Smart Meters Research Articles

Machine learning for smart water distribution systems: exploring applications, challenges and future perspectives

The advancements of the Internet of Things and Low-Power Wide-Area Network technology will accelerate in the next future the adoption of smart meters in water distribution systems, enabling the collection of a huge amount of fine-grained data. How to turn massive smart meter data into actionable knowledge will be the key point to limit water wastage and promote efficient and sustainable distribution. Although the collection of data worldwide is currently limited, the potential future impact of exploiting data-driven and machine learning methods is increasingly recognized in research and industry, as shown by many scientific works published in recent years. In particular, the interest in deep learning for smart water distribution systems is increasing, motivated by the ability to learn intricate patterns from big data. This work aims to provide an overview of the current research and identify challenges for future directions by conducting an application-oriented survey. Specifically, by analysing data characteristics and operational targets, we propose a new taxonomy that helps structure properly the macro-areas of water management into infrastructure analysis, demand analysis and water quality monitoring. Existing methods are discussed for each application under these three stages. In addition, we also discuss potential research directions, such as federated learning, incremental learning, probabilistic modeling and explainability and address broad issues like data availability and implications for privacy.

MODERNIZATION OF DIAPHRAGM GAS FLOW METERS

The article examines methods for measuring gas flow using mechanical devices and investigates the feasibility of including a pressure device in the design of membrane mechanical meters in order to improve the accuracy of flow measurement. Accurate measurement of gas consumption plays an important role in solutions for its industrial and commercial applications. Diaphragm mechanical gas meters have been successfully used for several decades to measure gas consumption in domestic, industrial and commercial purposes. The advantages of these meters are simplicity, reliability and cost-effectiveness. However, recent advances in materials, advanced sensors and digital technologies open up great opportunities for the modernization of these devices, increasing their accuracy, reliability and integration into smart utility networks. The article describes the operating principle of diaphragm mechanical gas meters, the limitations of traditional designs, and analyzes the issues of modernization by including pressure and temperature sensors in their design. Integrating a pressure sensor into traditional diaphragm gas meters allows for increased accuracy by compensating for pressure changes in real time and at the same time bridging the gap between traditional mechanical systems and modern smart metering technologies. Comparative analysis shows that as a result of modernization, the productivity and cost-effectiveness of membrane meters have increased. Keywords: Flow meter, volumetric flow rate, mechanical equipment for measuring gas flow of membrane type, pressure compensation device, pressure and temperature sensor.

The Design of NB-IoT Network for Smart Metering Infrastructure in Residential Area

The Design of NB-IoT Network for Smart Metering Infrastructure in Residential Area

Online forecasting using neighbor-based incremental learning for electricity markets

Abstract Electricity market forecasting is very useful for the different actors involved in the energy sector to plan both the supply chain and market operation. Nowadays, energy demand data are data coming from smart meters and have to be processed in real-time for more efficient demand management. In addition, electricity prices data can present changes over time such as new patterns and new trends. Therefore, real-time forecasting algorithms for both demand and prices have to adapt and adjust to online data in order to provide timely and accurate responses. This work presents a new algorithm for electricity demand and prices forecasting in real-time. The proposed algorithm generates a prediction model based on the k-nearest neighbors algorithm, which is incrementally updated in an online scenario considering both changes to existing patterns and adding new detected patterns to the model. Both time-frequency and error threshold based model updates have been evaluated. Results using energy demand from 2007 to 2016 and prices data for different time periods from the Spanish electricity market are reported and compared with other benchmark algorithms.

Comprehensive Evaluation Method for the Metrological Performance of Intelligent Energy Meters in Complex Electromagnetic Field Environments

The existing evaluation methods mainly focus on the basic measurement accuracy of electric energy meters, without fully considering the anti-interference ability of electric energy meters under different electromagnetic interference intensities. In order to comprehensively evaluate the metrological performance of electric energy meters in complex electromagnetic field environments, this article adopted a comprehensive and systematic AHP-EWM (Analytical Hierarchy Process-Entropy Weight Method) comprehensive evaluation algorithm. This article used the Finite Element Method (FEM) to simulate complex electromagnetic environments, designed a multidimensional performance index system, and combined AHP and FEM to construct a comprehensive evaluation model for systematically evaluating the metrological performance of Intelligent Energy Meters (IEM) in complex electromagnetic environments. The experimental results show that the measurement error of smart energy meters significantly increases with the increase of interference intensity. AHP-EWM has shown high consistency and reliability under different electromagnetic interference intensity conditions and multiple repeated experimental tests. The weight allocation of various indicators remains relatively stable in different testing environments, and the comprehensive evaluation score fluctuates slightly, with a range of only 0.01 to 0.03. The AHP-EWM model can overcome electromagnetic interference of different intensities in practical applications and conduct comprehensive IEM metrological performance evaluation.

