. 753-757
Author(s):  
Xing Ming Xiao ◽  
Na Ma

According to the working principle of load monitored oil pressure, in order to real-time monitor the actual load of auxiliary shift, and make the execution of alarming on the malfunctions in the working state of the equipment concerned, we designed a monitor system of auxiliary shift based on Labview[1]. This system can provide guarantee of the safety lifting. So the formation, design principle, hardware and software design well be introduced in this article.


2012 ◽  
Vol 134 (3) ◽  
Author(s):  
M. Torres ◽  
F. J. Muñoz ◽  
J. V. Muñoz ◽  
C. Rus

The Guidelines for the Assessment of Photovoltaic Plants provided by the Joint Research Centre (JRC) and the International Standard IEC 61724 recommend procedures for the analysis of monitored data to asses the overall performance of photovoltaic (PV) systems. However, the latter do not provide a well adapted method for the analysis of stand-alone photovoltaic systems (SAPV) with charge regulators without maximum power point tracker (MPPT). In this way, the IDEA Research Group has developed a new method that improves the analysis performance of these kinds of systems. Moreover, it has been validated an expression that compromises simplicity and accuracy when estimating the array potential in this kind of systems. SAPV system monitoring and performance analysis from monitored data are of great interest to engineers both for detecting a system malfunction and for optimizing the design of future SAPV system. In this way, this paper introduces an online monitoring system in real time for SAPV applications where the monitored data are processed in order to provide an analysis of system performance. The latter, together with the monitored data, are displayed on a graphical user interface using a virtual instrument (VI) developed in LABVIEW®. Furthermore, the collected and monitored data can be shown in a website where an external user can see the daily evolution of all monitored and derived parameters. At present, three different SAPV systems, installed in the Polytechnic School of University of Jaén, are being monitorized and the collected data are being published online in real time. Moreover, a performance analysis of these stand-alone photovoltaic systems considering both IEC 61724 and the IDEA Method is also offered. These three systems use the charge regulators more widespread in the market. Systems #1 and #2 use pulse width modulation (PWM) charge regulators, (a series and a shunt regulator, respectively), meanwhile System #3 has a charge regulator with MPPT. This website provides a tool that can be used not only for educational purposes in order to illustrate the operation of this kind of systems but it can also show the scientific and engineering community the main features of the system performance analysis methods mentioned above. Furthermore, it allows an external user to download the monitored and analysis data to make its own offline analysis. These files comply with the format proposed in the standard IEC 61724. The SAPV system monitoring website is now available for public viewing on the University of Jaén. (http://voltio.ujaen.es/sfa/index.html).


Sign in / Sign up

Export Citation Format

Share Document