Smart Electricity Meters Research Articles

Spatiotemporal monitoring of groundwater supply and active energy for irrigation practice in semi-arid regions of Tunisia with machine learning

ABSTRACT Semiarid regions are facing overexploitation of groundwater resources to meet irrigation needs. Monitoring the water-energy nexus allows for optimal management of extracted water volumes and consumed energy. A semiarid zone was selected in the Nabeul region of Tunisia where 14 farmers, whose wells were equipped with smart electricity and water meters (SWEMs), for instant monitoring of pumped water volumes and the electrical energy required for irrigation. Monthly data over a period of 8 months were used to study the variations in water volumes and active energy. The analysis of variance classified farmers into four groups based on water volumes and five groups based on active energy. Spatial variability analysis using kriging showed that the northeast zone is the most solicited in terms of water pumping and energy consumption with water volume exceeding 4,000 m3/month and active energy reaching 2,500 kWh/month. The prediction of energy based on water volume using machine learning techniques such as random forest and support vector machine was successfully conducted. The tools generated by the methodology were applied to a chosen case in the region to estimate active energy and validate the results obtained. The implemented framework allows for better management of groundwater resources for irrigation.

Comparative analysis of life cycle assessment and material circularity indicator: study applied to smart electricity meter polycarbonate parts

Comparative analysis of life cycle assessment and material circularity indicator: study applied to smart electricity meter polycarbonate parts

Investigating the factors affecting the intention to adopt smart electricity meters in Indian households

Smart electric meters play a pivotal role in making energy systems decarbonized and automating the energy system. Smart electric meters denote huge business opportunities for both public and private companies. Utility players can manage the electricity demand more efficiently whereas customers can monitor and control the electricity bill through the adoption of smart electric meters. The study examines the factors affecting the adoption intention of smart electric meters in Indian households. This study draws a roadmap that how utility providers and customers can improve the smart electric meters adoption. The study has five independent variables (performance expectancy, effort expectancy, social influence, environmentalism, and hedonic motivation) and one dependent variable (adoption intention). The sample size for the study is four hundred and sixty-two respondents from Delhi and the National Capital Region (NCR). The data was analysed using structural equation modelling (SEM). The results of this study have confirmed that performance expectancy, environmentalism, and social influence have a significant impact on the intention of adopting smart electric meters. Therefore, utility providers can improve their strategies to attract more customers to adopt smart electric meters by focusing more on the performance of smart electric meters and by making them environmentally friendly. This research offers meaningful insights to both customers and utility providers to make energy systems decarbonized and control energy consumption.

Smart Electricity Meter Monitoring and Prediction using I-Socket

As the world's population and energy needs continue to grow, the demand for power is ever-increasing. This has put a strain on natural resources and renewable sources of power, which are not yet developed enough to operate self-sufficiently. In this context, optimal power sharing and efficient energy consumption is essential. To this end, a smart electricity meter monitoring and prediction system has been developed using i-Socket, a hardware module that tracks the energy consumed by each device in a house and estimates the monthly electricity bill. This system notifies the user when the bill surpasses a set limit and sets the monitoring rate of a connected device to the socket based on the type of device, making it an energy efficient system. Current sensor used is the ACS712 sensor and the microcontroller is Arduino UNO. A Boost converter is used for the power supply and the software application is developed for monitoring electricity bills. This system takes input of present data of current and predicts the meter reading for the following months. However, the same can also be achieved by using a python server for holding an ML model that will be developed to predict future price of the bill based on the current usage of power. This is acts as an affordable alternative to that by using the iSocket

Anomaly Detection in Smart Electric Meters for Detecting Faults and Misuse of Electric Energy Consumption

The emergence of Smart Electric Meters (SEMs) has revolutionized energy management, providing real-time data collection and monitoring capabilities. However, ensuring the accuracy and security of this data presents challenges. Anomaly detection in electric energy consumption patterns is crucial for identifying issues like technical faults, erroneous billing, and misuse of electricity. Our project offers an Anomaly Detection System that leverages data analytics and machine learning to scrutinize SEM data. By analyzing historical patterns, the system distinguishes anomalies from routine fluctuations, triggering alerts when irregularities are detected. This system enhances the reliability and security of electric energy consumption data, fostering a more efficient and sustainable energy sector. Key Words: Anomaly Detection, Smart electric Meters, Fault Detection, Energy Misuse.

