A deep learning framework for building energy consumption forecast

Somu, Nivethitha; R, Gauthama Raman M; Ramamritham, Krithi

doi:10.1016/j.rser.2020.110591

Cited by 286 publications

(118 citation statements)

References 45 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…These systems are developed aiming to overcome the limitations of single ML models regarding misspecification, overfitting, and underfitting [27]. In this sense, Somu et al [53] employed the K-means clustering-based convolutional neural networks and long short term memory (KCNN-LSTM) to forecast energy consumption using data from smart meters. In this work, the K-means is employed to identify tendency and seasonal patterns in the time series, while the CNN-LSTM is used in the forecasting process.…”

Section: Related Workmentioning

confidence: 99%

Evolutionary Hybrid System for Energy Consumption Forecasting for Smart Meters

et al. 2021

View full text Add to dashboard Cite

The usage of smart grids is growing steadily around the world. This technology has been proposed as a promising solution to enhance energy efficiency and improve consumption management in buildings. Such benefits are usually associated with the ability of accurately forecasting energy demand. However, the energy consumption series forecasting is a challenge for statistical linear and Machine Learning (ML) techniques due to temporal fluctuations and the presence of linear and non-linear patterns. Traditional statistical techniques are able to model linear patterns, while obtaining poor results in forecasting the non-linear component of the time series. ML techniques are data-driven and can model non-linear patterns, but their feature selection process and parameter specification are a complex task. This paper proposes an Evolutionary Hybrid System (EvoHyS) which combines statistical and ML techniques through error series modeling. EvoHyS is composed of three phases: (i) forecast of the linear and seasonal component of the time series using a Seasonal Autoregressive Integrated Moving Average (SARIMA) model, (ii) forecast of the error series using an ML technique, and (iii) combination of both linear and non-linear forecasts from (i) and (ii) using a a secondary ML model. EvoHyS employs a Genetic Algorithm (GA) for feature selection and hyperparameter optimization in phases (ii) and (iii) aiming to improve its accuracy. An experimental evaluation was conducted using consumption energy data of a smart grid in a one-step-ahead scenario. The proposed hybrid system reaches statistically significant improvements when compared to other statistical, hybrid, and ML approaches from the literature utilizing well known metrics, such as Mean Squared Error (MSE).

show abstract

Section: Related Workmentioning

confidence: 99%

Evolutionary Hybrid System for Energy Consumption Forecasting for Smart Meters

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, in literature, the forecasting methods are divided into three groups, including statistical methods, engineering methods, and data-driven methods [34]. Whereas the datadriven forecasting methods refer to the ensemble machine learning approaches and deep learning methods [35].…”

Section: A Forecasting Methodsmentioning

confidence: 99%

Deep Learning in Energy Modeling: Application in Smart Buildings With Distributed Energy Generation

et al. 2021

View full text Add to dashboard Cite

Over 33% of final energy consumption is used in buildings which leads to nearly 40% of total direct and indirect CO 2 emissions in the world. While energy consumption is steadily rising globally, managing building energy utilization by on-site renewable energy generation can help responding this demand. This paper proposes a deep learning method based on a discrete wavelet transformation and long short-term memory method (DWT-LSTM) and a scheduling framework for the integrated modelling and management of energy demand and supply for buildings. This method considers several factors including a two-step electricity price, uncertainty in climatic factors, availability of renewable energy resources (wind and solar), energy consumption patterns in buildings, and the non-linear relationships between these parameters. This novel method analyzes and continuously learns from data patterns based on hourly, daily, weekly and monthly intervals. The method enables monitoring and controlling renewable energy generation, the share of energy imports from the grid, employment of saving strategy based on the user priority list, and energy storage management. The main objective of the proposed method is to minimize the reliance on the grid and electricity cost, especially during the peak days. The results demonstrate that the proposed method can forecast building energy demand and energy supply with a high level of accuracy, showing a 3.63-8.57% error range in hourly data prediction for one month ahead. The results also show that the method can supply 304 days (83.2%) of a year without reliance on energy grids, decreasing 87.2% in energy demand on one hand and exporting annually 7777 kWh to the grid on the other hand. In addition, the rescheduling framework decreased the imported electricity cost with the higher electricity tariff by 98 %. The combination of the deep learning forecasting, energy storage, and scheduling algorithm enables reducing annual energy import from the grid from 6709 to 858 kWh (84.3%).

show abstract

“…with I and J corresponding to the sensors and continuous days belonging to the bicluster b. penalty measures the sum of the weights of each element that belongs to b and its purpose is to avoid overlapping among biclusters. wp(eij) is calculated using the expression (5). Finally, w_d is given by the expression:…”

Section: Sequential Coveringmentioning

confidence: 99%

“…Doing that that would allow the system managers to carry out actions that can correct such abnormal situations. Different data analysis techniques are usually used in the processing of these data, such as classification [1,2], forecasting [2][3][4][5][6][7][8], and clustering [9][10][11][12]. To this aim, biclustering can come in handy.…”

Section: Introductionmentioning

confidence: 99%

Parallel Evolutionary Biclustering of Short-term Electric Energy Consumption

Pinto-Roa¹,

Medina²,

Román³

et al. 2021

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

The discovery and description of patterns in electric energy consumption time series is fundamental for timely management of the system. A bicluster describes a subset of observation points in a time period in which a consumption pattern occurs as abrupt changes or instabilities homogeneously. Nevertheless, the pattern detection complexity increases with the number of observation points and samples of the study period. In this context, current bi-clustering techniques may not detect significant patterns given the increased search space. This study develops a parallel evolutionary computation scheme to find biclusters in electric energy. Numerical simulations show the benefits of the proposed approach, discovering significantly more electricity consumption patterns compared to a state-of-the-art non-parallel competitive algorithm.

show abstract

A deep learning framework for building energy consumption forecast

Cited by 286 publications

References 45 publications

Evolutionary Hybrid System for Energy Consumption Forecasting for Smart Meters

Evolutionary Hybrid System for Energy Consumption Forecasting for Smart Meters

Deep Learning in Energy Modeling: Application in Smart Buildings With Distributed Energy Generation

Parallel Evolutionary Biclustering of Short-term Electric Energy Consumption

Contact Info

Product

Resources

About