A mixed-integer programming approach for industrial non-intrusive load monitoring

Energy consumption data of individual appliances at home can be obtained by nonintrusive appliance load monitoring (NILM) which aims at disaggregating total amount of power consumption into that of each appliance. NILM can be implemented utilizing pattern recognition algorithms, one of which is Factorial Hidden Markov Model (FHMM) that was employed in previous researches. In spite of the known importance of real-time disaggregation system, it has not been actively studied compared to the batch system. This study suggests a prototype of real-time NILM system via ZigBee smart plug and FHMM algorithm.

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.

Unsupervised approach for load disaggregation with devices interactions

Non-intrusive load monitoring (NILM) is to estimate individual appliance’s power consumption from aggregated smart meter data, which is useful for optimized energy management and provisioning of customized services. While deep learning (DL) has achieved state-of-the-art NILM performance, it is still constrained by the dependency on large amounts of data and intensive computations on training. In this paper, we propose a pre-training approach to address the generalization of DL models for NILM. We develop a meta-learning based approach and an ensemble learning based approach, which pre-train a base model and then fine-tune it with few-short learning when applied to an unknown dataset. The models are validated with two real-world datasets and shown to achieve a superior transferability performance compared with traditional DL and transfer learning methods.

Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network

Non-intrusive load monitoring (NILM) considers different approaches for disaggregating energy consumption in residential, tertiary, and industrial buildings to enable smart grid services. The main feature of NILM is that it can break down the bulk electricity demand, as recorded by conventional smart meters, into the consumption of individual appliances without the need for additional meters or sensors. Furthermore, NILM can identify when an appliance is in use and estimate its real-time consumption based on its unique consumption patterns. However, NILM is based on machine learning methods and its performance is dependent on the quality of the training data for each appliance. Therefore, a common problem with NILM systems is that they may not generalize well to new environments where the appliances are unknown, which hinders their widespread adoption and more significant contributions to emerging smart grid services. The main goal of the presented research is to apply a domain adversarial neural network (DANN) approach to improve the generalization of NILM systems. The proposed semi-supervised algorithm utilizes both labeled and unlabeled data and was tested on data from publicly available REDD and UK-DALE datasets. The results show a improvement in generalization performance on highly uncorrelated data, indicating the potential for real-world applications.

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 is widely appreciated technique for managing segregated-level energy-efficiency. Event detection algorithms play a crucial role in non-intrusive load monitoring applications. This paper proposes a new unsupervised hybrid event detection algorithm that tracks the difference and standard deviation of the aggregated load data. To evaluate the performance of the proposed algorithm, simulations are carried out on 24 hours of real-world load data from a single household having diverse load elements. This paper also assessed the sensitivity of the input parameter on the performance of the proposed event detector. The proposed hybrid event detection algorithm performed well and accomplished highly promising results.

Monitoring electricity consumption in residential buildings is an important way to help reduce energy usage. Nonintrusive load monitoring is a technique to separate the total electrical load of a single household into specific appliance loads. This problem is difficult because we aim to extract the energy consumption of each appliance by only using the total electrical load. Deep transfer learning is expected to solve this problem. This paper proposes a deep neural network model based on an attention mechanism. This model improves the traditional sequence-to-sequence model with a time-embedding layer and an attention layer so that it can be better applied in nonintrusive load monitoring. In particular, the improved model abandons the recurrent neural network structure and shortens the training time, which means it is more appropriate for use in model pretraining with large datasets. To verify the validity of the model, we selected three open datasets and compared them with the current leading model. The results show that transfer learning can effectively improve the prediction ability of the model, and the model proposed in this study has a better performance than the most advanced available model.

Evaluation of regression models and Bayes-Ensemble Regressor technique for non-intrusive load monitoring

With the advancement of smart residential buildings, houseowners are increasingly interested to monitor the connected electrical loads in view of energy conservation and load management. Smart grid technology in the distribution system includes cutting-edge load monitoring applications, permitting efficient use of electrical energy. Nonintrusive load monitoring (NILM) technique is such a tool to recognize the consumption of energy for individual electrical loads in a residential system at a solitary point of measurement. In this article, an improved NILM method is proposed using a shunt passive filter installed at the source end of residential building with the help of current harmonic signature analysis. A fuzzy rule-based intelligent identification method is employed in order to detect and monitor different electrical loads considering various load features at the utility side. The major contribution of the proposed technique is the improvement in identification accuracy of household loads with multiple appliances. The connected filter additionally restricts the injected harmonics generated by the loads at the source end. The usage of the fuzzy technique also reduces the processor memory requirement than conventional machine learning techniques. Simulations backed by experimental results validate the viability of the proposed methodology.

A non-intrusive load monitoring algorithm based on real-time feature extraction and deep learning model

Non-Intrusive Load Monitoring (NILM) disaggregates appliance-level energy consumption 
from aggregate load data, offering a practical approach for analyzing household energy use 
and promoting efficiency. Event detection, a critical element in NILM, identifies state 
transitions in appliances. However, existing approaches often struggle with real-world data, 
where challenges arise from subtle load changes, high-frequency noise, and load-switching 
transients, all of which impact detection accuracy. Additionally, high computational demands 
can limit real-time applicability and reduce adaptability to varied appliance behaviors. In this 
paper, we present a multi-window cumulative sum (CUSUM) method featuring adaptive 
thresholds and variable-length windows, enhanced by a dynamic parameter adjustment 
mechanism driven by signal statistics. To address noise interference, the method integrates 
median filtering and exponentially weighted moving average (EWMA) preprocessing. 
Dynamic parameter adjustments enable adaptation to fluctuating appliance behaviors, while 
multi-window accumulation and rate-of-change analysis improve discrimination between 
genuine events and spurious fluctuations. Experimental results demonstrate the proposed 
method's superiority over conventional CUSUM and other improved methods on PLAID, 
BLUED, and private datasets, achieving F1 scores of 94.72%, 96.43%, and 91.98%, 
respectively. Its robustness across thresholds, practicality, and low computational 
requirements highlight its potential for real-world NILM applications on resource-constrained 
devices.
Keywords: NILM, event detection, multi-window, adaptive threshold, variable-length

Energy signature analysis of power appliance is the core of nonintrusive load monitoring (NILM) where the detailed data of the appliances used in houses are obtained by analyzing changes in the voltage and current. This paper focuses on developing an automatic power load event detection and appliance classification based on machine learning. In power load event detection, the paper presents a new transient detection algorithm. By turn-on and turn-off transient waveforms analysis, it can accurately detect the edge point when a device is switched on or switched off. The proposed load classification technique can identify different power appliances with improved recognition accuracy and computational speed. The load classification method is composed of two processes including frequency feature analysis and support vector machine. The experimental results indicated that the incorporation of the new edge detection and turn-on and turn-off transient signature analysis into NILM revealed more information than traditional NILM methods. The load classification method has achieved more than ninety percent recognition rate.

Energy management using non-intrusive load monitoring techniques – State-of-the-art and future research directions