Regression analysis for prediction of residential energy consumption

Fumo, Nelson; Biswas, M. A. Rafe

doi:10.1016/j.rser.2015.03.035

Cited by 504 publications

(235 citation statements)

References 34 publications

Supporting

Mentioning

227

Contrasting

Unclassified

Order By: Relevance

“…Many bottom-up regression models for energy demand modeling rely on the Princeton Scorekeeping Method [25], which describes the fundamental correlation between outdoor temperature and heating energy consumption. Recent studies using regression for modeling and predicting energy consumption often analyze hourly or sub-hourly energy meter data [26][27][28][29][30][31][32][33].…”

Section: Methods For Modeling Aggregate Hourly Energy Consumptionmentioning

confidence: 99%

Modeling Aggregate Hourly Energy Consumption in a Regional Building Stock

Kipping

Trømborg

2017

Energies

View full text Add to dashboard Cite

Sound estimates of future heat and electricity demand with high temporal and spatial resolution are needed for energy system planning, grid design, and evaluating demand-side management options and polices on regional and national levels. In this study, smart meter data on electricity consumption in buildings are combined with cross-sectional building information to model hourly electricity consumption within the household and service sectors on a regional basis in Norway. The same modeling approach is applied to model aggregate hourly district heat consumption in three different consumer groups located in Oslo. A comparison of modeled and metered hourly energy consumption shows that hourly variations and aggregate consumption per county and year are reproduced well by the models. However, for some smaller regions, modeled annual electricity consumption is over-or underestimated by more than 20%. Our results indicate that the presented method is useful for modeling the current and future hourly energy consumption of a regional building stock, but that larger and more detailed training datasets are required to improve the models, and more detailed building stock statistics on regional level are needed to generate useful estimates on aggregate regional energy consumption.

show abstract

Section: Methods For Modeling Aggregate Hourly Energy Consumptionmentioning

confidence: 99%

Modeling Aggregate Hourly Energy Consumption in a Regional Building Stock

Kipping

Trømborg

2017

Energies

View full text Add to dashboard Cite

show abstract

“…Numerous factors are involved in China's electricity demand variation, such as economic development level, electricity price, population growth and policy constraint [24][25][26][27][28][29][30][31][32]. While considering the data availability and typicality, this paper merely took into account of gross domestic product (GDP), booming of the population and energy policy constraints (specifically explained in Section 2.3.3), described in Table 1.…”

Section: Scenario Parameter Settingmentioning

confidence: 99%

Analysis and Modeling for China’s Electricity Demand Forecasting Using a Hybrid Method Based on Multiple Regression and Extreme Learning Machine: A View from Carbon Emission

et al. 2016

View full text Add to dashboard Cite

Abstract:The power industry is the main battlefield of CO 2 emission reduction, which plays an important role in the implementation and development of the low carbon economy. The forecasting of electricity demand can provide a scientific basis for the country to formulate a power industry development strategy and further promote the sustained, healthy and rapid development of the national economy. Under the goal of low-carbon economy, medium and long term electricity demand forecasting will have very important practical significance. In this paper, a new hybrid electricity demand model framework is characterized as follows: firstly, integration of grey relation degree (GRD) with induced ordered weighted harmonic averaging operator (IOWHA) to propose a new weight determination method of hybrid forecasting model on basis of forecasting accuracy as induced variables is presented; secondly, utilization of the proposed weight determination method to construct the optimal hybrid forecasting model based on extreme learning machine (ELM) forecasting model and multiple regression (MR) model; thirdly, three scenarios in line with the level of realization of various carbon emission targets and dynamic simulation of effect of low-carbon economy on future electricity demand are discussed. The resulting findings show that, the proposed model outperformed and concentrated some monomial forecasting models, especially in boosting the overall instability dramatically. In addition, the development of a low-carbon economy will increase the demand for electricity, and have an impact on the adjustment of the electricity demand structure.

show abstract

“…Both inputs and outputs are known, and historical data are used to define the mathematical description of the system by statistical methods whose variables have no physical meaning. Examples of these statistical models would be simple or multiple linear regression [16] or conditional demand analysis [17]. • Artificial methods: These methods, as in the case of the statistical methods, use historical data to model the system under evaluation, and are very useful tools to solve nonlinear problems of energy consumption.…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Characterization and Analysis of Energy Demand Patterns in Airports

Alba¹,

Canteli

2017

Energies

View full text Add to dashboard Cite

Airports in general have high-energy consumption. Influenced by many factors, the characteristics of airport energy consumption are stochastic, nonlinear and dynamic. In recent years, airport managers have made huge efforts to harmonize airport operation with environmental sustainability by minimizing the environmental impact, with energy conservation and energy efficiency as one of their pillars. A key factor in order to reduce energy consumption at airports is to understand the energy use and consumption behavior, due to the multiple parameters and singularities that are involved. In this article, a 3-step methodology based on monitoring methods is proposed to characterize and analyze energy demand patterns in airports through their electric load profiles, and is applied to the Seve Ballesteros-Santander Airport (Santander, Spain). This methodology can be also used in airports in order to determine the way energy is used, to establish the classification of the electrical charges based on their operation way as well as to determine the main energy consumers and main external influencers. Results show that airport present a daily energy demand pattern since electric load profiles follow a similar curve shape for every day of the year, having a great dependence of the terminal building behavior, the main energy consumer of the airport, and with heating, ventilation and air conditioning (HVAC) and lighting being the most energy-intensive facilities, and outside temperature and daylighting the main external influencers.

show abstract

Regression analysis for prediction of residential energy consumption

Cited by 504 publications

References 34 publications

Modeling Aggregate Hourly Energy Consumption in a Regional Building Stock

Modeling Aggregate Hourly Energy Consumption in a Regional Building Stock

Analysis and Modeling for China’s Electricity Demand Forecasting Using a Hybrid Method Based on Multiple Regression and Extreme Learning Machine: A View from Carbon Emission

Characterization and Analysis of Energy Demand Patterns in Airports

Contact Info

Product

Resources

About