Evaluating the Performance of Smart Meters: Insights into Energy Management, Dynamic Pricing and Consumer Behavior

Evaluating the Performance of Smart Meters: Insights into Energy Management, Dynamic Pricing and Consumer Behavior

Application analysis of wireless communication technology in China's smart grid

With the rapid advancement of China's economy and technological innovation, wireless communication technology has seen considerable development. Concurrently, global energy and environmental challenges have intensified, heightening the demand for efficient and sustainable energy management solutions. In response to evolving energy demands, China has introduced new standards for digital power grid construction, prioritizing the use of wireless communication technologies to improve energy efficiency and develop smarter grid systems. These technologies facilitate real-time data transmission, remote monitoring of equipment, and network interconnectivity, thereby improving operational efficiency and monitoring capabilities. This paper reviews recent applications of wireless communication technologies within smart grids, aiming to provide valuable insights for future developments based on existing literature and data. Wireless communication technology in smart grids mainly enhances the intelligence and efficiency of the grid by enabling real-time data transmission, remote device management, and optimized energy distribution. Technologies such as Wi-Fi, 5G, and LoRa facilitate key functions like smart meter monitoring, equipment status management, and demand response, driving the automation and intelligent development of power systems. Future research should focus on optimizing the integration of these technologies, strengthening network security, and leveraging big data and artificial intelligence to advance the intelligence of power systems, thereby addressing critical energy challenges and fostering sustainable development

Designing Channel Attention Fully Convolutional Networks with Neural Architecture Search for Customer Socio-Demographic Information Identification Using Smart Meter Data

Designing Channel Attention Fully Convolutional Networks with Neural Architecture Search for Customer Socio-Demographic Information Identification Using Smart Meter Data

Processing techniques for metrological improvement of low-cost smart meter hardware solution for IEC 61000-4-7 Class I harmonics measurements

The work investigates the feasibility of harmonic analysis implementation on smart meter microcontroller devices, according to IEC 61000-4-30 Class A and IEC 61000-4-7 Class I requirements. The final aim was to evaluate to what extent Class I harmonic analysis can be integrated into existing low-cost hardware platforms for smart metering, which normally have limited hardware features, especially concerning the ADC and the possibility of varying the sampling frequency with high resolution, according to the power system signal frequency. An extended experimental characterization is carried out on a case study device, aimed at analyzing its performances in terms of both measurement accuracy and computational burden. To increase metrological ADC behavior and decrease computational costs, sampling strategies and optimized interpolation algorithm have been implemented and tested verifying the feasibility of harmonic analysis implementation on smart meter microcontroller devices, according to IEC 61000-4-30 Class A and IEC 61000-4-7 Class I requirements.

ВОЗМОЖНОСТИ СОВРЕМЕННЫХ ТЕХНОЛОГИЙ В ЭКОНОМИИ РЕСУРСОВ ЖКХ

The article analyzes the use of modern accounting technologies in the field of housing and communal services (housing and communal services) and their impact on energy efficiency and sustainable use of resources. Special attention is paid to intelligent metering systems (IMS), which automate the process of accounting for water, gas and electricity consumption. These devices are capable of collecting, transmitting and processing data in real time, providing management companies with accurate indicators, which helps eliminate errors associated with manual input and increases the transparency of calculations. IMS allow management companies to respond promptly to emergencies such as leaks, anomalies in consumption and unauthorized use of resources, which reduces the cost of their elimination and provides greater safety for consumers. Users, having access to information through mobile applications and web portals, are able to monitor and regulate their consumption, which helps to optimize costs and increases an informed attitude to resources. The article also provides examples of successful implementation of smart meters in various countries such as the USA, Great Britain, the Netherlands, Russia and Australia, where they have become an important tool to support sustainable development. The use of ICS allows the integration of renewable energy sources and the implementation of energy saving programs, including dynamic pricing and incentives for reducing consumption during peak hours. This technology contributes to the creation of “smart cities” in which data from various systems — lighting, heating and water supply — are analyzed comprehensively to optimize resources. The introduction of smart meters is emphasized as strategically important for the modernization of housing and communal services: they open up new opportunities for rational resource management, reduce the carbon footprint and help provide a comfortable and transparent environment for consumers, forming the basis for a sustainable future

