Robust Building Energy Load Forecasting Using Physically-Based Kernel Models

Prakash, Anand Krishnan; Xu, Susu; Rajagopal, Ram; Noh, Hae Young

doi:10.3390/en11040862

Cited by 27 publications

(12 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a hybrid method frequently requires long computation time because of the boundary advancement procedure and master information during the model improvement process [84]. There have been studies on hybrid methods that have focused on electrical consumption [85][86][87][88][89][90][91][92], cooling and heating load [79,80,[93][94][95], energy consumption [96][97][98][99][100][101], thermal load [102], thermal response [103] and load demand [104]. Based on the aforementioned studies, a summary of their contributions and limitations is presented in Table 3.…”

Section: ] Yumentioning

confidence: 99%

A Review of Energy Consumption Forecasting in Smart Buildings: Methods, Input Variables, Forecasting Horizon and Metrics

et al. 2020

View full text Add to dashboard Cite

Buildings are among the largest energy consumers in the world. As new technologies have been developed, great advances have been made in buildings, turning conventional buildings into smart buildings. These smart buildings have allowed for greater supervision and control of the energy resources within the buildings, taking steps to energy management strategies to achieve significant energy savings. The forecast of energy consumption in buildings has been a very important element in these energy strategies since it allows adjusting the operation of buildings so that energy can be used more efficiently. This paper presents a review of energy consumption forecasting in smart buildings for improving energy efficiency. Different forecasting methods are studied in nonresidential and residential buildings. Following this, the literature is analyzed in terms of forecasting objectives, input variables, forecasting methods and prediction horizon. In conclusion, the paper examines future challenges for building energy consumption forecasting.

show abstract

Section: ] Yumentioning

confidence: 99%

A Review of Energy Consumption Forecasting in Smart Buildings: Methods, Input Variables, Forecasting Horizon and Metrics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Some of these models are developed for specific application areas such as building performance measurement and verification [14][15][16][17], building control [18][19][20] and demand-side management [21,22], whereas a significant number of studies are application agnostic. Literature demonstrates the capability of supervised ML algorithms such as artificial neural networks (ANN) [23], support vector machines (SVM) [24], decision trees [25,26], Gaussian processes [27][28][29] and nearest neighbours [30], among others, in developing reliable building load forecast models. In contrast to the physics based models, the ML based load forecast models require lesser amount of information from the buildings.…”

Section: Literature Reviewmentioning

confidence: 99%

A Machine Learning Pipeline for Demand Response Capacity Scheduling

Krishnadas¹,

Kiprakis

2020

Energies

View full text Add to dashboard Cite

Demand response (DR) is an integral component of smart grid operations that offers the necessary flexibility to support its decarbonisation. In incentive-based DR programs, deviations from the scheduled DR capacity affect the grid’s energy balance and result in revenue losses for the DR participants. This issue aggravates with increasing DR delivery from participants such as large consumer buildings who have limited standard methods to follow for DR capacity scheduling. Load curtailment based DR capacity availability from such consumers can be forecasted reliably with the help of supervised machine learning (ML) models. This study demonstrates the development of data-driven ML based total and flexible load forecast models for a retail building. The ML model development tasks such as data pre-processing, training-testing dataset preparation, cross-validation, algorithm selection, hyperparameter optimisation, feature ranking, model selection and model evaluation are guided by deployment-centric design criteria such as reliability, computational efficiency and scalability. Based on the selected performance metrics, the day-ahead and week-ahead ML based load forecast models developed for the retail building are shown to outperform the timeseries persistence models used for benchmarking. Furthermore, the deployment of these models for DR capacity scheduling is proposed as an ML pipeline that can be realised with the help of ML workflows, computational resources as well as systems for monitoring and visualisation. The ML pipeline ensures faster, cost-effective and large-scale deployment of forecast models that support reliable DR capacity scheduling without affecting the grid’s energy balance. Minimisation of revenue losses encourages increased DR participation from large consumer buildings, ensuring further flexibility in the smart grid.

show abstract

“…Their finding has shown the potential trend of growing improvement from the security index during 2015 to 2020, while the security degree and the corresponding alarm are found to be negative. Prakash, Xu, Rajagopal and Noh [16] presented a forecasting technique according to Gaussian process regression (GPR) to estimate an energy load, and the result reflected that the above method outperformed precisely as compared to other forecasting models. While Mehedintu, Sterpu and Soava [17] embarked on a study to estimate and predict the share of renewable energy consumption in final energy use within the European Union by 2020.…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting Energy-Related Carbon Dioxide Emissions in Thailand’s Construction Sector by Enriching the LS-ARIMAXi-ECM Model

Sutthichaimethee

Kubaha

2018

Sustainability

View full text Add to dashboard Cite

The Thailand Development Policy focuses on the simultaneous growth of the economy, society, and environment. Long-term goals have been set to improve economic and social well-being. At the same time, these aim to reduce the emission of CO 2 in the future, especially in the construction sector, which is deemed important in terms of national development and is a high generator of greenhouse gas. In order to achieve national sustainable development, policy formulation and planning is becoming necessary and requires a tool to undertake such a formulation. The tool is none other than the forecasting of CO 2 emissions in long-term energy consumption to produce a complete and accurate formulation. This research aims to study and forecast energy-related carbon dioxide emissions in Thailand's construction sector by applying a model incorporating the longand short-term auto-regressive (AR), integrated (I), moving average (MA) with exogenous variables (Xi) and the error correction mechanism (LS-ARIMAXi-ECM) model. This model is established and attempts to fill the gaps left by the old models. In fact, the model is constructed based on factors that are causal and influential for changes in CO 2 emissions. Both independent variables and dependent variables must be stationary at the same level. In addition, the LS-ARIMAXi-ECM model deploys a co-integration analysis and error correction mechanism (ECM) in its modeling. The study's findings reveal that the LS-ARIMAXi (2, 1, 1, X t−1 )-ECM model is a forecasting model with an appropriate time period (t − i), as justified by the Q-test statistic and is not a spurious model. Therefore, it is used to forecast CO 2 emissions for the next 20 years (2019 to 2038). From the study, the results show that CO 2 emissions in the construction sector will increase by 37.88% or 61.09 Mt CO 2 Eq. in 2038. Also, the LS-ARIMAXi (2, 1, 1, X t−1 )-ECM model has been evaluated regarding its performance, and it produces a mean absolute percentage error (MAPE) of 1.01% and root mean square error (RMSE) of 0.93% as compared to the old models. Overall, the results indicate that determining future national sustainable development policies requires an appropriate forecasting model, which is built upon causal and contextual factors according to relevant sectors, to serve as an important tool for future sustainable planning.

show abstract

Robust Building Energy Load Forecasting Using Physically-Based Kernel Models

Cited by 27 publications

References 55 publications

A Review of Energy Consumption Forecasting in Smart Buildings: Methods, Input Variables, Forecasting Horizon and Metrics

A Review of Energy Consumption Forecasting in Smart Buildings: Methods, Input Variables, Forecasting Horizon and Metrics

A Machine Learning Pipeline for Demand Response Capacity Scheduling

Forecasting Energy-Related Carbon Dioxide Emissions in Thailand’s Construction Sector by Enriching the LS-ARIMAXi-ECM Model

Contact Info

Product

Resources

About