Non-intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) is the method of detecting an individual device's energy signal from an aggregated energy consumption signature [1]. As existing energy meters provide very little to no information regarding the energy consumptions of individual appliances apart from the aggregated power rating, the spotting of individual appliances' energy usages by NILM will not only provide consumers the feedback of appliance-specific energy usage but also lead to the changes of their consumption behavior which facilitate energy conservation. B Neenan et al. [2] have demonstrated that direct individual appliance-specific energy usage signals lead to consumers' behavioral changes which improves energy efficiency by as much as 15%. Upon disaggregation of an energy signal, the signal needs to be classified according to the appropriate appliance. Hence, the goal of this paper is to disaggregate total energy consumption data to individual appliance signature and then classify appliance-specific energy loads using a prominent supervised classification method known as K-Nearest Neighbors (KNN). To perform this operation we have used a publicly accessible dataset of power signals from several houses known as the REDD dataset. Before applying KNN, data is preprocessed for each device. Then KNN is applied to check whether their energy consumption signature is separable or not. KNN is applied with K=5.

In this article, a new software tool named "ECCO" is introduced. This one is intended to highlight money savings made by a home electricity management system. The simulation is based on a complete database of real electricity consumption patterns of AC loads. Two case studies are particularly described to point out the relevance of the simulation results. The first one consists in postponing the power demand using the delay start function of home appliances. The second one enables to smooth the electricity consumption from a storage system coupled with a converter. The management strategy described in this article uses the difference between electricity prices in peak time and off-peak time. The results demonstrate that this strategy is currently not profitable in France, but it is much more cost-effective in countries, such as in Australia, where this gap of pricing is higher.

In today’s scenario the consumption of electricity is ever increasing and the electric grids are being upgraded to smart grids. A smart grid is an enhanced version of electrical grid where digital technology is used to communicate between utilities and consumers. This helps the users to manage the consumption of energy in a better way. Seasons play an important role in the consumption of energy as the home appliances are used based upon seasons. To achieve better energy management there arises the need for prediction. In this paper an attempt is made to use Markov Chain for the prediction of energy consumption during various seasons in a smart grid. Markov chain is one of the stochastic process which is used when random variables are considered. Since the energy consumption during various seasons are random, Markov Chain is used for prediction. The dataset is taken from Pecan Street, Austin, USA and the energy consumed from the grid is combined based on various seasons. The seasons ...

W artykule opisano proces przygotowania oraz wysyłania przez członków Studenckiego Koła Naukowego Elektroników "Amper" Akademii Tarnowskiej trzech misji balonowych. W pierwszej jego części przedstawiono ważniejsze zagadnienia związane z lotem balonu (dobór odpowiedniego osprzętu, użytego gazu czy uzyskanie niezbędnych pozwoleń). W tej części zawarto również zagadnienia związane z prognozowaniem tras przelotu, tak aby zwiększyć szanse na pozytywne przeprowadzenie całej misji. W kolejnym rozdziale opisano zarówno sprzęt projektowany przez studentów i użyty w czasie misji (radiosonda, rejestrator danych, nadajnik SSTV) jak i komercyjny (lokalizator GNSS, kamera). Kolejny rozdział opisuje oprogramowanie i osprzęt służące do monitorowania lotu balonu. W ostatnim zaprezentowano wykorzystanie systemu SondeHub. System ten umożliwia pasjonatom śledzenie tras przelotu balonów zarówno tych wysyłanych przez stacje meteorologiczne jak i amatorskich. Dodatkowo posiada system bazodanowy przechowujący komplet danych wysyłanych przez radiosondę (zarówno lokalizacyjnych jak i telemetrycznych). Artykuł stanowi notę aplikacyjną i może być pomocny dla osób chcących zrealizować własne misje stratosferyczne.

I am interested in making our built environment more operationally efficient and robust through the use of information technologies, so that it can better deal with future resource constraints and a changing environment. In other words, I am interested in providing buildings, and other man-made structures that support our urban environment, with the ability to sense, plan and act autonomously, just as many living organisms do.

Increasing population indicates that energy demands need to be managed in the residential sector. Prior studies have reflected that the customers tend to reduce a significant amount of energy consumption if they are provided with appliancelevel feedback. This observation has increased the relevance of load monitoring in today’s tech-savvy world. Most of the previously proposed solutions claim to perform load monitoring without intrusion, but they are not completely nonintrusive. These methods require historical appliance-level data for training the model for each of the devices. This data is gathered by putting a sensor on each of the appliances present in the home which causes intrusion in the building. Some recent studies have proposed that if we frame NonIntrusive Load Monitoring (NILM) as a multi-label classification problem, the need for appliance-level data can be avoided. In this paper, we propose Multi-label Restricted Boltzmann Machine(ML-RBM) for NILM and report an experim...

