A survey of artificial neural network-based prediction models for thermal properties of biomass
- Olatunji, Obafemi, Akinlabi, Stephen, Oluseyi, Ajayi, Madushele, Nkosinathi
- Authors: Olatunji, Obafemi , Akinlabi, Stephen , Oluseyi, Ajayi , Madushele, Nkosinathi
- Date: 2019
- Subjects: ANN , Biomass , Heating value
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/398288 , uj:33150 , Citation: Olatunji, O. et al. 2019. A survey of artificial neural network-based prediction models for thermal properties of biomass.
- Description: Abstract: The global community has supported the need for sustainable and renewable energy due to environmental concerns from the greenhouse gas emission. Biomass stands as one of the most abundant and predictable sources of renewable energy. Therefore, to explore the maximum potential of biomass, a detailed understanding of its embedded potential is needed. However, most experimental procedures require equipment that is highly sophisticated and expensive. The advancement of knowledge in artificial intelligence and blockchain technology is unlocking new potential prediction accuracy for biomass thermal properties. Artificial Neural Network (ANN) is proving to be a vital tool that can enhance the research development in biomass energy prediction. This review highlights the stages in ANN modeling and the application of ANN in Biomass thermal value prediction. It identifies the research gaps in the current status of research on ANN as related to biomass and the direction for further study.
- Full Text:
- Authors: Olatunji, Obafemi , Akinlabi, Stephen , Oluseyi, Ajayi , Madushele, Nkosinathi
- Date: 2019
- Subjects: ANN , Biomass , Heating value
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/398288 , uj:33150 , Citation: Olatunji, O. et al. 2019. A survey of artificial neural network-based prediction models for thermal properties of biomass.
- Description: Abstract: The global community has supported the need for sustainable and renewable energy due to environmental concerns from the greenhouse gas emission. Biomass stands as one of the most abundant and predictable sources of renewable energy. Therefore, to explore the maximum potential of biomass, a detailed understanding of its embedded potential is needed. However, most experimental procedures require equipment that is highly sophisticated and expensive. The advancement of knowledge in artificial intelligence and blockchain technology is unlocking new potential prediction accuracy for biomass thermal properties. Artificial Neural Network (ANN) is proving to be a vital tool that can enhance the research development in biomass energy prediction. This review highlights the stages in ANN modeling and the application of ANN in Biomass thermal value prediction. It identifies the research gaps in the current status of research on ANN as related to biomass and the direction for further study.
- Full Text:
Estimation of municipal solid waste (MSW) com-bustion enthalpy for energy recovery
- Olatunji, Obafemi, Akinlabi, Stephen, Madushele, Nkosinathi, Adedeji, Paul A.
- Authors: Olatunji, Obafemi , Akinlabi, Stephen , Madushele, Nkosinathi , Adedeji, Paul A.
- Date: 2019
- Subjects: Renewable energy, Climate change, Energy recovery
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/396616 , uj:32938 , Citation : Olatunji, O. 2019. Estimation of municipal solid waste (MSW) com-bustion enthalpy for energy recovery , 10.4108/eai.11-6-2019.159119
- Description: Abstract : The global challenges of climate change have been compounded by an unprecedented level of environmental pollution consequent upon the municipal solid waste, MSW generation. Recent advances by researchers and policymakers are focused on sustainable and renewable energy sources which are technologically feasible, environmentally friendly, and economically viable. Waste-to-fuel initiative is therefore highly beneficial to our environment while also improves the socio-economic well-being the nations. This current study introduces an adaptive neuro-fuzzy inference systems (ANFIS) model optimised with Particle Swarm Optimisation (PSO) algorithm aimed at predicting the enthalpy of combustion of MSW fuel based on the moisture content (H2O), Carbon, Hydrogen, Oxygen, Nitrogen, Sulphur, and Ash contents. This model was trained with 86 MSW biomass data and further tested with a new 37 data points. The developed model was observed to performed better in term of the accuracy when compared with other existing models in the literature. The model was evaluated based on some known error estimation. The values of Root Mean Squared Error (RMSE), Mean Absolute Deviation (MAD), Mean Absolute Percentage Error (MAPE), Log Accuracy ratio (LAR), Coefficient of Correlation (CC) were 3.6277, 22.6202, 0.0337, 0.8673 respectively at computation time (CT) of 36.96 secs. Regression analysis was also carried out to determine the level of correlation between the experimental and predicted high heating values (HHV).
