Building's electricity consumption prediction using optimized artificial neural networks and principal component analysis

Li, Kangji; Chenglei, Hu; Liu, Guohai; Xue, Wenping

doi:10.1016/j.enbuild.2015.09.002

Cited by 188 publications

(64 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The total yearly energy consumption per square meter of the heated/cooled area is estimated to be 87. 16,133.94, and 125.55 kWh/m 2 for the three techniques, respectively.…”

Section: The Test Buildingmentioning

confidence: 99%

“…Different types of mathematical models have been used in the past to estimate the space heating/cooling energy use of buildings. Statistical approaches such as regression [13][14][15], Artificial Neural Networks [16], and Support Vector Machines [17] are found in the literature for energy predictions. A combined physical and statistical approach has been used in [18].…”

Section: The Test Buildingmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Space Heating Energy Consumption of Residential Buildings Based on Traditional and Model-Based Techniques

Perera

Skeie

2017

Buildings

View full text Add to dashboard Cite

This paper presents a comparison of different scenarios in controlling the space heating systems in residential buildings. The space heating energy consumption of a three-storey residential building is estimated using traditional control methods (fixed-temperature schedule and fixed-time schedule) and a mathematical model-based control strategy. The model-based control technique takes the usage pattern of the building into account and operates the heaters based on the calculated heating time of the building. The results from the experiments confirm that the use of a model in heating control is the best option, which can save up to 1400 kWh and 320 kWh per year compared to a fixed-temperature schedule and fixed-time schedule, respectively.

show abstract

“…The total yearly energy consumption per square meter of the heated/cooled area is estimated to be 87. 16,133.94, and 125.55 kWh/m 2 for the three techniques, respectively.…”

Section: The Test Buildingmentioning

confidence: 99%

Section: The Test Buildingmentioning

confidence: 99%

Comparison of Space Heating Energy Consumption of Residential Buildings Based on Traditional and Model-Based Techniques

Perera

Skeie

2017

Buildings

View full text Add to dashboard Cite

show abstract

“…In order to improve its capability of global search and avoid local minimization, the genetic operations including crossover and mutation are further introduced to update method of PSO algorithm. The improved PSO algorithm is proposed by Li et al 33 The crossover and mutation equations are the essential part of the algorithm, which are described as follows:…”

Section: Model Ordermentioning

confidence: 99%

Comprehensive approach to modeling and simulation of dynamic soft-sensing design for real-time building energy consumption

Liu

Fang

et al. 2017

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

This research develops a multi-layer hybrid soft-sensor model to improve the accuracy of building thermal load prediction using integrated data. The multi-layer hybrid model (autoregressive and particle swarm optimization neural network) hybridizes an autoregressive model with exogenous inputs and a particle swarm optimization neural network. The distributed sensors' experimental scenario was set in a medium-sized office building located in Shanghai, which has applied this multi-layer hybrid model to evaluate the prediction accuracy, meanwhile its performance was also compared with several commonly used methods under different evaluation criteria. Through frequency-domain decomposition, the heat balance equation is used to validate the autoregressive and particle swarm optimization neural network model. Both the simulation of building thermal load and experiment results demonstrate that the proposed autoregressive and particle swarm optimization neural network method can recognize soft sensing of the building thermal load much more quickly and efficiently, and achieve higher accuracy in both cooling load and heating load prediction. KeywordsAutoregressive model with exogenous inputs, particle swarm optimization neural network, multi-layer hybrid model (autoregressive and particle swarm optimization neural network), soft sensor, thermal load Date

show abstract

“…Also, is tried to find out the pattern of electrical power usage with the dataset which is prepared by real data. Many of proposed models we find in energy load forecasting, in [5] different forecasting methods were utilized to formulate prediction models of the electricity demand in Thailand are autoregressive integrated moving average (ARIMA) [7,16], artificial neural network (ANN) and multiple linear regression (MLR) then compared the performance of these three approaches the results showed that the ANN model has better mean absolute percentage error (MAPE) than ARIMA and MLR model respectively [7,18].…”

Section: Introductionmentioning

confidence: 99%

Short-Term Forecasting of Electricity Consumption in Palestine Using Artificial Neural Networks

Salahat¹

2017

IJAIA

View full text Add to dashboard Cite

show abstract

Building's electricity consumption prediction using optimized artificial neural networks and principal component analysis

Cited by 188 publications

References 26 publications

Comparison of Space Heating Energy Consumption of Residential Buildings Based on Traditional and Model-Based Techniques

Comparison of Space Heating Energy Consumption of Residential Buildings Based on Traditional and Model-Based Techniques

Comprehensive approach to modeling and simulation of dynamic soft-sensing design for real-time building energy consumption

Short-Term Forecasting of Electricity Consumption in Palestine Using Artificial Neural Networks

Contact Info

Product

Resources

About