Zobrazit v EDS

Artificial Neural Network (ANN) Backpropagation for Forecasting 100% Renewable Energy in North Sumatera

Uloženo v:
Podrobná bibliografie
Název: Artificial Neural Network (ANN) Backpropagation for Forecasting 100% Renewable Energy in North Sumatera
Autoři: Rimbawati, Rimbawati, Ambarita, Himsar, Burhanuddin Sitorus, Tulus, Irwanto , M
Zdroj: Environmental Research, Engineering and Management ; Vol. 81 No. 1 (2025); 87-101
Informace o vydavateli: Kaunas University of Technology (KTU), 2025.
Rok vydání: 2025
Témata: optimisation, firefly algorithm, renewable energy, energy trasition, artificial neural network, particle swarm optimisation
Popis: Growing environmental awareness and the increasing need to reduce reliance on fossil fuels have driven the development of renewable energy (RE) technologies, such as micro-hydro, photovoltaics, biomass, geothermal, and biogas. However, the utilisation of RE in North Sumatera remains limited compared with fossil fuels, highlighting the need for optimisation strategies to accelerate the transition towards 100% RE. This study develops a predictive model using the artificial neural network (ANN) backpropagation algorithm to maximise RE contributions, minimise dependence on fossil fuels, and forecast the timeline for a full transition to RE. Data from Perusahaan Listrik Negara (North Sumatera), Independent Power Producers (IPP), and palm oil mills were used to model a hybrid generation system incorporating micro-hydro, hydropower, geothermal, biomass, biogas, and solar energy. Simulations were carried out using the firefly algorithm (FA) and particle swarm optimisation (PSO), with optimisation assessed through the renewable energy contribution ratio (RECR). The results indicate that FA outperforms PSO in meeting RE targets, with an average RECR of −51.514 for FA compared with −911.054 for PSO. Predictions using ANN backpropagation suggest that the transition to 100% RE could be realised by 2064 (FA) and 2065 (PSO). This research offers valuable insights for accelerating the transition to sustainable energy, enhancing energy resilience, and reducing environmental impacts.
Druh dokumentu: Article
Popis souboru: application/pdf
ISSN: 2029-2139
1392-1649
DOI: 10.5755/j01.erem.81.1.37767
Přístupová URL adresa: https://erem.ktu.lt/index.php/erem/article/view/37767
Rights: CC BY
Přístupové číslo: edsair.doi.dedup.....3fe519417bbf1fa757466a8e05662449
Databáze: OpenAIRE
Popis
Abstrakt:Growing environmental awareness and the increasing need to reduce reliance on fossil fuels have driven the development of renewable energy (RE) technologies, such as micro-hydro, photovoltaics, biomass, geothermal, and biogas. However, the utilisation of RE in North Sumatera remains limited compared with fossil fuels, highlighting the need for optimisation strategies to accelerate the transition towards 100% RE. This study develops a predictive model using the artificial neural network (ANN) backpropagation algorithm to maximise RE contributions, minimise dependence on fossil fuels, and forecast the timeline for a full transition to RE. Data from Perusahaan Listrik Negara (North Sumatera), Independent Power Producers (IPP), and palm oil mills were used to model a hybrid generation system incorporating micro-hydro, hydropower, geothermal, biomass, biogas, and solar energy. Simulations were carried out using the firefly algorithm (FA) and particle swarm optimisation (PSO), with optimisation assessed through the renewable energy contribution ratio (RECR). The results indicate that FA outperforms PSO in meeting RE targets, with an average RECR of −51.514 for FA compared with −911.054 for PSO. Predictions using ANN backpropagation suggest that the transition to 100% RE could be realised by 2064 (FA) and 2065 (PSO). This research offers valuable insights for accelerating the transition to sustainable energy, enhancing energy resilience, and reducing environmental impacts.
ISSN:20292139
13921649
DOI:10.5755/j01.erem.81.1.37767