AUTOMATED SYSTEM FOR DETERMINING OF ELECTRICITY CONSUMPTION WITH ELEMENTS OF ARTIFICIAL INTELLIGENCE

Currently, Russia is moving towards automating the collection of information from metering devices for heat, gas, water, electricity, etc. Technologies are being developed that allow the transmission of resource consumption data via various communication channels, both wired and over-the-air. There are already devices and devices that allow transmitting readings of electricity metering devices over existing wired communication networks and this issue is being resolved at the legislative level, Federal Law No. 522-FZ of 07/01/2020 has been adopted. The basis for the research is to save time and effort in obtaining the necessary information to account for electricity readings from substations, increase the speed of decision-making, and be able to predict the situation with big data to identify abnormal values and eliminate them (for example, identified data from electricity meters will reduce the time labor of metering operators and economic losses of an energy supply company). The article proposes hardware and software methods for detecting data on electricity losses based on the use of artificial neural network algorithms and allowing to detect inconsistencies in commercial data readings of electric meters, which will reduce the commercial component of electricity losses. A verification calculation of an artificial neural network was performed for inconsistencies in the data on the transmitted electricity. The design of a receiving and transmitting digital module for remote data recording has been carried out, as well as the development of an automated system designed for remote collection, processing, storage and transmission of information on energy consumption and balance. The developed automated information and measurement system for remote data collection and transmission was tested at the manufacturer of smart electric energy meters with a radio channel.

Detecting Cyber Attacks on Renewable Distributed Generation for Future Smart Electric Meters to Prevent Electricity Theft

Electricity theft represents a pressing problem that has brought enormous fiscal losses to electric mileage companies worldwide. In the United States alone, $ 6 billion of electricity is stolen annually. Traditionally, electricity theft is committed in the consumption sphere via physical attacks that include line tapping or cadence tampering. With the advanced metering structure (AMI), smart measures are installed at the guests’ demesne and regularly report the guests’ consumption for monitoring and billing purposes. In this environment, vicious guests can launch cyber-attacks on smart measures to manipulate the readings in a way that reduces their electricity bill. Second, the smart grid paradigm enables guests to install renewable-grounded distributed generation (DG) units at their demesne to induce energy and send it back to the grid driver and hence make a profit.

Detection and confirmation of electricity thefts in Advanced Metering Infrastructure by Long Short-Term Memory and fuzzy inference system models

The successful implementation of Smart Grids heavily relies on energy efficiency, particularly through the Advanced Metering Infrastructure (AMI) and Smart Electricity Meters (SEM). However, cyber-attacks pose a threat to SEM, with electricity theft being a primary motivation. Despite the valuable data provided by SEM for analytical purposes, existing methods to identify theft involve cumbersome and costly on-site inspections. This research proposes an electricity theft detection model using the Long Short-Term Memory (LSTM) network. The model employs a collective anomaly approach, defining prediction errors through a threshold and forecast horizon. Suspicious consumption profiles are analysed, and a fuzzy inference system (FIS) implemented in MATLAB 2021b is used to model security risks based on these profiles. The study utilizes energy consumption data from four diverse consumer profiles (consumers 1, 2, 3, and 4) to develop consumer-specific LSTM models for detection and an FIS model for confirmation. Tampered consumer data is identified and confirmed based on selected AMI parameters. While all consumers exhibit suspicious profiles at times, only consumers 2 and 3 are confirmed as engaging in electricity theft. This research provides a robust approach to detecting and verifying fraudulent consumption profiles within the context of AMI, offering a more reliable dimension to theft detection and confirmation.