Energy disaggregation is to discover the energy consumption of individual appliances from their aggregated energy values. To solve the problem, most existing approaches rely on either appliances' signatures or their state transition patterns, both hard to obtain in practice. Aiming at developing a simple, universal model that works without depending on sophisticated machine learning techniques or auxiliary equipments, we make use of easily accessible knowledge of appliances and the sparsity of the switching events to design a Sparse Switching Event Recovering (SSER) method. By minimizing the total variation (TV) of the (sparse) event matrix, SSER can effectively recover the individual energy consumption values from the aggregated ones. To speed up the process, a Parallel Local Optimization Algorithm (PLOA) is proposed to solve the problem in active epochs of appliance activities in parallel. Using real-world trace data, we compare the performance of our method with that of the state-of-the-art solutions, including Least Square Estimation (LSE) and iterative Hidden Markov Model (HMM). The results show that our approach has an overall higher detection accuracy and a smaller overhead.

Streszczenie. podczas realizowania obecnych misji wojskowych obserwuje się gwałtowny wzrost znaczenia improwizowanych ładunków wybuchowych ieD. powodem tak dużego zainteresowania terrorystów tymi rozwiązaniami jest łatwy dostęp do broni oraz tanich i szeroko osiągalnych systemów komunikacji. W celu zminimalizowania działania ładunków ieD, w urządzeniach odpowiedzialnych za monitorowanie środowiska elektromagnetycznego wprowadza się nowe metody skanowania i wykrywania sygnałów radiowych. Wpływają one na zwiększenie jakości odbieranych danych oraz skracają czas detekcji, a tym samym czas reakcji całego systemu. Dlatego też celem niniejszego artykułu jest przedstawienie metody skanowania sygnałów radiowych. Do zrealizowania tego zadania zaproponowano procedurę detekcji, którą następnie sprawdzono na stanowisku pomiarowym. praca składa się z czterech rozdziałów. W pierwszym opisano założenia oraz ideę działania proponowanego systemu skanowania sygnałów. przedstawiona w nim metoda składa się z dwóch części: detektora tła szumowego i detektora energii. W następnym rozdziale zaprezentowano stanowisko pomiarowe. opisano podstawowe parametry odbiornika, szczególnie zwracając uwagę na zastosowany w nim tor obliczania widma sygnału. Następnie zaprezentowano sposób wykonywania testów. W rozdziale trzecim przedstawiono wyniki przeprowadzonych testów, znajdują się tam podstawowe charakterystyki prawdopodobieństwa fałszywego alarmu i detekcji dla różnych trybów pracy. ostatni rozdział podsumowuje uzyskane wyniki i przedstawia wnioski.

Przedstawiono bezprzewodową sieć sensorową, pobierającą i przekazującą informacje z czujników temperatury i oświetlenia sterowanych głosem. Funkcjonalność systemu może zostać wykorzystana do sterowania urządzeniami automatyki domowej. System składa się z trzech zasadniczych elementów: koordynatora sieci ZigBee, urządzenia końcowego (pomiarowego) wyposażonego w czujniki światła i temperatury oraz komputera PC. Użytkownik może zarządzać systemem za pomocą trzech interfejsów: komend głosowych rejestrowanych przez mikrofon, wyświetlacza TFT z panelem dotykowym oraz komputera PC z opracowanym oprogramowaniem. W koordynatorze zastosowano uproszczony algorytm rozpoznawania izolowanych słów przy pomocy współczynników LPC (Linear Predictive Coding). System został skonstruowany na popularnych mikrokontrolerach firmy STM z nowoczesnym mikroprocesorem ARM Cortex-M3.

The following article presents the results obtained in experiences that use the Impulse Frequency Response Analysis (IFRA) method with a transformer in service. The IFRA method has been implemented in order to transform the transient signals to the frequency domain using Discrete Fourier Transform (DFT). However, it can be considered that the DFT is not the most suitable tool for this type of analysis, since, by definition, this tool is useful for processing stationary signals. Taking that into consideration, the analysis of transient signals could be hypothetically improved by using continuous wavelet transform (CWT), given their variable time/frequency resolution. The analysis of transient signals in Wavelet domain has improved the repeatability of the frequency response curves, as it has been observed in experimental results. The proposed on-line IFRA method, based on Wavelet transform, was validated under load and noload conditions on a 150 kVA three-phase transformer 13200/225 Volts, in the Campus of the

Indoor energy consumption can be understood by breaking overall power consumption down into individual components and appliance activations. The clas- sification of components of energy usage is known as load disaggregation or ap- pliance recognition. Most of the previous efforts address the separation of devices with high energy demands. In many contexts though, such as an office, the devices to separate are numerous, heterogeneous, and have low consumptions. The disag- gregation problem becomes then more challenging and, at the same time, crucial for understanding the user context. In fact, from the disaggregation one can deduce the number of people in an office room, their activities, and current energy needs. In this paper, we review the characteristics of office appliances load disaggregation efforts. We then illustrate a proposal for a classification model based on Recur- rent Neural Network (RNN). RNN is used to infer device activation from aggre- gated energy consumptions. T...

