Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Electricity Consumption Forecasting based on Machine Learning Techniques
Electricity is generated by coal, natural gas, renewable resources and nuclear energy, where coal and natural gas generate around 50% of the generated electricity. The global power market is expected to grow by more than 6% during the next five years. Therefore, predicting electricity demand is essential for formulating the energy strategy and developing its policies. In this paper, we apply five prediction models, namely: Artificial Neural Network (ANN), long short-term memory network (LSTM), Bidirectional LSTM (BiLSTM), Gated recurrent unit (GRU) and Deep Neural Network (DNN) to address the problem of electricity demand forecasting. Then, we will evaluate the prediction model's performance based on the Mean Square Error (MSE) and Root Mean Squared Error (RMSE) values. The results demonstrated that the BiLSTM performs better than LSTM, ANN, DNN, RNN and GRU prediction models.
Electricity Consumption Forecasting based on Machine Learning Techniques
Electricity is generated by coal, natural gas, renewable resources and nuclear energy, where coal and natural gas generate around 50% of the generated electricity. The global power market is expected to grow by more than 6% during the next five years. Therefore, predicting electricity demand is essential for formulating the energy strategy and developing its policies. In this paper, we apply five prediction models, namely: Artificial Neural Network (ANN), long short-term memory network (LSTM), Bidirectional LSTM (BiLSTM), Gated recurrent unit (GRU) and Deep Neural Network (DNN) to address the problem of electricity demand forecasting. Then, we will evaluate the prediction model's performance based on the Mean Square Error (MSE) and Root Mean Squared Error (RMSE) values. The results demonstrated that the BiLSTM performs better than LSTM, ANN, DNN, RNN and GRU prediction models.
Electricity Consumption Forecasting based on Machine Learning Techniques
Skaf, Zakwan (Autor:in) / Abdulmouti, Hassan (Autor:in) / Alshareif, Abdulla (Autor:in) / Albanna, Mansoor Hassan (Autor:in)
20.02.2023
2786875 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Day ahead electricity consumption forecasting with MOGUL learning model
| BASE | 2018
Day ahead electricity consumption forecasting with MOGUL learning model
| BASE | 2018
Load Forecasting and Electricity Consumption by Regression Model
| TIBKAT | 2023
Electricity Demand Forecasting Using Regression Techniques
| Springer Verlag | 2019