Estimates of energy consumption in Turkey using neural networks with the teaching–learning-based optimization algorithm

Uzlu, Ergun; Kankal, Murat; Akpınar, Adem; Dede, Tayfun

doi:10.1016/j.energy.2014.07.078

Cited by 105 publications

(56 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The second category of studies includes those that are based on non-numerical simulations conducted by artificial intelligence software, such as fuzzy logic, genetic algorithms, neural networks, support vector machines, ant colony algorithms and particle swarm optimization algorithms. Specifically, Uzlu et al [6] predicted Turkey's energy consumption using the artificial neural network method; Ekonomou [7] estimated Greece's energy consumption in 2012 and 2015 by training a multilayer perceptron model with actual energy consumption data; and Ceylan and Ozturk [8] used a genetic algorithm to predict Turkey's energy consumption through 2025 based on gross national product (GNP), population, and import and export data. In addition to the above two categories, coherent models of the dynamic mechanisms involved in the relationship between economics, energy and emissions can be constructed to conduct comprehensive assessments of the driving force of energy consumption and economic impacts of emissions control, which leads to the third category of computable economics modeling to analyze energy consumption and carbon emissions.…”

Section: Introductionmentioning

confidence: 99%

An Agent-Based Model to Project China’s Energy Consumption and Carbon Emission Peaks at Multiple Levels

Mohamed

Wang

2017

Sustainability

View full text Add to dashboard Cite

Abstract:To assess whether China's emissions will peak around 2030, we forecast energy consumption and carbon emissions in China. We use an agent-based model driven by enterprises' innovation. Results show some differences in both energy consumption peaks and carbon emission peaks when we compare trends at different levels. We find that carbon emissions and energy consumption will peak in 2027 and 2028, respectively. However, the primary, secondary, and tertiary industries will reach energy consumption in different years: 2023, 2029, and 2022, respectively, and reach carbon emission peaks in 2022, 2028, and 2022, respectively. At the sectoral level, we find a wider range of energy consumption peaks and carbon emission peaks. Peak energy consumption occurs between 2020 and 2034, and peak carbon emissions between 2020 and 2032. Commercial and catering businesses, utilities and resident services, and finance and insurance achieve peak energy consumption and carbon emissions earliest in 2020, while building materials and other non-metallic mineral products manufacturing and metal products manufacturing are the two latest sectors to reach peak energy consumption and emissions, in 2034 and 2032, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

An Agent-Based Model to Project China’s Energy Consumption and Carbon Emission Peaks at Multiple Levels

Mohamed

Wang

2017

Sustainability

View full text Add to dashboard Cite

show abstract

“…Hidden layer Output layer As shown in Figure 5, the final output of the network can be expressed as [40][41][42] …”

Section: Input Layermentioning

confidence: 99%

“…In the weight update phase, the error is propagated from the output layer back through the whole network, until each neuron has an associated error value that can reflect its contribution to the original output. These error values are then used to calculate the gradients of the loss function that are fed to the update rules to renew the weights [40][41][42].…”

Section: Input Layermentioning

confidence: 99%

See 1 more Smart Citation

Deep Belief Network Based Hybrid Model for Building Energy Consumption Prediction

Ding

et al. 2018

Energies

View full text Add to dashboard Cite

Abstract:To enhance the prediction performance for building energy consumption, this paper presents a modified deep belief network (DBN) based hybrid model. The proposed hybrid model combines the outputs from the DBN model with the energy-consuming pattern to yield the final prediction results. The energy-consuming pattern in this study represents the periodicity property of building energy consumption and can be extracted from the observed historical energy consumption data. The residual data generated by removing the energy-consuming pattern from the original data are utilized to train the modified DBN model. The training of the modified DBN includes two steps, the first one of which adopts the contrastive divergence (CD) algorithm to optimize the hidden parameters in a pre-train way, while the second one determines the output weighting vector by the least squares method. The proposed hybrid model is applied to two kinds of building energy consumption data sets that have different energy-consuming patterns (daily-periodicity and weekly-periodicity). In order to examine the advantages of the proposed model, four popular artificial intelligence methods-the backward propagation neural network (BPNN), the generalized radial basis function neural network (GRBFNN), the extreme learning machine (ELM), and the support vector regressor (SVR) are chosen as the comparative approaches. Experimental results demonstrate that the proposed DBN based hybrid model has the best performance compared with the comparative techniques. Another thing to be mentioned is that all the predictors constructed by utilizing the energy-consuming patterns perform better than those designed only by the original data. This verifies the usefulness of the incorporation of the energy-consuming patterns. The proposed approach can also be extended and applied to some other similar prediction problems that have periodicity patterns, e.g., the traffic flow forecasting and the electricity consumption prediction.

show abstract

“…It was observed that applying ABC to ANN could improve the estimations of the network outputs. Uzlu et al [42] applied ABC and a recently developed advanced optimization algorithm, Teaching-Learning Based Optimization (TLBO), to the regression functions of the data for the estimation of the berm parameters in understanding sediment movements. Although these optimization techniques have been applied to a wide range of hydrological and hydraulics problems, such as rainfall runo modeling, hydrologic forecasting, and coastal engineering, there is not any in RFFA with the ABC and TLBO.…”

Section: Introductionmentioning

confidence: 99%

The estimation of flood quantiles in ungauged sites using teaching-learning based optimization and artificial bee colony algorithms

et al. 2017

Self Cite

View full text Add to dashboard Cite

Abstract. In this study, a Regional Flood Frequency Analysis (RFFA) was applied to 33 stream gauging stations in the Eastern Black Sea Basin, Turkey. Homogeneity of the region was determined by discordancy (D i ) and heterogeneity measures (H i ) based on L-moments. Generalized extreme-value, lognormal, Pearson type III, and generalized logistic distributions were tted to the ood data of the homogeneous region. Based on the appropriate distribution for the region, ood quantiles were estimated for return periods of T = 5; 10; 25; 50; 100, and 500 years. A non-linear regression model was then developed to determine the relationship between ood discharges and meteorological and hydrological characteristics of the catchment. In order to compare regression analysis with other models, Arti cial Bee Colony algorithm (ABC) and Teaching-Learning Based Optimization (TLBO) models were developed. The equations were obtained using the ABC and TLBO algorithms to estimate ood discharges for di erent return periods. The analysis showed that the TLBO and ABC results were superior to the regression analysis. Error values indicated that the TLBO method yielded better results for the estimation of ood quantiles for di erent independent variables.

show abstract

Estimates of energy consumption in Turkey using neural networks with the teaching–learning-based optimization algorithm

Cited by 105 publications

References 50 publications

An Agent-Based Model to Project China’s Energy Consumption and Carbon Emission Peaks at Multiple Levels

An Agent-Based Model to Project China’s Energy Consumption and Carbon Emission Peaks at Multiple Levels

Deep Belief Network Based Hybrid Model for Building Energy Consumption Prediction

The estimation of flood quantiles in ungauged sites using teaching-learning based optimization and artificial bee colony algorithms

Contact Info

Product

Resources

About