Assessment of Operation State for Smart Electricity Meters Using Multiple Fusion Support Vector Regression With Improved SA

Assessment of Operation State for Smart Electricity Meters Using Multiple Fusion Support Vector Regression With Improved SA

Operational Status Evaluation of Smart Electricity Meters Using Gaussian Process Regression With Optimized-ARD Kernel

Operational Status Evaluation (OSE) is essential for the health management of Smart Electricity Meters (SEM). This paper develops a machine learning-enabled OSE method for SEM. Specifically, the Gaussian Process Regression (GPR) is developed for modeling analysis, where an Optimized Automatic Relevance Determination (OARD) kernel is first used. Though the conventional ARD kernel structure can capture the potential mapping relationship between running time, temperature, humidity, and Measurement Error (ME), it cannot extract the influence degree of different stresses on the ME. To address this problem, an OARD kernel structure is proposed to identify the contribution of each part in ARD structure to the target data. Furthermore, the quartiles line instead of 95% confidence interval is exploited to enhance the performance of GPR for long-term prediction. Combining the two above improvements, a novel OSE model is established for the future-oriented long-term operation of the SEM. It is the first-known data-driven application that utilizes the GPR with OARD kernel to perform OSE for SEM. Actual SEM datasets collected from both dry and hot region are used for model validation and prediction. The results demonstrate that the proposed GPR model with OARD Matern52 kernel outperforms other conventional kernel approaches in the aspect of interpretability. More importantly, the operational status of the SEM in future can be assessed via the proposed OSE framework.

A Graph-Based Neural Approach to Linear Sum Assignment Problems.

Linear assignment problems are well-known combinatorial optimization problems involving domains such as logistics, robotics and telecommunications. In general, obtaining an optimal solution to such problems is computationally infeasible even in small settings, so heuristic algorithms are often used to find near-optimal solutions. In order to attain the right assignment permutation, this study investigates a general-purpose learning strategy that uses a bipartite graph to describe the problem structure and a message passing Graph Neural Network (GNN) model to learn the correct mapping. Comparing the proposed structure with two existing DNN solutions, simulation results show that the proposed approach significantly improves classification accuracy, proving to be very efficient in terms of processing time and memory requirements, due to its inherent parameter sharing capability. Among the many practical uses that require solving allocation problems in everyday scenarios, we decided to apply the proposed approach to address the scheduling of electric smart meters access within an electricity distribution smart grid infrastructure, since near-real-time energy monitoring is a key element of the green transition that has become increasingly important in recent times. The results obtained show that the proposed graph-based solver, although sub-optimal, exhibits the highest scalability, compared with other state-of-the-art heuristic approaches. To foster the reproducibility of the results, we made the code available at https://github.com/aircarlo/GNN_LSAP.

An electricity smart meter dataset of Spanish households: insights into consumption patterns

Smart meters are devices that provide detailed information about the energy consumed by specific electricity supply points, such as homes, offices, and businesses. Data from smart meters are useful for modeling energy systems, predicting electricity consumption, and understanding human behavior. We present the first smart meter dataset from Spanish electricity supply points, expanding the geographic diversity of available data on energy consumption at the household level and reducing biases in existing data, which typically come from a limited number of countries. The dataset consists of 25,559 raw hourly time series with an average length of nearly three years, spanning from November 2014 to June 2022. It also includes three subsets obtained by segmenting and cleaning the raw time series data, each focusing on the periods before, during, and after the COVID-19 lockdowns in Spain. This dataset is a valuable resource for studying electricity consumption patterns and behaviors that emerge in response to different natural experiments, such as nationwide and regional lockdowns, nighttime curfews, and changes in electricity pricing.

