Developing a Mixed Neural Network Approach to Forecast the Residential Electricity Consumption Based on Sensor Recorded Data.
ABSTRACT: In this paper, we report a study having as a main goal the obtaining of a method that can provide an accurate forecast of the residential electricity consumption, refining it up to the appliance level, using sensor recorded data, for residential smart homes complexes that use renewable energy sources as a part of their consumed electricity, overcoming the limitations of not having available historical meteorological data and the unwillingness of the contractor to acquire such data periodically in the future accurate short-term forecasts from a specialized institute due to the implied costs. In this purpose, we have developed a mixed artificial neural network (ANN) approach using both non-linear autoregressive with exogenous input (NARX) ANNs and function fitting neural networks (FITNETs). We have used a large dataset containing detailed electricity consumption data recorded by sensors, monitoring a series of individual appliances, while in the NARX case we have also used timestamps datasets as exogenous variables. After having developed and validated the forecasting method, we have compiled it in view of incorporating it into a cloud solution, being delivered to the contractor that can provide it as a service for a monthly fee to both the operators and residential consumers.
Project description:Smart energy meters generate real time, high frequency data which can foster demand management and response of consumers and firms, with potential private and social benefits. However, proper statistical techniques are needed to make sense of this large amount of data and translate them into usable recommendations. Here, we apply Functional Data Analysis (FDA), a novel branch of Statistics that analyses functions-to identify drivers of residential electricity load curves. We evaluate a real time feedback intervention which involved about 1000 Italian households for a period of three years. Results of the FDA modelling reveal, for the first time, daytime-indexed patterns of residential electricity consumption which depend on the ownership of specific clusters of electrical appliances and an overall reduction of consumption after the introduction of real time feedback, unrelated to appliance ownership characteristics.
Project description:The data presented in this article are related to the research article entitled: "Information strategies for energy conservation: a field experiment in India" (Chen et al., 2017) . The availability of high-resolution electricity data offers benefits to both utilities and consumers to understand the dynamics of energy consumption for example, between billing periods or times of peak demand. However, few public datasets with high-temporal resolution have been available to researchers on electricity use, especially at the appliance-level. This article describes data collected in a residential field experiment for 19 apartments at an Indian faculty housing complex during the period from August 1, 2013 to May 12, 2014. The dataset includes detailed information about electricity consumption. It also includes information on apartment characteristics and hourly weather variation to enable further studies of energy performance. These data can be used by researchers as training datasets to evaluate electricity usage consumption.
Project description:This study explores the effect of slum rehabilitation on appliance ownership and its implications on residential electricity demand. The low-income scenario makes it unique because the entire proposition is based on the importance of non-income drivers of appliance ownership that includes effects of changing the built environment (BE), household practices (HP) and appliances characteristics (AC). This study demonstrates quantitatively that non-income factors around energy practices influence appliance ownership, and therefore electricity consumption. The methodology consists of questionnaire design across the dimension of BE, HP and AC based on social practice theory, surveying of 1224 households and empirical analysis using covariance-based structural equation modelling. Results show that higher appliance ownership in the slum rehabilitation housing is due to change in household practice, built environment and affordability criteria of the appliances. Change in HP shifts necessary activities like cooking, washing and cleaning from outdoor to indoor spaces that positively and significantly influences higher appliance ownership. Poor BE conditions about indoor air quality, thermal comfort and hygiene; and product cost, discounts and ease of use of the appliances also triggers higher appliance ownership. The findings of this study can aid in designing better regulatory and energy efficiency policies for low-income settlements.
Project description:AMI has been gradually replacing conventional meters because newer models can acquire more informative energy consumption data. The additional information has enabled significant advances in many fields, including energy disaggregation, energy consumption pattern analysis and prediction, demand response, and user segmentation. However, the quality of AMI data varies significantly across publicly available datasets, and low sampling rates and numbers of houses monitored seriously limit practical analyses. To address these challenges, we herein present the ENERTALK dataset, which contains both aggregate and per-appliance measurements sampled at 15?Hz from 22 houses. Among the publicly available datasets with both aggregate and per-appliance measurements, 15?Hz was the highest sampling rate. The number of houses (22) was the second-largest where the largest one had a sampling rate of 1?Hz. The ENERTALK dataset is also the first Korean open dataset on residential electricity consumption.