In the current energy ecosystem, the need for a Hybrid Appliance Load Monitoring System (HALMS) to establish a smarter grid and energy infrastructure is undeniable. The increasing popularity of the Internet of Things (IoT) has suddenly pushed the demand for smart and connected devices. This review introduces the term smart plug as a device that uses IoT for establishing HALMS. These smart plugs are a handy solution to make the so-called 'dumb' devices smart. The strategy of smart plugs to enhance the energy management experience in connected spaces is presented. This study extensively highlights the current smart plug technologies and the relevant activities and limitations that need to overcome the requirements of HALMS.

In the current energy ecosystem, the need for a Hybrid Appliance Load Monitoring System (HALMS) to establish a smarter grid and energy infrastructure is undeniable. The increasing popularity of the Internet of Things (IoT) has suddenly pushed the demand for smart and connected devices. This review introduces the term smart plug as a device that uses IoT for establishing HALMS. These smart plugs are a handy solution to make the so-called ‘dumb’ devices smart. The strategy of smart plugs to enhance the energy management experience in connected spaces is presented. This study extensively highlights the current smart plug technologies and the relevant activities and limitations that need to overcome the requirements of HALMS.

Non-intrusive load monitoring (NILM) is the process of obtaining appliance-level data from a single metering point, measuring total electricity consumption of a household or a business. Appliance-level data can be directly used for demand response applications and energy management systems as well as for awareness raising and motivation for improvements in energy efficiency. Recently, classical machine learning and deep learning (DL) techniques became very popular and proved as highly effective for NILM classification, but with the growing complexity these methods are faced with significant computational and energy demands during both their training and operation. In this paper, we introduce a novel DL model aimed at enhanced multilabel classification of NILM with improved computation and energy efficiency. We also propose an evaluation methodology for comparison of different models using data synthesized from the measurement datasets so as to better represent real-world scenarios. Compared to the state-of-the-art, the proposed model has its energy consumption reduced by more than 23% while providing on average approximately 8 percentage points in performance improvement when evaluating on data derived from REFIT and UK-DALE datasets. We also show a 12 percentage point performance advantage of the proposed DL based model over a random forest model and observe performance degradation with the increase of the number of devices in the household, namely with each additional 5 devices, the average performance degrades by approximately 7 percentage points. Index Terms-non-intrusive load monitoring (NILM), deep learning (DL), convolutional recurrent neural network (CRNN), multi-label classification, load profiling 4https://tinyurl.com/home-consumption-statistic (accessed 4.3.2024)

In practice, a standard energy meter can only capture the overall electricity consumption and estimating electricity consumption pattern of various appliances from the overall consumption pattern is complicated. Therefore, the Non-Intrusive Appliance Load Monitoring (NIALM) technique can be applied to trace electricity consumption from each appliance in a monitored building. However, the method requires a detailed, second-bysecond power consumption data which is commonly not available without the use of high specification energy meter. Hence, this paper analyzes the impact of different time sampling data in estimating the energy consumption pattern of various appliances through NIALM method. This is so that consumers will have an overview of time sampling data which is required in order to apply the NIALM technique. As for the analysis, airconditioning systems and fluorescent lamps were used in the experimental setup. One minute sample rate was the minimum time interval required by NIALM carried out in this analysis. Through the study presented in this paper, it can be established that higher time sampling led to uncertain appliance detection and low accuracy.

Energy disaggregation algorithms disintegrate aggregate demand into appliance-level demands. Among various energy disaggregation approaches, non-intrusive load monitoring (NILM) algorithms requiring a single sensor have gained much attention in recent years. Various machine learning and optimization-based NILM approaches are available in the literature, but bulk training data and high computational time are their respective drawbacks. Considering these drawbacks, we devised an event matching energy disaggregation algorithm (EMEDA) for NILM of multistate household appliances using smart meter data. Having limited training data, K-means clustering was employed to estimate appliance power states. These power states were accumulated to generate an event database (EVD) containing all combinations of appliance operations in their various states. Prior to matching, the test samples of aggregate demand events were decreased by event-driven data compression for computational effectiveness. T...

