Individual Smart Meters Research Articles

LSTM Networks for Home Energy Efficiency

This study aims to develop and evaluate an LSTM neural network for predicting household energy consumption. To conduct the experiment, a testbed was created consisting of five common appliances, namely, a TV, air conditioner, fan, computer, and lamp, each connected to individual smart meters within a Home Energy Management System (HEMS). Additionally, a meter was installed on the distribution board to measure total consumption. Real-time data were collected at 15-min intervals for 30 days in a residence that represented urban energy consumption in Sincelejo, Sucre, inhabited by four people. This setup enabled the capture of detailed and specific energy consumption data, facilitating data analysis and validating the system before large-scale implementation. Using the detailed power consumption information of these devices, an LSTM model was trained to identify temporal connections in power usage. Proper data preparation, including normalisation and feature selection, was essential for the success of the model. The results showed that the LSTM model was effective in predicting energy consumption, achieving a mean squared error (MSE) of 0.0169. This study emphasises the importance of continued research on preferred predictive models and identifies areas for future research, such as the integration of additional contextual data and the development of practical applications for residential energy management. Additionally, it demonstrates the potential of LSTM models in smart-home energy management and serves as a solid foundation for future research in this field.

Emissions From Smart Meters and Other Residential Radiofrequency Sources.

The advent of the Internet of things comes with a huge increase in wirelessly communicating devices in our environment. For example, smart energy-consumption meters are being widely deployed in residences from which they communicate their state using radiofrequency networks. Accurate characterization of the radiofrequency emissions from emerging residential wireless solutions is important to inform the public about the potential impact on their exposure to radiofrequency electromagnetic fields. A new measurement procedure to determine the exposure from residential radiofrequency devices is proposed by assessing the peak emitted fields at various distances and the proportion of time they transmit (duty cycle). Radiofrequency emissions from 55 residential devices were measured in 10 residences (Belgium and France) and compared to environmental levels, emissions from 41 mobile phones, and international standards. Overall, residential levels of radiofrequency electromagnetic field exposure are low. In addition to the continuous environmental exposure, wireless access points (due to frequent use) and especially mobile phones and other personal communication devices (due to their use close to the body) continue to represent the bulk of the radiofrequency electromagnetic field exposure in the smart home. However, some residential devices can significantly increase the exposure if their duty cycles are high enough (>10%), especially when held or used close to the body. Individual smart meters, on the other hand, will contribute only little in general, despite emissions of up to 20 V m at 50 cm, due to their low duty cycles (maximum 1%) and locations.

The District Energy-Efficient Retrofitting of Torrelago (Laguna de Duero – Spain)

The urban growth is estimated to reach up the 66 % by 2050 and consequently the need of resources within the cities will increase significantly. This, combined with the 40 % of energy consumption and 36 % of CO2 emissions of the building sector, makes necessary to accelerate the transition towards more sustainable cities. The CITyFiED project contributes to this transition, aiming to develop an innovative and holistic methodological approach for energy-efficient district renovation and deliver three large scale demonstration cases in the cities of Lund (Sweden), Laguna de Duero (Spain) and Soma (Turkey). CITyFiED methodology consists of several phases that ease the decision-making tasks towards the district renovation, considering the energy efficiency as the main pillar and local authorities as clients. For the case of Torrelago district (Spain) the intervention consists of a set of energy conservative measures including the façade retrofitting of 143.025 m2 of living space in 31 twelve-storey buildings; the renovation of the district heating network with a new biomass thermal plant; the integration of renewable energy sources, including a micro-cogeneration system, and the installation of individual smart meters. After the renovation action, one-year monitoring campaign is ongoing. The CITyFiED monitoring platform will collect information from the energy systems and deliver environmental, technical, economic and social key performance indicators by March 2019. At the end of the project the achievement of the predefined goals will be verified: up to 36 % of energy saving and 3,429 tons-CO2/yr emissions saving covering the 59,4 % of the energy consumption with renewable sources

Privacy-Preserving Aggregation and Authentication of Multi-Source Smart Meters in a Smart Grid System

The smart grid is a promising electrical grid paradigm for enhancing flexibility and reliability in power transmission through two-way communications among grid entities. In the smart grid system, the privacy of usage information measured by individual smart meters has gained significant attention, owing to the possibility of personal information inference. Moreover, efficient and reliable power provisioning can be seriously impeded through illicit manipulations of aggregated data under the influence of malicious adversaries. Due to such potential risks, it becomes an important requirement for the smart grid to preserve privacy of metering data by secure aggregation and to authenticate the aggregated result in an efficient manner within large scale environments. From this perspective, this paper investigates the current status of security and privacy in smart grid systems and representative state-of-the-art studies in secure aggregation and authentication of metering data for future directions of a smart grid.

Forecasting electricity smart meter data using conditional kernel density estimation

The recent advent of smart meters has led to large micro-level datasets. For the first time, the electricity consumption at individual sites is available on a near real-time basis. Efficient management of energy resources, electric utilities, and transmission grids, can be greatly facilitated by harnessing the potential of this data. The aim of this study is to generate probability density estimates for consumption recorded by individual smart meters. Such estimates can assist decision making by helping consumers identify and minimize their excess electricity usage, especially during peak times. For suppliers, these estimates can be used to devise innovative time-of-use pricing strategies aimed at their target consumers. We consider methods based on conditional kernel density (CKD) estimation with the incorporation of a decay parameter. The methods capture the seasonality in consumption, and enable a nonparametric estimation of its conditional density. Using 8 months of half-hourly data for 1000 meterswe evaluate point and density forecasts, for lead times ranging from one half-hour up to a week ahead. We find that the kernel-based methods outperform a simple benchmark method that does not account for seasonality, and compare well with an exponential smoothing method that we use as a sophisticated benchmark. To gauge the financial impact, we use density estimates of consumption to derive prediction intervals of electricity cost for different time-of-use tariffs. We show that a simple strategy of switching between different tariffs, based on a comparison of cost densities, delivers significant cost savings for the great majority of consumers.

Characterization of radiofrequency field emissions from smart meters

This study presents measurement data that describe radiofrequency emission levels and patterns from smart meters (rated nominally at 1 W) currently deployed in Pacific Gas and Electric Company's service territory in northern California. The smart meters in our investigation could not be set to operate continuously and required a Field Service Unit to induce short periods of emitted fields. To obtain peak field data under both laboratory and ambient conditions, a spectrum analyzer scanned across the 83 transmitting channels between 902 and 928 MHz used by the smart meter on a random frequency-hopping basis. To obtain data describing temporal emission patterns, the analyzer operated in scope mode. Duty cycle was estimated using transmit data acquired by the system operator from over 88,000 m. Instantaneous peak fields at 0.3 m in front of the meters were no more than 15% of the US Federal Communications Commission (FCC) exposure limit for the general public, and 99.9% of the meters operated with a duty cycle of 1.12% or less during the sampling period. In a sample of measurements in six single-detached residences equipped with individual smart meters, no interior measurement of peak field exceeded 1% of the FCC's general public exposure limit.