Heat load prediction through recurrent neural network in district heating and cooling systems

Kato, Kosuke; Sakawa, Masatoshi; Ishimaru, K.; Ushiro, Satoshi; Shibano, Toshihiro

doi:10.1109/icsmc.2008.4811482

Cited by 49 publications

(41 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their work, SVM was compared with static neural network and result showed SVM better than static neural network in terms of model performance. Dynamic neural network method which includes time dependence was presented by Kato et al [27] to predict heating load of district heating and cooling system based on maximum and minimum air temperature. Kalogirou et al [28] used Jordan Elman recurrent dynamic network to predict energy consumption of a passive solar building system based on seasonal information, masonry thickness and thermal insulation.…”

Section: Introductionmentioning

confidence: 99%

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Paudel

Elmtiri

Kling

et al. 2014

Energy and Buildings

106

View full text Add to dashboard Cite

This paper presents the building heating demand prediction model with occupancy profile and operational heating power level characteristics in short time horizon (a couple of days) using artificial neural network. In addition, novel pseudo dynamic transitional model is introduced, which consider time dependent attributes of operational power level characteristics and its effect in the overall model performance is outlined. Pseudo dynamic model is applied to a case study of French Institution building and compared its results with static and other pseudo dynamic neural network models. The results show the coefficients of correlation in static and pseudo dynamic neural network model of 0.82 and 0.89 (with energy consumption error of 0.02%) during the learning phase, and 0.61 and 0.85 during the prediction phase respectively. Further, orthogonal array design is applied to the pseudo dynamic model to check the schedule of occupancy profile and operational heating power level characteristics. The results show the new schedule and provide the robust design for pseudo dynamic model. Due to prediction in short time horizon, it finds application for Energy Services Company (ESCOs) to manage the heating load for dynamic control of heat production system.

show abstract

Section: Introductionmentioning

confidence: 99%

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Paudel

Elmtiri

Kling

et al. 2014

Energy and Buildings

106

View full text Add to dashboard Cite

show abstract

“…[7] [5] [4] and [9] presented a load forecasting methods in DHS with limitation to the production environment. [5] proposed a new heat load prediction method which uses a recurrent neural network to deal with the dynamic variation of heat load and its characteristics. The approach shows decent prediction accuracy for non-stationary heat load.…”

Section: Background and Related Workmentioning

confidence: 99%

“…This is due to the effectiveness of the ML approach. For estimating energy demand at the consumption environment commonly used data-driven methods are SVR [2], Multiple Regression [3], Neural Networks based methods [4] [5]. In specific to heat load forecast, some of the advantages of data-driven approach over a classical approach include the ability to discover models from large volumes of data and the ability to adapt and update models based on new data [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting heat load for smart district heating systems: A machine learning approach

Idowu

Saguna

Åhlund

et al. 2014

2014 IEEE International Conference on Smart Grid Communications (SmartGridComm)

View full text Add to dashboard Cite

Abstract-The rapid increase in energy demand requires effective measures to plan and optimize resources for efficient energy production within a smart grid environment. This paper presents a data driven approach to forecasting heat load for multifamily apartment buildings in a District Heating System (DHS). The forecasting model is built using six and eleven weeks of data from five building substations. The external factors and internal factors influencing the heat load in substations are parameters used as our model's input. Short-term forecast models are generated using four supervised Machine Learning (ML) techniques: Support Vector Regression (SVR), Regression Tree, Feed Forwards Neural Network (FFNN) and Multiple Linear Regression (MLR). Performance comparison among these ML methods was carried out. The effects of combining the internal and external factors influencing heat load at substations was studied. The models are evaluated with varying horizon up to 24-hours ahead. The results show that SVR has the best accuracy of 5.6% MAPE for the best-case scenario.

show abstract

“…Seasonal Autoregressive Integrated Moving Average (SARIMA) heat load models were developed in [19]. Recurrent neural networks were used in [20] for heat load prediction. In [21] an ensemble of decision trees was used for building an online learning algorithm for heat load forecasting in DHS.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the most influential parameters of heat load in district heating systems

Petković

Protić

Shamshirband

et al. 2015

Energy and Buildings

View full text Add to dashboard Cite

Heat load prediction through recurrent neural network in district heating and cooling systems

Cited by 49 publications

References 7 publications

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Pseudo dynamic transitional modeling of building heating energy demand using artificial neural network

Forecasting heat load for smart district heating systems: A machine learning approach

Evaluation of the most influential parameters of heat load in district heating systems

Contact Info

Product

Resources

About