Based on neural network and machine learning, we apply the energy disaggregation for both classification (prediction on usage time) and estimation (prediction on usage amount) on 150 AMI (Advanced Metering Infrastructure) smart meters and a small amount of HEMS (Home Energy Management System) smart plugs in a community in New Taipei City, Taiwan. The aim of this paper is to clarify how we lower the cost, obtain the model of appliance usage from only a small portion of households, improve it with simple questionnaire, and generalize it for prediction on collective households. Our investigation demonstrates the benefits and various possibilities for power suppliers and the government, and won the Elite Award in the Presidential Hackathon 2020, Taiwan.

Source separation of whole-home electrical consumption also known as energy disaggregation plays a crucial role in energy savings and sustainable development. One important approach towards accurate energy disaggregation is based on sparse code learning. The sparsity-based source separation algorithms allow to build models that explicitly generalize across multiple different devices of the same category. While this method has recently been investigated, yet the importance of the degree of sparseness given by the regularization parameter is rarely considered. In this paper we aim at investigating the performance of learning representations from the aggregated electrical load signal with sparse models for energy disaggregation. In particular we focus our study on the influence of the regularization parameter in the overall approach. The computational experiments yielded in real data from home electrical energy consumption show that for several degrees of sparseness a reliable scheme for energy disaggregation can be obtained with statistical significance.

This paper looks at the extraction of trends of household electrical seasonal consumption via load disaggregation. With the proviso that data for the several home devices can be embedded in a tensor, non-negative multi-way array factorization is performed in order to extract the most relevant components. First, in the decomposition step the decomposed signals are incorporated in the test signal consisting of the whole-home measured consumption. Second, the disaggregated data corresponding to each electrical device is obtained by factorizing the associated matrix through the learned model. Finally, we evaluate the performance of load disaggregation by the supervised method and study the trends along several years and across seasons. Towards this end, computational experiments were yielded using real-world data from a household electrical consumption measurements along several years. While breaking down the whole house energy consumption into appliance level gives less accurate estimates in the late years, we empirically show the adequacy of the method for handling the earlier years and the estimates of the underlying seasonal trend-cycle.

This paper looks at the extraction of trends of household electrical seasonal consumption via load disaggregation. With the proviso that data for the several home devices can be embedded in a tensor, non-negative multi-way array factorization is performed in order to extract the most relevant components. First, in the decomposition step the decomposed signals are incorporated in the test signal consisting of the whole-home measured consumption. Second, the disaggregated data corresponding to each electrical device is obtained by factorizing the associated matrix through the learned model. Finally, we evaluate the performance of load disaggregation by the supervised method and study the trends along several years and across seasons. Towards this end, computational experiments were yielded using real-world data from a household electrical consumption measurements along several years. While breaking down the whole house energy consumption into appliance level gives less accurate estimates in the late years, we empirically show the adequacy of the method for handling the earlier years and the estimates of the underlying seasonal trend-cycle.

Non-intrusive load monitoring (NILM) is a promising approach to provide energy consumption monitoring of electrical appliances and analysis of current and voltage data with less instrumentation. This paper proposes an electrical load classification model using support vector machine (SVM). SVM was chosen to keep the computational cost low and be able to implement an embedded system. The SVM model was utilized to classify the on/off state of air conditioners, light bulbs, other uncategorized electronics, and their combinations. It utilizes low-frequency sampling data captured every minute, or at a 0.0167 Hz rate. Utilization change in active and reactive power was used as a feature in the model training. The optimal kernel for the model was the radial basis function (RBF) kernel with C and gamma values of 88.587 and 2.336 as hyperparameters, producing a highly accurate model. In testing with real-time conditions, the model classified the on/off state of the electrical loads with 0.93...

Omówiono testery liczników energii elektrycznej podłączonych do sieci energetycznej i kluczowy problem tych testerów -specyfikację dokładności testera w szerokim zakresie dynamicznym napięć, prądów i mocy. Przedstawiono rozwój testerów w ciągu ostatnich kilkunastu lat i ich koncepcje do najnowszego zintegrowanego testera liczników z funkcjami testera przekładników i analizatora jakości energii. Z przedstawionej analizy wynika, że krajowe testery opracowane i produkowane w Zielonej Górze są zgodne z aktualnym stanem techniki na świecie a ich asortyment w pełni pokrywa aktualne potrzeby krajowych użytkowników bez konieczności korzystania z importu.

In Poland, approx. 95% of electrical energy is generated in a coal combustion process. Saving electrical energy gives economic effects related to the smaller fees and contributes to protection of the natural environment. Additionally, saving electrical energy should translate into our health, lesser degradation of the natural environment, or less consumption of natural deposits of energy. The paper has presented the issues related to analysis of energy consumption in a selected building object. The analyse includes the following issues − document analysis related to the building’s power, energy distribution, and power consumption of individual load and time regimes of work of receivers in the object and analysis of electrical energy which has been measured in a building. Keywords: electricity quality parameters measurement, higher harmonics of current/voltage.