E-REDES solution for real-time overvoltage monitoring in LV grid | smart meter as an active asset to avoid damages and increase resilience

E-REDES solution for real-time overvoltage monitoring in LV grid | smart meter as an active asset to avoid damages and increase resilience

Monitoring and control of DER using AMI equipment SMGW and smart meter

Monitoring and control of DER using AMI equipment SMGW and smart meter

Operation of on-load tap changer (OLTC) in MV/LV transformer by using smart meter data for voltage optimization and increasing hosting capacity in low voltage distribution grids with distributed photovoltaics (DPV)

Operation of on-load tap changer (OLTC) in MV/LV transformer by using smart meter data for voltage optimization and increasing hosting capacity in low voltage distribution grids with distributed photovoltaics (DPV)

Anomaly Detection of Cyber Attacks in Smart Grid Communications Based on Residual Recurrent Neural Networks

ABSTRACTThe smart grid consists of widely distributed devices, and the complex, multitiered communication network structure increases its vulnerability to attacks. Attackers can exploit communication vulnerabilities between layers to launch network attacks. To optimize communication among smart grid devices and improve the accuracy of detecting network anomalies, this article proposes a deep learning‐based method for detecting communication network anomalies in power grid devices. Data from standard sources, such as smart meters, are collected, and the modified flow direction algorithm (MFDA) is employed for optimal weighted feature selection. The selected features are then input into an adaptive residual recurrent neural network (ARRNN) with dilated gated recurrent units (DGRUs) for anomaly detection, improving the accuracy of abnormal traffic monitoring in the smart grid. Simulation results show significant improvements in key performance indicators, with the false discovery rate (FDR) reduced to 0.060, the Matthews correlation coefficient (MCC) reaching 0.881, and specificity, recall, and precision all at 0.940. Large‐scale data experiments demonstrate outstanding performance in terms of memory usage, computational speed, and latency. This method proves to be effective and robust for communication anomaly detection in power grid networks.

Determination of the line parameters of electrical distribution grids based on smart meter data

Determination of the line parameters of electrical distribution grids based on smart meter data

Multimodal feature fusion and ensemble learning for non-intrusive occupancy monitoring using smart meters

Multimodal feature fusion and ensemble learning for non-intrusive occupancy monitoring using smart meters

Enhancing low voltage network capacity through phase load balance optimization using advanced smart meter data analytics and static reconnections

Enhancing low voltage network capacity through phase load balance optimization using advanced smart meter data analytics and static reconnections

Leveraging Artificial Intelligence for Assessing Metering Faults in Electric Power Systems

Operations sampling inspections, manual verification, user applications, and other labor-intensive methods are commonly used for energy meter error analysis in the power industry. Accurate fault detection in electric energy meters is crucial for achieving reliable measurements. The fundamental issue with on-site testing of electrical energy metering equipment is the characteristics of electric power meters under dynamic settings. This research develops a deep learning-assisted prediction model (DLPM) to address the problem of inaccurate energy power meters. Electricity is measured precisely, and the meters can pinpoint the most consequential deviations between the predicted and actual trajectories. The results of this research point to the widespread adoption of a consistent and autonomous method for analyzing discrepancies in energy meters. Compared to the traditional way, this technology considerably improves the electric intelligent meter deviance computation, providing exact data assistance for analysis and diagnostics of the source of the electric smart meter abnormality. The simulation results show that the suggested DLPM model has better prediction accuracy (99.2%), performance (97.8%), efficiency (98.9%), average consumption (10.3%), and root mean square error (11.2%) than the state-of-the-art.

Using smart meter data to analyse low carbon technology loads in Northern Ireland

Using smart meter data to analyse low carbon technology loads in Northern Ireland

Empowering consumers through smart meter technology

Empowering consumers through smart meter technology