Load Disaggregation Through Particle Filtering of Harmonic Features

A new generation of smart meters are called cognitive meters, which are essentially based on Artificial Intelligence (AI) and load disaggregation methods for Non-Intrusive Load Monitoring (NILM). Thus, modern NILM may recognize appliances connected to the grid during certain periods, while providing much more information than the traditional monthly consumption. Therefore, this article presents a new load disaggregation methodology with microscopic characteristics collected from current and voltage waveforms. Initially, the novel NILM algorithm—called the Power Signature Blob (PSB)—makes use of a state machine to detect when the appliance has been turned on or off. Then, machine learning is used to identify the appliance, for which attributes are extracted from the Conservative Power Theory (CPT), a contemporary power theory that enables comprehensive load modeling. Finally, considering simulation and experimental results, this paper shows that the new method is able to achieve 95% accuracy considering the applied data set.

This paper presents a complete real-time implementation of a Non-Intrusive Appliance Load Monitoring (NIALM) system that, is robust under residential voltage level fluctuations. Existing NIALM techniques rely on multiple measurements taken at high sampling rates, but, only have been proven in simulated environments without even considering the effect of residential voltage level fluctuations — which is a severe problem in power systems of most developing countries like Sri Lanka. In contrast, through the NIALM method proposed in this paper, accurate load monitoring results were obtained in realtime using only smart meter measurements taken at a low sampling rate from a real appliance setup under residential voltage level fluctuations. In the proposed NIALM method, initially in the learning phase, a properly constructed MATLABTM Graphical User Interface (GUI) was used to acquire signals of each appliance active power consumption and voltage levels. Then, obtained active power measurements were separated into subspace components (SCs) via the Karhunen Loeve' Expansion (KLE) while also taking the voltage variations into account. Using those SCs, a unique information rich appliance level signature database was constructed and it was then used to obtain the signatures for all possible device combinations. Next, a separate GUI was designed to identify the turned ON appliance combination in the current time window using the pre-constructed signature databases, after reading the total residential active power consumption and the supply voltage. To validate the proposed real-time NIALM implementation, data from a laboratory arrangement consisting of ten household appliances was used. From the results, it was found that the proposed method is capable of accurately identifying the turned on appliances even under severe residential supply voltage level fluctuations.

Non-Intrusive Load Monitoring (NILM) is an efficient way for energy disaggregation, as it can identify and monitor power consumption of downstream appliances or equipment from the aggregated data acquired from a single electricity metering point. There are many researches and applications of NILM in residential load disaggregation, but very few are applied on industrial load so far. This paper studies the industrial load disaggregation via NILM based on on-situ monitoring energy consumption data from one factory. The factorial hidden Markov model (FHMM) is applied for load disaggregation of five industrial equipment in the factory with the active power and reactive power data synchronously sampled at the rate of 1 Hz. This is the first attempt of using FHMM with both active power and reactive power as outputs for modeling industrial load in this field of NILM, and the promising results demonstrate its effectiveness for industrial load disaggregation.

Renewable energy sources are slowly but surely supplementing conventional sources of energy. These energy sources create a large number of micro-grids which become a part of the main grid. Smart meters are essential components in smart micro-grids and smart grids. Together they form a complex system which has become today an attractive area of research world-wide in view of enormous benefits of reliability and safety of power supply economically. Several studies in smart meter applications have shown that in residential buildings, energy consumption can be reduced up to 15% with better management. For this, a non-intrusive appliance load monitoring (NIALM) technique has been advocated which enables appliance identification to help better energy management. The identification is done using load signatures with appropriate algorithm. Several features of load signatures ranging from voltage and current profiles (steady states and transients) to a plethora of features such as active power (P) and reactive power (Q), power factor (pf), harmonic components (h), magnitudes of h (mh), current waveform (CW), eigen values, switching transient waveform, instantaneous admittance waveform, etc have been used in NIALM. The algorithms used vary from a `single algorithm' to `multiple algorithms', the latter used in `Committee Decision Mechanism' (CDM) in which majority of `votes' (i.e., agreement), `cast' by each of the algorithms, decides the final result of appliances identified. This scenario presents a serious difficulty with regard to choice of features and algorithms, besides the possibility of increasing the hardware and software costs of smart meters. The motivation for the study in this paper is provided by this scenario. The basic objective of this paper is to investigate the possibility of including only a limited number of features as load signature of appliances, and the use of only a single algorithm to effectively implement NIALM without any ambiguity. Results of our study so far indicate that generally only four features of P, Q, h and mh are sufficient for detection of appliances in operation; however, in some cases (~>10%), the additional feature, CW, may be needed for final identification.. The experiments conducted so far yielded unambiguous identification of appliances and the results are encouraging enough for possible use in practice for residential loads only.