W pracy zamieszczono wybrane wyniki badań dotyczące modelowania neuralnego rozwoju systemu elektroenergetycznego na bazie danych testowych IEEE RTS 96., m.in.: sposób tworzenia macierzy danych wejściowych oraz wyjściowych, sposób doboru parametrów sieci, itp. W wyniku projektowania i uczenia SSN uzyskano modele rozwoju SEE, które poddano badaniom wrażliwości m.in. na zmianę liczby warstw ukrytych oraz liczby neuronów w warstwie.

In this paper, we address the problem of predicting the usage of home appliances where a key challenge is to model the everyday routine of homeowners and the inter-dependency between the use of different appliances. In particular, given an efficient day-ahead prediction of electrical usage, home energy management systems can suggest homeowners when is the best time to run appliances in order to save cost, without violating their preferred everyday habits. To this end, we propose an agent based prediction algorithm that captures the everyday habits by exploiting their periodic features. In addition, our algorithm uses a episode generation hidden Markov model (EGH) to model the inter-dependency between appliances. We demonstrate that our approach outperforms existing methods by up to 40% in experiments based on real-world data from a prominent database of home energy usage. We also show that the computational cost of our algorithm is 100 times lower on average, compared to that of the benchmark algorithms.

Non-intrusive load monitoring (NILM), or energy disaggregation, aims to estimate individual appliance consumption from a single-point measurement without using dedicated appliance-wise sensors or sub-meters. For around three decades, signal processing, machine learning algorithms, and statistical tools have been used by researchers to propose different approaches to the problem. However, there are still many challenges to achieving a universal approach that can be applied due to the particularities of the electrical distribution network and the electrical appliances of each country. In this paper, an approach for the NILM of residential electrical energy based on digital signal processing is presented. The experimental scenarios were carried out in Argentina where there was no public dataset for the consumption of electrical appliances.

Celem pracy była próba oceny przydatności diagnostycznej sztucznych sieci neuronowych w ocenie parametrów klinicznych i scyntymammogramów w rozpoznaniu raka piersi. Porównano wynik sieci neuronowej z oceną dwóch niezależnych obserwatorów, lekarzy specjalistów medycyny nuklearnej. M Ma at te er ri ia ał ł i i m me et to od dy y: : Materiał stanowiły dane kliniczne oraz liczbowe uzyskane przez opracowanie badania scyntymammograficznego 103 pacjentów. Metodą referencyjną było badanie histopatologiczne wycinka biopsji aspiracyjnej cienkoigłowej i/lub biopsji gruboigłowej. W Wy yn ni ik ki i: : Czułość oceny dokonanej przez lekarzy w badanej populacji wyniosła 78%, a swoistość-72%. W ocenie wartości diagnostycznej sieci neuronowej uzyskano czułość-71%, a swoistość-73%. Otrzymane czułości nie różniły się istotnie statystycznie (p=0,4619). W Wn ni io os sk ki i: : Sztuczne sieci neuronowe stanowią przydatne narzędzie, wykorzystujące techniki sztucznej inteligencji we wspomaganiu rozpoznawania raka piersi przez lekarzy medycyny nuklearnej. S Sł ło ow wa a k kl lu uc cz zo ow we e: : sztuczna sieć neuronowa, scyntymammografia, rak piersi.

Stopień inż. otrzymał na Wydziale Elektrotechniki, Informatyki i Telekomunikacji w 2005r., a stopień mgr na Wydziale Mechanicznym Uniwersytetu Zielonogórskiego w roku 2008. Obecnie pracuje jako nauczyciel. Do jego zainteresowań naukowych należą: metody sztucznej inteligencji, przetwarzanie sygnałów, nauki kognitywne.

Reduction and conservation of electrical energy consumption in residential buildings is the main objective of Non-Intrusive Load Monitoring (NILM) techniques. NILM detects events and estimate the power consumption of individual appliances by analyzing the aggregate power consumption measured at the service entry. Indeed, our major contribution in this paper is to update research works on NILM methodologies by adding the most recent NILM methods proposed in the literature. In this paper we present an overview of NILM and energy disaggregation methods. Then, we discuss the challenges of this technique to provide useful recommendations for future research.