An Online Accuracy Evaluation Method for Smart Electricity Meter Calibration Devices Based on Mutual Correlations of Calibration Data

An Online Accuracy Evaluation Method for Smart Electricity Meter Calibration Devices Based on Mutual Correlations of Calibration Data

Soil moisture forecasting for precision irrigation management using real-time electricity consumption records

The installation of the smart electricity meters (SEMs) to the high-density pumping wells in the North China Plain (NCP) provided a method to control the groundwater withdraw. The record in real-time electricity consumption from SEMs also provided an alternative method to forecast soil moisture to make irrigation decisions to improve irrigation efficiency. The irrigation timing and the irrigation amount could be obtained on-line from the SEMs based on the coefficients obtained for electricity-to-water conversion (E-Wc). The real-time recordings in the irrigation timing and amounts were further used to forecast the next irrigation timing and amount based on the water rights per area of land, the lower limit of soil water contents for different crops at their different growing stages and online meteorological data. A smartphone app was developed based on this framework. The running of the app to simulate soil water contents based on the soil water balance equation was supported by databases on soil texture, crop coefficients, water rights, E-Wc and threshold soil water content values as well as the real-time collection of electricity consumption and meteorological data. The simulated real-time soil water contents were shown on the mobile phone screen and could be compared with the threshold values for making irrigation decisions for users. The accuracy in forecasting the soil water contents using the methods developed in this framework was tested under different irrigation schedules for winter wheat and summer maize during 2018–2019 and 2021–2022, and the app was tested for three locations starting from sowing winter wheat in October 2022 to April in 2023. The results showed that the app could be easily run, and precise real-time soil water contents were simulated. With the application of the pumping well renovation project in the NCP, most of the pumping wells were installed with the SEMs, and using SEMs for groundwater pumping control and irrigation decisions should be possible.

Prepaid Smart Electric Meter Curbs Power Thefts and Improves Indian Economy: Review

Prepaid Smart Electric Meter Curbs Power Thefts and Improves Indian Economy: Review

Demand for a “smart” add-on: the case of in-home displays

ABSTRACTAn in-home display (IHD) is an important add-on to a smart electric meter that provides continuous real-time feedback to households about their energy usage and costs. Utilising experimental variation in an online survey, I estimate a price elasticity of demand for IHD of −0.15, conditional on smart meter adoption. Households who did not pay for their smart meter device are also more sensitive to the IHD price, suggesting potential negative spillovers from smart meter subsidies.

Transformative disruptiveness or transition? Revealing digitalization and deep decarbonization pathways in the Italian smart electricity meter roll-out

Energy infrastructure digitalization is proposed as key for a just deep decarbonization. However, an integrative literature review reveals the lack of a more profound exploration on normative considerations tied to world perspectives and values, as levers of a lasting transformation in the context of socio-technical transitions. Thus, the paper employs qualitative research methods to investigate how energy infrastructure digitalization contributes to transformative disruption, along which deliberated deep decarbonization pathways, using Italy's smart electricity meter roll-out as a case study. While the roll-out represents a substantial effort in introducing digital devices into the residential sector, concerns persist about its effectiveness, also due to potential societal disruptions. Through in-depth interviews with experts (N = 17) and citizens (N = 23) and content-oriented analysis, the research unveils evolving pathways between ever more disengaged two grand narratives and value systems: energy as a commodity and energy as a common good. The first opts for technological progress, changing consumer behavior, to address energy poverty and social justice, building on market-based instruments and new business models. Conversely, the second harbors skepticism towards technological fixes, emphasizes energy sufficiency and questions energy opulence, linked to environmental justice considerations, and calling for corrective principles by regulatory means. Finally, the paper presents a conceptual framework to re-shape deep deliberative transformation, highlighting the importance of re-connecting to defined values, re-generating actionable knowledge, restructuring institutions in societal experimentation, and recognizing underlying processes such as justice claims. It argues for further research into discourse coalitions capitalizing on defined narratives, to better understand their impact on policy-making processes.

