Various multistage ensembles for prediction of heating energy consumption

Jovanović, Radiša; Sretenović, Aleksandra

doi:10.4173/mic.2015.2.4

Cited by 8 publications

(13 citation statements)

References 33 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The innovative approach comprised of: using ensemble technique (combining outputs of individual networks in single prediction), multi-stage ensembles (using neural network for combining the outputs of individual models), using k-means clustering for selecting ensemble members, kmeans clustering of input dataset. More details about these methodologies and achieved results can be found in [9][10][11][12]. The accuracy of the neural networks models for prediction of hourly heating energy use is investigated in this paper, as an extension of the previously published work.…”

Section: Model Developmentmentioning

confidence: 98%

See 1 more Smart Citation

Prediction of Hourly Heating Energy Use for Hvac Using Feedforward Neural Networks

Sretenović¹,

Jovanović²,

Novaković³

et al. 2017

Proceedings of the International Scientific Conference - Sinteza 2017

View full text Add to dashboard Cite

In this paper, feedforward neural network, one of the most widely used artificial intelligence methods, was proposed for the prediction of hourly heating energy use of one university campus. Two different approaches were presented: network that provides one output (heating energy use for selected hour) and network with 24 outputs (daily profile of heating energy use). The proposed models were trained and tested using real measured hourly energy use and meteorological data. It has been shown that both models can be used for the prediction with satisfying accuracy. This kind of prediction can be used for calculating accurate energy bills, which is very useful considering that the significant part of the campus is being leased. Estimating energy use for different weather conditions can help in energy planning.

show abstract

Section: Model Developmentmentioning

confidence: 98%

“…In previous work, various models for prediction of daily heating energy use and their improvements were proposed [9][10][11][12]. For training and testing the models, the coldest period for years 2009-2012 was selected.…”

Section: Model Developmentmentioning

confidence: 99%

Prediction of Hourly Heating Energy Use for Hvac Using Feedforward Neural Networks

Sretenović¹,

Jovanović²,

Novaković³

et al. 2017

Proceedings of the International Scientific Conference - Sinteza 2017

View full text Add to dashboard Cite

show abstract

“…First, clustering had been used to divide networks in groups, and then the most accurate individual network was selected for the ensemble. In paper [12] FFNN and ANFIS networks in the second level were used to create the multistage ensemble. Also, different ANFIS models were constructed: using different membership functions (trimf, gbellmf, gaussmf), fuzzy C-means clustering (FCM) and subtractive clustering.…”

Section: Prediction Indices For Various Modelsmentioning

confidence: 99%

“…Ensemble, as a technique of combining individual network`s outputs, achieves higher accuracy. In [12] various multistage ensembles were compared. The k-means clustering was used for resampling training dataset before creating the ensembles in [13].…”

Section: Introductionmentioning

confidence: 99%

Support vector machine for the prediction of heating energy use

et al. 2018

Self Cite

View full text Add to dashboard Cite

Prediction of a building energy use for heating is very important for adequate energy planning. In this paper the daily district heating use of one university campus was predicted using the support vector machine model. Support vector machine is the artificial intelligence method that has recently proved that it can achieve comparable, or even better prediction results than the much more used artificial neural networks. The proposed model was trained and tested on the real, measured data. The model accuracy was compared with the results of the previously published models (various neural networks and their ensembles) on the same database. The results showed that the support vector machine model can achieve better results than the individual neural networks, but also better than the conventional and multistage ensembles. It is expected that this theoretically well-known methodology finds wider application, especially in prediction tasks.

show abstract

“…On the other hand, compared with previous, there are not great number of scientific papers and research dealing with shortterm heat load prediction for district heating systems. These papers show that ambient temperature together with social component described customer needs and behavior has the greatest influence on heat response from customers and needs for heat energy delivered from heat source [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Heat load prediction of small district heating system using artificial neural networks

et al. 2016

View full text Add to dashboard Cite

Accurate models for heat load prediction are essential to the operation and planning of a utility company. Load prediction helps a heat utility to make important and advanced decisions in district heating systems. As a popular data driven method, artificial neural networks are often used for prediction. The main idea is to achieve quality prediction for a short period in order to reduce the consumption of heat energy production and increased coefficient of exploitation of equipment. To improve the short term prediction accuracy, this paper presents a kind of improved artificial neural network model for 1 to 7 days ahead prediction of heat consumption of energy produced in small district heating system. Historical data set of one small district heating system from city of Nis, Serbia, was used. Particle swarm optimization is applied to adjust artificial neural network weights and threshold values. In this paper, application of feed forward artificial neural network for short-term prediction for period of 1, 3, and 7 days, of small district heating system, is presented. Two test data sets were considered with different interruption non-stationary performances. Comparison of prediction accuracy between regular and improved artificial neural network model was done. The comparison results reveal that improved artificial neural network model have better accuracy than that of artificial neural network ones.

show abstract

Various multistage ensembles for prediction of heating energy consumption

Cited by 8 publications

References 33 publications

Prediction of Hourly Heating Energy Use for Hvac Using Feedforward Neural Networks

Prediction of Hourly Heating Energy Use for Hvac Using Feedforward Neural Networks

Support vector machine for the prediction of heating energy use

Heat load prediction of small district heating system using artificial neural networks

Contact Info

Product

Resources

About