The availability of smart meters and IoT technology has opened new opportunities, ranging from monitoring electrical energy to extracting various types of information related to household occupancy, and with the frequency of usage of different appliances. Non-intrusive load monitoring (NILM) allows users to disaggregate the usage of each device in the house using the total aggregated power signals collected from a smart meter that is typically installed in the household. It enables the monitoring of domestic appliance use without the need to install individual sensors for each device, thus minimizing electrical system complexities and associated costs. This paper proposes an NILM framework based on low frequency power data using a convex hull data selection approach and hybrid deep learning architecture. It employs a sliding window of aggregated active and reactive powers sampled at 1 Hz. A randomized approximation convex hull data selection approach performs the selection of the mo...

Human behaviour and occupancy accounts for a substantial proportion of variation in the energy efficiency profile of domestic buildings. Yet while people often claim that they would like to reduce their energy bills, rhetoric frequently fails to match action due to the effort involved in understanding and changing deeply engrained energy consumption habits. Here, we present and, through dedicated experiments, test in-house developed software to remotely identify appliance energy usage within buildings, using energy equipment which could be placed at the electricity meter location. Furthermore, we monitor and compare the occupancy of the location under study through Ultra-Wideband (UWB) radar technology and compare the resulting data with those received from the power monitoring software, via time synchronization. These signals when mapped together can potentially provide both occupancy and specific appliances power consumption, which could enable energy usage segregation on a yet impossible scale as well as usage attributable to occupancy behaviour. Such knowledge forms the basis for the implementation of automated energy saving actions based on a households unique energy profile.

Smart meters are used to measure the energy consumption of households. Specifically, within the energy consumption task, a smart meter must be used for load forecasting, the reduction in consumer bills as well as the reduction in grid distortions. Smart meters can be used to disaggregate the energy consumption at the device level. In this paper, we investigated the potential of identifying the multimedia content played by a TV or monitor device using the central house’s smart meter measuring the aggregated energy consumption from all working appliances of the household. The proposed architecture was based on the elastic matching of aggregated energy signal frames with 20 reference TV channel signals. Different elastic matching algorithms, which use symmetric distance measures, were used with the best achieved video content identification accuracy of 93.6% using the MVM algorithm.

Conventional power meters measure total kilowatthours yet reveal little about how power was used. Modern solid-state metering solutions are not necessarily taking full advantage of the inexpensive but high performance computation capability that is available. This paper contains the details of a field test of a new software architecture for nonintrusive utility monitoring that endeavors to solve the big data problem of handling interesting but high bandwidth data streams from many monitored sites, e.g., residences and commercial buildings. Results from a field test are used to illustrate the utility of this system.

The development of awareness and legislative aspects related to the energy efficiency of water distribution systems,
combined with the ageing of water supply infrastructure and water stress, led to the search for solutions to support
more effective control and management of technical infrastructure. Increasing the standard of smart or intelligent water
supply systems at all levels of key areas is still a problem under domestic and foreign conditions. This also applies to
the microscale of water supply networks, namely water consumers of water and the use of smart water meters with
integrated machine learning algorithms. This article presents the results of research on the implementation of a short-
-term water consumption prediction model with anomaly detection for multifamily residential buildings. The prediction
of water consumption, based on high-frequency measurements and deep neural networks, achieved a prediction
error of less than 3.0%. Anomaly detection, based on the underlying prediction model, had up to 97.3% accuracy.

Energy profligacy and appliance degradation are the apex reasons accounting for the continuous rise in power wastage and high energy bills. The decline in energy conservation and management in residences has been largely attributed to the financial implications of using intrusive methods. This work aimed to resolve the challenges of intrusive load monitoring by introducing artificial intelligence and machine learning to optimise load monitoring. To solve this challenge, a non-intrusive approach was proposed where modalities for load prediction and classification were achieved with a Bagging regressor and a modified multiclass K-Nearest Neighbour algorithms. This developed supervised learning models produced a 0.9624 R 2 score and 78.24% accuracy for prediction and classification, respectively, when trained and tested on a Dutch Residential Energy Dataset. This work seeks to provide a cost-effective approach to the optimisation of energy using steady state active power features. Essentially, the adoption of this nonintrusive technique for load monitoring would effectively aid customers on the distribution network save cost on energy bills, facilitate the detection of faulty appliances, provide recommendations for smart homes and buildings with the required information for efficient decision making and planning of energy needs. In the long term, easing the pressure on power generation to meet demand would translate to reduction in carbon emissions based on a wide-scale implementation of this proposed system. Hence, these are important parameters in realising the development of smart sustainable cities and sustainable energy systems in this current industrial revolution. K E Y W O R D S artificial intelligence, data analytics, data structures and machine learning, smart cities, smart cities applications, smart power grids 2-KOMMEY ET AL.