- Full Text:
- Authors: Olatunji, Obafemi , Akinlabi, Stephen , Madushele, Nkosinathi , Adedeji, Paul A.
- Date: 2019
- Subjects: Renewable energy, Climate change, Energy recovery
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/396616 , uj:32938 , Citation : Olatunji, O. 2019. Estimation of municipal solid waste (MSW) com-bustion enthalpy for energy recovery , 10.4108/eai.11-6-2019.159119
- Description: Abstract : The global challenges of climate change have been compounded by an unprecedented level of environmental pollution consequent upon the municipal solid waste, MSW generation. Recent advances by researchers and policymakers are focused on sustainable and renewable energy sources which are technologically feasible, environmentally friendly, and economically viable. Waste-to-fuel initiative is therefore highly beneficial to our environment while also improves the socio-economic well-being the nations. This current study introduces an adaptive neuro-fuzzy inference systems (ANFIS) model optimised with Particle Swarm Optimisation (PSO) algorithm aimed at predicting the enthalpy of combustion of MSW fuel based on the moisture content (H2O), Carbon, Hydrogen, Oxygen, Nitrogen, Sulphur, and Ash contents. This model was trained with 86 MSW biomass data and further tested with a new 37 data points. The developed model was observed to performed better in term of the accuracy when compared with other existing models in the literature. The model was evaluated based on some known error estimation. The values of Root Mean Squared Error (RMSE), Mean Absolute Deviation (MAD), Mean Absolute Percentage Error (MAPE), Log Accuracy ratio (LAR), Coefficient of Correlation (CC) were 3.6277, 22.6202, 0.0337, 0.8673 respectively at computation time (CT) of 36.96 secs. Regression analysis was also carried out to determine the level of correlation between the experimental and predicted high heating values (HHV).
- Full Text:
Neuro-fuzzy mid-term forecasting of electricity consumption using meteorological data
- Adedeji, Paul A, Akinlabi, Stephen, Madushele, Nkosinathi, Olatunji, Obafemi
- Authors: Adedeji, Paul A , Akinlabi, Stephen , Madushele, Nkosinathi , Olatunji, Obafemi
- Date: 2019
- Subjects: ANFIS , Electricity Consumption , FCM
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/406893 , uj:34228 , Citation: Adedeji, P.A. et al. 2019 : Neuro-fuzzy mid-term forecasting of electricity consumption using meteorological data.
- Description: Abstract : Forecasting energy consumption is highly essential for strategic and operational planning. This study uses the Adaptive-Neuro-Fuzzy Inference System (ANFIS) for a mid-term forecast of electricity consumption. The model comprises of three meteorological variables as inputs and electricity consumption as output. Two ANFIS models with two clustering techniques (Fuzzy c-Means (FCM) and Grid Partitioning (GP) were developed (ANFIS-FCM and ANFIS- GP) to forecast monthly energy consumption based on meteorological variables. The performance of each model was determined using known statistical metrics. This compares the predicted electricity consumption with the observed and a statistical significance between the two reported. ANFIS-FCM model recorded a better mean absolute deviation (MAD), root mean square (RMSE), and mean absolute percentage error (MAPE) values of 0.396, 0.738, and 8.613 respectively compared to the ANFIS-GP model, which has MAD, RMSE, and MAPE values of 0.450, 0.762, and 9.430 values respectively. The study established that FCM is a good clustering technique in ANFIS compared to GP and recommended a comparison between the two techniques on hybrid ANFIS model.
- Full Text:
- Authors: Adedeji, Paul A , Akinlabi, Stephen , Madushele, Nkosinathi , Olatunji, Obafemi
- Date: 2019
- Subjects: ANFIS , Electricity Consumption , FCM
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/406893 , uj:34228 , Citation: Adedeji, P.A. et al. 2019 : Neuro-fuzzy mid-term forecasting of electricity consumption using meteorological data.