Non-intrusive load monitoring by using active and reactive power in additive Factorial Hidden Markov Models

Non-Intrusive Load Monitoring (NILM) relies on the extraction of meaningful features from electrical signals to effectively disaggregate power consumption. Traditional NILM methods often focus on low-frequency power features, while recent advancements explore more sophisticated signal processing techniques. This study investigates two feature extraction approaches based on sinusoidal current and voltage waveforms. First, the impact of using only apparent power and phase angle is analyzed, followed by an evaluation of harmonic components alone. The experimental setup included both linear and non-linear electrical appliances to ensure that the proposed approach could handle a wide range of load characteristics and accurately reflect realistic operating conditions. The results indicate that the best performance is achieved by combining these features into a single method, which constitutes the first approach. The findings provide insights into the effectiveness of these feature sets and their potential advantages over existing NILM techniques.

Deep attention and generative neural networks for nonintrusive load monitoring

Nonintrusive load monitoring (NILM), sometimes referred to as load disaggregation, is the process of determining what loads or appliances are running in a house from analysis of the power signal of the whole-house power meter. As the popularity of NILM grows, we find that there is no consistent way the researchers are measuring and reporting accuracies. In this short communication, we present a unified approach that would allow for consistent accuracy testing.

Sequence to point learning based on bidirectional dilated residual network for non-intrusive load monitoring

In order to enable demand response schemes for residential and industrial users, it is crucial to be able to predict and monitor each component of the total power consumption of a household or of an industrial site over time. We used the cross-validation method which is a model validation technique for assessing how the results of a statistical analysis will generalize to an independent data set. It is mainly used in settings where the goal is prediction, and one wants to estimate how accurately a predictive model will perform in practice. We exploit Non-Intrusive Load Monitoring (NILM) techniques in order to provide behavior patterns of the variables identified. This work presents a review Non-Intrusive Load Monitoring (NILM) techniques and describe the results of recognition patterns used for the identification of electrical devices. The proposed method has been validated on an experimental setting and using direct measurements of appliances consumption, proving that it allows achieving a high level of accuracy in load disaggregation.

The present methods used to calibrate an active power or energy meter device under test (DUT) under nonsinusoidal conditions are based on a limited number of current and voltage waveforms and do not exercise the dynamic range of the DUT. After reviewing a method recently developed at the National Physical Laboratory (NPL) to exercise the dynamic range of a DUT under sinusoidal and nonsinusoidal conditions for specified current and voltage waveforms, the paper reports on the performance of the DUT under nonsinusoidal conditions measured using the NPL method. Experimental results: 1) verify theoretical predictions that the active power fractional full-scale (FS) error depends on both the phase-angle group between the current and voltage waveforms and the phase angle between the harmonics and the fundamental of both the current and voltage waveforms and 2) show that the active power fractional FS error for sinewave excitation can be larger than that for nonsinusoidal conditions

The objective of this paper is to present an approach for isolating the harmonic contents in both voltage and current waveforms of the montage feeder of Gharb Talkha substation (60/11 KV). A novel technique using Discrete Wavelet transform (DWT) for the analysis of the waveforms harmonics content At the beginning the substation is simulated using Simulink toolbox in Matlab program with and without the presence of capacitor bunk. The obtained voltage and current waveforms are compared to the actual data. The proposed model is used to study the effect of replacing the capacitor bank with single tuned parallel passive filter. The resulting current and voltage waveforms are analyzed using the proposed DWT technique. The analysis showed that the Total Harmonic Distortion (THD) of both voltage and current waveforms is improved as well as the power factor.