Enabling diagnosis capabilities of Appliance Load Monitoring (ALM) necessitates providing in-operation information of appliances' behavior. Due to both appliances' time-varying model parameters and operations, household aggregated consumption has a dynamic structure. Existing time-invariant load models, built of offline datasets with static information, are not sufficient to capture the actual behavior of the power consumption. In fact, these models, generally obtained from exhaustive training phases are intended to satisfy load monitoring goals. Therefore, a time-variant load modeling is more practical to capture such a dynamic property of the power consumption. Accordingly, this paper presents an adaptive on-line appliance-level load modeling approach, to design a load monitoring structure for diagnosis purposes. By using the aggregated power consumption of individual households, our proposed structure results in an autonomous household database construction. The modeling procedure begins with a designed recurrent pattern recognition system that is capable of detecting and maintaining load models. This load model structure is determined by using a hidden Markov model (HMM) with dynamic parameters, that are extracted from aggregated signal and trained within an on-line learning process. Our proposed approach can detect time-varying power consumption behavior and estimate the robust load models of appliances. Additionally, our novelty in employing a set of straightforward algorithms, suggests the practicality of our database construction approach. 1.2. Contribution This paper aims to design an ALM system for load diagnosis purposes in a non-intrusive context. Both time-varying model parameters and operations of household appliances, give the aggregated power consumption a dynamic structure. As a result, a time-variant appliancelevel load modeling framework is more practical to capture such a

The following article presents the results obtained in experiences that use the Impulse Frequency Response Analysis (IFRA) method with a transformer in service. The IFRA method has been implemented in order to transform the transient signals to the frequency domain using Discrete Fourier Transform (DFT). However, it can be considered that the DFT is not the most suitable tool for this type of analysis, since, by definition, this tool is useful for processing stationary signals. Taking that into consideration, the analysis of transient signals could be hypothetically improved by using continuous wavelet transform (CWT), given their variable time/frequency resolution. The analysis of transient signals in Wavelet domain has improved the repeatability of the frequency response curves, as it has been observed in experimental results. The proposed on-line IFRA method, based on Wavelet transform, was validated under load and noload conditions on a 150 kVA three-phase transformer 13200/225 Volts, in the Campus of the

In response to the governmental policy of saving energy sources and reducing CO 2 , and carry out the resident quality of local; this paper proposes a new method for a non-intrusive load-monitoring (NILM) system in smart home to implement the load identification of electric equipments and establish the electric demand management. Non-intrusive load-monitoring techniques were often based on power signatures in the past, these techniques are necessary to be improved for the results of reliability and accuracy of recognition. By using neural network (NN) in combination with genetic programming (GP) and turn-on transient energy analysis, this study attempts to identify load demands and improve recognition accuracy of non-intrusive loadmonitoring results. The turn-on transient energy signature can improve the efficiency of load identification and computational time under multiple operations.