- Description: Abstract : Forecasting energy consumption is highly essential for strategic and operational planning. This study uses the Adaptive-Neuro-Fuzzy Inference System (ANFIS) for a mid-term forecast of electricity consumption. The model comprises of three meteorological variables as inputs and electricity consumption as output. Two ANFIS models with two clustering techniques (Fuzzy c-Means (FCM) and Grid Partitioning (GP) were developed (ANFIS-FCM and ANFIS- GP) to forecast monthly energy consumption based on meteorological variables. The performance of each model was determined using known statistical metrics. This compares the predicted electricity consumption with the observed and a statistical significance between the two reported. ANFIS-FCM model recorded a better mean absolute deviation (MAD), root mean square (RMSE), and mean absolute percentage error (MAPE) values of 0.396, 0.738, and 8.613 respectively compared to the ANFIS-GP model, which has MAD, RMSE, and MAPE values of 0.450, 0.762, and 9.430 values respectively. The study established that FCM is a good clustering technique in ANFIS compared to GP and recommended a comparison between the two techniques on hybrid ANFIS model.
- Full Text:
The future of renewable energy for electricity generation in sub-Saharan Africa
- Adedeji, Paul A, Akinlabi, Stephen, Madushele, Nkosinathi, Olatunji, Obafemi
- Authors: Adedeji, Paul A , Akinlabi, Stephen , Madushele, Nkosinathi , Olatunji, Obafemi
- Date: 2019
- Subjects: Non-linear autoregressive ANN , Renewable energy , sub-Saharan Africa
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/406901 , uj:34229 , Citation: Adedeji, P.A. et al. 2019 : The future of renewable energy for electricity generation in sub-Saharan Africa.
- Description: Abstract : Energy transition in the last decade has experienced increased quota of renewable energy in the global energy mix. In sub-Saharan Africa (SSA), the transition from the fossil fuel to the renewable energy source has been gradual. The state of renewable energy in the region in the next decade is the focus of this study. This study uses a single-layer perceptron artificial neural network (SLP-ANN) to backcast from 2015 to 2006 and forecast from 2016 to 2020 the percentage of renewable energy for electricity generation, exempting the hydropower in the energy mix of the SSA based on historical data. The backcast percentage renewable energy mix was evaluated using known statistical metrics for accuracy measures. The root mean square error (RMSE), mean absolute deviation (MAD) and mean absolute percentage error (MAPE) obtained were 0.29, 0.18, and 14.69 respectively. The result shows possibility of an increase in the percentage of renewable energy in the electricity sector in the region. In 2020, the percentage of renewable energy in sub-Saharan region is expected to rise to 4.13% with exclusion of the hydropower. With government policies encouraging the growth of the renewable energy as a means of power generation in the region, the predicted percentage and even more can be realized.
- Full Text:
- Authors: Adedeji, Paul A , Akinlabi, Stephen , Madushele, Nkosinathi , Olatunji, Obafemi
- Date: 2019
- Subjects: Non-linear autoregressive ANN , Renewable energy , sub-Saharan Africa
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/406901 , uj:34229 , Citation: Adedeji, P.A. et al. 2019 : The future of renewable energy for electricity generation in sub-Saharan Africa.
- Description: Abstract : Energy transition in the last decade has experienced increased quota of renewable energy in the global energy mix. In sub-Saharan Africa (SSA), the transition from the fossil fuel to the renewable energy source has been gradual. The state of renewable energy in the region in the next decade is the focus of this study. This study uses a single-layer perceptron artificial neural network (SLP-ANN) to backcast from 2015 to 2006 and forecast from 2016 to 2020 the percentage of renewable energy for electricity generation, exempting the hydropower in the energy mix of the SSA based on historical data. The backcast percentage renewable energy mix was evaluated using known statistical metrics for accuracy measures. The root mean square error (RMSE), mean absolute deviation (MAD) and mean absolute percentage error (MAPE) obtained were 0.29, 0.18, and 14.69 respectively. The result shows possibility of an increase in the percentage of renewable energy in the electricity sector in the region. In 2020, the percentage of renewable energy in sub-Saharan region is expected to rise to 4.13% with exclusion of the hydropower. With government policies encouraging the growth of the renewable energy as a means of power generation in the region, the predicted percentage and even more can be realized.
- Full Text:
- «
- ‹
- 1
- ›
- »