Project description:Leveraging smart metering solutions to support energy efficiency on the individual household level poses novel research challenges in monitoring usage and providing accurate load forecasting. Forecasting electricity usage is an especially important component that can provide intelligence to smart meters. In this paper, we propose an enhanced approach for load forecasting at the household level. The impacts of residents' daily activities and appliance usages on the power consumption of the entire household are incorporated to improve the accuracy of the forecasting model. The contributions of this paper are threefold: (1) we addressed short-term electricity load forecasting for 24 hours ahead, not on the aggregate but on the individual household level, which fits into the Residential Power Load Forecasting (RPLF) methods; (2) for the forecasting, we utilized a household specific dataset of behaviors that influence power consumption, which was derived using segmentation and sequence mining algorithms; and (3) an extensive load forecasting study using different forecasting algorithms enhanced by the household activity patterns was undertaken.
Project description:Many countries are rolling out smart electricity meters. These measure a home's total power demand. However, research into consumer behaviour suggests that consumers are best able to improve their energy efficiency when provided with itemised, appliance-by-appliance consumption information. Energy disaggregation is a computational technique for estimating appliance-by-appliance energy consumption from a whole-house meter signal. To conduct research on disaggregation algorithms, researchers require data describing not just the aggregate demand per building but also the 'ground truth' demand of individual appliances. In this context, we present UK-DALE: an open-access dataset from the UK recording Domestic Appliance-Level Electricity at a sample rate of 16 kHz for the whole-house and at 1/6 Hz for individual appliances. This is the first open access UK dataset at this temporal resolution. We recorded from five houses, one of which was recorded for 655 days, the longest duration we are aware of for any energy dataset at this sample rate. We also describe the low-cost, open-source, wireless system we built for collecting our dataset.
Project description:In the electricity sector, energy conservation through technological and behavioral change is estimated to have a savings potential of 123 million metric tons of carbon per year, which represents 20% of US household direct emissions in the United States. In this article, we investigate the effectiveness of nonprice information strategies to motivate conservation behavior. We introduce environment and health-based messaging as a behavioral strategy to reduce energy use in the home and promote energy conservation. In a randomized controlled trial with real-time appliance-level energy metering, we find that environment and health-based information strategies, which communicate the environmental and public health externalities of electricity production, such as pounds of pollutants, childhood asthma, and cancer, outperform monetary savings information to drive behavioral change in the home. Environment and health-based information treatments motivated 8% energy savings versus control and were particularly effective on families with children, who achieved up to 19% energy savings. Our results are based on a panel of 3.4 million hourly appliance-level kilowatt-hour observations for 118 residences over 8 mo. We discuss the relative impacts of both cost-savings information and environmental health messaging strategies with residential consumers.
Project description:Based on 1128 survey questionnaires, main information on urban and rural household electricity consumption was obtained. Original data included household income, the price of electricity, all kinds of electrical appliances, purchase price of main appliances, household size, electricity consumption, as well as power, daily use time of electrical appliances in this data article. These data fully reflected behavior, preferences and living pattern of sample households in electricity use and provided the basis for analyzing the relationship between household electricity consumption and the quality of life ("Does electricity consumption improve residential living status in less developed regions? An empirical analysis using the quantile regression approach" ).
Project description:Estimating the impact of climate change on energy use across the globe is essential for analysis of both mitigation and adaptation policies. Yet existing empirical estimates are concentrated in Western countries, especially the United States. We use daily data on household electricity consumption to estimate how electricity consumption would change in Shanghai in the context of climate change. For colder days <7 °C, a 1 °C increase in daily temperature reduces electricity consumption by 2.8%. On warm days >25 °C, a 1 °C increase in daily temperatures leads to a 14.5% increase in electricity consumption. As income increases, households' weather sensitivity remains the same for hotter days in the summer but increases during the winter. We use this estimated behavior in conjunction with a collection of downscaled global climate models (GCMs) to construct a relationship between future annual global mean surface temperature (GMST) changes and annual residential electricity consumption. We find that annual electricity consumption increases by 9.2% per +1 °C in annual GMST. In comparison, annual peak electricity use increases by as much as 36.1% per +1 °C in annual GMST. Although most accurate for Shanghai, our findings could be most credibly extended to the urban areas in the Yangtze River Delta, covering roughly one-fifth of China's urban population and one-fourth of the gross domestic product.
Project description:An electricity demand reduction project based on comprehensive residential consumer engagement was established within an Australian community in 2008. By 2011, both the peak demand and grid supplied electricity consumption had decreased to below pre-intervention levels. This case study research explored the relationship developed between the utility, community and individual consumer from the residential customer perspective through qualitative research of 22 residential households. It is proposed that an energy utility can be highly successful at peak demand reduction by becoming a community member and a peer to residential consumers and developing the necessary trust, access, influence and partnership required to create the responsive environment to change. A peer-community approach could provide policymakers with a pathway for implementing pro-environmental behaviour for low carbon communities, as well as peak demand reduction, thereby addressing government emission targets while limiting the cost of living increases from infrastructure expenditure.