A Comparison Study of Predictive Models for Electricity Demand in a Diverse Urban Environment

The increasing population migration to urban and peri-urban areas increases basic service needs for cities worldwide. Residential electricity demand increases with more customers and varies with novel uses, such as charging electric vehicles, which may add additional dynamics to the residential electricity demand profile. Widespread installation of smart electricity meters provides fine temporal resolution data reflecting current demands and supports predicting future demands. As part of a demand-side management program, understanding the main drivers of current electricity usage based on demand-driven and exogenous predictors represents a valuable tool for utilities facing new demand scenarios. This work presents the application of multiple models to forecast electricity demand based on the input data and the forecasting horizon. Models with exogenous variables as predictors are part of the input–output category, including a Feed Forward Neural Network, Random Forest, and a Linear Gaussian State Space model. The second category is demand-driven models, where predictors include only previous demand values. The demand-driven models in our analysis include a univariate Nonlinear Autoregressive Neural Network and a Linear Gaussian State Space. Using smart electricity meter data from the greater Chicago area, we compare the performance of the models on two different types of accounts: single- and multi-family residential users when forecasting one and multiple steps. Results show that the Linear Gaussian model reports an R2 of 0.99 compared to an average R2 of 0.92 from the Feed Forward Neural Networks and Random Forest when forecasting single- and multi-family electricity demand one step ahead. However, Nonlinear Autoregressive Neural Networks report an average R2 of 0.85 compared to the Linear Gaussian R2 of 0.58 when forecasting 48 steps. We also found that the most important predictors for single-family demand are temporal variables like weekdays, working and non-working days, and day hours. For multi-family demand, electricity demand at the same hour as the previous week replaces weekdays as a significant predictor. Different forecasting models can assist utilities and city planners to manage demand under different and novel residential electricity usage conditions.

Benford’s Law in Electric Distribution Network

Benford’s law can be used as a method to detect non-natural changes in data sets with certain properties; in our case, the dataset was collected from electricity metering devices. In this paper, we present a theoretical background behind this law. We applied Benford’s law first digit probability distribution test for electricity metering data sets acquired from smart electricity meters, i.e., the natural data of electricity consumption acquired during a specific time interval. We present the results of Benford’s law distribution for an original measured dataset with no artificial intervention and a set of results for different kinds of affected datasets created by simulated artificial intervention. Comparing these two dataset types with each other and with the theoretical probability distribution provided us the proof that with this kind of data, Benford’s law can be applied and that it can extract the dataset’s artificial manipulation markers. As presented in the results part of the article, non-affected datasets mostly have a deviation from BL theoretical probability values below 10%, rarely between 10% and 20%. On the other side, simulated affected datasets show deviations mostly above 20%, often approximately 70%, but rarely lower than 20%, and this only in the case of affecting a small part of the original dataset (10%), which represents only a small magnitude of intervention.

Managing Knowledge Acquired from Smart Meters in a Distributed Advanced Metering Infrastructure

The primary purpose of this article is to present the functional information and knowledge - acquired from smart electricity meter readings, which are a component of the Advanced Metering Infrastructure (AMI). The relations between the management of knowledge acquired from the AMI system and the new empirically identifieddecision-making processes that make the management of electricity value more efficient, both on the side of the supplier but also, which need to be emphasised, on the side of the consumer/household, often the energy prosumer (micro RES production), are indicated in it. In the first part of the article - the theoretical and cognitive part - justification has been given for the subject matter specified in the title of the paper. Attention was drawn to the dynamic digitization and automation of energy metering readings. The size of the AMI market in terms of the growth in the number of smart meters in households, as well as the size of the market, has been quantitatively described. In the context of the dynamic growth of smart electricity meters, the growth of heterogeneous knowledge on households resulting from high-frequency readings was justified, which in fact reflect not only variable energy demand but also the culture of energy demand and use. In the paper its author has structured the insights gained from the AMI infrastructure. In turn, the second - empirical - part attempts to answer two research questions: 1) What information/knowledge in addition to real-time bi-directional energy readings necessary for energy value management can be generated through the use of high-frequency clocking smart meters?; 2) How to use the acquired knowledge, manage the knowledge, acquired from the readings of the distributed AMI (smart electricity meters) infrastructure, in terms of key decision-making processes that make energy value management more effective, both on the supplier side but also on the consumer/household side, frequently the energy prosumer - micro RES production. In order to answer the above two research questions, a questionnaire survey was conducted and a brainstorming, scientific discourse with inference was carried out with a group of business practitioners, including managers of corporations and energy companies - improving their knowledge, and competences in the area of management and entrepreneurship in energy markets, including RES.