Aim: This article focuses on the use of artificial neural networks to mathematically describe the parameters that determine the size of a jet fire flame. To teach the neural network, the results of a horizontal propane jet fire, carried out experimentally and using CFD mathematical modelling, were used. Project and methods: The main part of the work consisted of developing an artificial neural network to describe the flame length and propane-air mixing path lengths with good accuracy, depending on the relevant process parameters. Two types of data series were used to meet the stated objective. The first series of data came from field tests carried out by CNBOP-PIB and from research contained in scientific articles. The second type of data was provided by numerical calculations made by the authors. The methods of computational fluid mechanics were used to develop the numerical simulations. The ANSYS Fluent package was used for this purpose. Matlab 2022a was used to develop the artificial neural network and to verify it. Results: Using the n ftool function included in Matlab 2022a, an artificial neural network was developed to determine the flame length L flame and the length of the S lift-off mixing path as a function of the diameter of the d nozzle and the mass flux of gas leaving the nozzle. Using Pearson's correlation coefficient, a selection was made of the best number of neurons in the hidden layer to describe the process parameters. The neural network developed allows L flame and S lift-off values to be calculated with good accuracy. Conclusions: Artificial neural networks allow a function to be developed to describe the parameters that determine flame sizes in relation to process parameters. For this purpose, the results of the CFD simulations and the results of the jet fire experiments were combined to create a single neural network. The result is a ready-made function that can be used in programmes for the rapid determination of flame sizes. Such a function can support the process of creating scenarios in the event of an emergency. A correctly developed neural network provides opportunities for the mathematical description of jet fires wherever experimental measurements are not possible. Solution proposed by the authors does not require a large investment in ongoing calculations, as the network can be implemented in any programming language_________Cel: W artykule skupiono się na wykorzystaniu sztucznych sieci neuronowych do opisu matematycznego parametrów określających rozmiary płomienia pożaru strumieniowego. Do uczenia sieci neuronowej wykorzystano wyniki badań poziomego pożaru strumieniowego propanu, przeprowadzone doświadczalnie i przy pomocy modelowania matematycznego metodą CFD. Projekt i metody: Główna część pracy polegała na opracowaniu sztucznej sieci neuronowej, która z dobrą dokładnością będzie opisywała długość płomienia oraz długości drogi mieszania propanu z powietrzem w zależności od istotnych parametrów procesowych. Do realizacji postawionego celu wykorzystano dwa typy serii danych. Pierwsza seria danych pochodziła z badań poligonowych wykonanych przez CNBOP-PIB oraz z badań zawartych
w artykułach naukowych. Drugi typ danych dostarczyły obliczenia numeryczne wykonane przez autorów. Do opracowania symulacji numerycznych wykorzystano metody obliczeniowej mechaniki płynów. W tym celu zastosowany został pakiet ANSYS Fluent. Do opracowania sztucznej sieci neuronowej oraz jej weryfikacji użyto programu Matlab 2022a. Wyniki: Korzystając z funkcji nftool , zawartej w programie Matlab 2022a, opracowano sztuczną sieć neuronową do wyznaczenia długości płomienia Lflame i długości drogi mieszania Slift-off w zależności od średnicy dyszy dnozzle i strumienia masowego gazu opuszczającego dyszę. Do opisu parametrów procesowych wybrano najbardziej adekwatną liczbę neuronów w warstwie ukrytej. Wykorzystano do tego współczynnik korelacji Pearsona. Opracowana sieć neuronowa pozwala z dobrą dokładnością obliczyć wartości Lflame i Slift-off. Wnioski: Sztuczne sieci neuronowe pozwalają na opracowanie funkcji opisującej rozmiar płomienia w zależności od parametrów procesowych. W celu stworzenia jednej sieci neuronowej połączono wyniki symulacji CFD i wyniki doświadczeń pożarów strumieniowych. W rezultacie otrzymano gotową
funkcję, która może być użyta w programach służących do szybkiego określania rozmiarów płomienia. Funkcja taka może wspomagać proces tworzenia scenariuszy na wypadek wystąpienia sytuacji awaryjnej. Poprawnie opracowana sieć neuronowa pozwala opisać w sposób matematyczny pożary strumieniowe wszędzie tam, gdzie wykonanie pomiarów doświadczalnych nie jest możliwe. Proponowane rozwiązanie nie wymaga dużych nakładów finansowych na prowadzone obliczenia, ponieważ sieć może być zaimplementowana w dowolnym języku programowania. Słowa kluczowe: obliczeniowa mechanika płynów, sztuczne sieci neuronowe, pożar strumieniowym Typ artykułu: oryginalny artykuł naukowy

Z 1. Symbole bezpieczeństwa Z 2. Jednostki w układzie SI Z 3. Wykaz używanych skrótów i symboli Z 4. Mnożniki, oznaczenia, symbole Z 5. Stałe fizyczne Z 6. Znaki klasycznego alfabetu greckiego Z 7. Zasoby internetowe użyte do opracowania 111 Z 8. Literatura użyta do opracowania [wg 15] Miernik RLC Oscyloskop dwukanałowy Miernik mocy wyjściowej Miernik zniekształceń nieliniowych Miernik napięć stałych i zmiennych Generator funkcyjny Badany obiekt Regulowany zasilacz stabilizowany

Non-intrusive load monitoring (NILM) or energy disaggregation is an inverse problem whereby the goal is to extract the load profiles of individual appliances, given an aggregate load profile of the mains of a home. NILM could help identify the power usage patterns of individual appliances in a home, and thus, could help realize novel energy conservation schemes for smart homes. In this backdrop, this work proposes a novel deep-learning approach to solve the NILM problem and a few related problems as follows. 1) We build upon the reputed seq2-point convolutional neural network (CNN) model to come up with the proposed seq2-[3]-point CNN model to solve the (home) NILM problem and site-NILM problem (basically, NILM at a smaller scale). 2) We solve the related problem of appliance identification by building upon the state-of-the-art (pretrained) 2D-CNN models, i.e., AlexNet, ResNet-18, and DenseNet-121, which are trained upon two custom datasets that consist of Wavelets and short-time Fourier transform (STFT)-based 2D electrical signatures of the appliances. 3) Finally, we do some basic qualitative inference about an individual appliance's health by comparing the power consumption of the same appliance across multiple homes. Low-frequency REDD dataset is used to train and test the proposed deep learning models for all problems, except site-NILM where REFIT dataset has been used. As for the results, we achieve a maximum accuracy of 94.6% for home-NILM, 81% for site-NILM, and 88.9% for appliance identification (with Resnet-based model).