What we measure, we can improve. In accordance to this approach, Indian Institute of Science (IISc), Bangalore has developed a Micro-grid Monitoring System in the campus through the installation of Smart Meters, covering almost 250 nodes including substations, centers, departments, administration, hostels and other utilities. This will help the institute in various ways such as capacity planning, substation loading, phase imbalance correction, over-voltage monitoring, billing and so on. Smart Meters measure the power consumption at a single point in the building giving a picture of the energy consumption of the building as a whole. It is necessary to also understand the scenario of the constituent loads at the point where the smart meter is installed so that ways could be found to reduce consumption. Personalised, concise and reliable feedback providing appliance level breakdown of energy consumption in the premises is the key in implementing energy efficiency programs. Taking this into consideration the area of Non Intrusive Load Monitoring (NILM) was explored. In NILM the aggregate smart meter data is separated into constituent loads by machine learning techniques. The NILM system is trained through previous data sets and then the algorithm will disaggregate the total power into individual appliances based on its experience. A benchmark NILM algorithm called Factorial Hidden Markov Model was used for proper load disaggregation. Finally an attempt was made to develop a Smartphone app to visualize results and bring the data to the people.

Pantograph arcing with AC supply generates transients, cause asymmetries and distortion in supply voltage and current waveforms and can damage the pantograph and the overhead contact line. The asymmetry generates a net dc component and harmonics, which propagate within the traction power and signalling system and causes electromagnetic interference. Unlike DC-fed systems (Part I), the arcing in ac supply is complex because of the zero crossing of currents and voltages. In this paper, we discuss the mechanisms of sliding contact and arcing between pantograph-contact wire using the experimental setup described in Part I. Influences of various parameters and test conditions on arcing phenomenon and their signature patterns on the supply voltage and current waveforms are presented. It is shown how the arcing mechanism and corresponding asymmetry in the voltage and current waveforms are governed by line speed, current, supply voltage, inductive load, and pantograph material. The asymmetry in the current waveform is mainly due to the difference in the duration of successive zero-current regions and uneven distortion of the waveshapes. This, in turn, creates the asymmetry in the voltage waveform. The findings presented in this paper could be beneficial for coming up with appropriate mitigation techniques from the electromagnetic interference due to pantograph arcing in AC traction systems.

The use of electrical energy in remote areas must be carried out efficiently. This study proposed a load monitoring method in remote areas. This study developed a Non-Intrusive Load Monitoring (NILM) based on Data-Flow Programming (DFP) by applying a bagging decision tree algorithm to conduct load disaggregation. This study built the DFP and the Graphical User Interface (GUI) in LabVIEW connected to power sensor ADE9153A on Arduino UNO via serial communication. This experiment was conducted on the LabVIEW 2020 running on an Intel i5 2400-3.1 GHz CPU, 16 GB RAM, and 64-bit operating system computer. This study produced a good performance of NILM with 0.9617 of accuracy and 0.9728 of f1-score. The proposed method of the NILM process was suitable for electricity in remote areas because the DFP used in the algorithm is easy to understand, easy to operate, and inexpensive to build. Finally, the NILM technique can improve the efficiency of used electrical energy in remote areas. By applying NILM, the operator can determine the priority of which devices should be ON or OFF at a particular time as needed. In addition, the NILM can contribute to the balancing of small and weak microgrids in scenarios of high renewable energy penetration.