The study focuses on comparing two deep learning models, Long Short-Term Memory (LSTM) and Bidirectional LSTM (BLSTM), for short-term forecasting of univariate electric consumption time series. The objective is to assess the robustness of these models by using four different datasets with varying contexts and scales. The datasets include the power consumption of a household in France, a university building in Santarém, Brazil, the Tétouan city zones in Morocco, and the aggregated electric demand in Singapore. To evaluate the performance of the models, several metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared (R2) were calculated using a time series cross-validation scheme. Additionally, Friedman's test was applied to normalized RMSE results to determine if there is a statistically significant difference between LSTM and BLSTM. The results show that BLSTM outperforms LSTM with a statistically significant difference (p = 0.0455). This indicates that bidirectional weight updating significantly improves the performance of LSTM when dealing with different scales of electric power consumption. Furthermore, this study provides valuable insights into the application of deep learning models for electric consumption prediction and highlights the effectiveness of BLSTM compared to LSTM. It also emphasizes the importance of considering bidirectional weight updating in forecasting tasks related to energy efficiency and market dynamics.
The study looked at two different models, LSTM and BLSTM, to predict how much electricity people will use in the future. They used four different sets of data from different places to test the models. They used some numbers to see how well the models worked, like RMSE, MAE, MAPE, and R2. They also did a special test called Friedman's test to compare the two models. The results showed that BLSTM was better than LSTM at predicting electricity use. This is important because it can help us save energy and understand how the market works."
Definitions
- LSTM: A type of model used for predicting things based on patterns in data.
- BLSTM: Another type of model that is similar to LSTM but can look at data in both directions.
- Electric consumption: How much electricity people use.
- Time series: Data that shows how something changes over time.
- Performance evaluation metrics: Numbers used to measure how well something works.
- Statistical significance: A way to tell if something is really true or just by chance.
- Bidirectional weight updating: A way of making a model better by adjusting its settings based on data from both past and future.
Comparing Deep Learning Models for Short-Term Forecasting of Univariate Electric Consumption Time Series
Deep learning models have become increasingly popular in recent years due to their ability to accurately predict future events and trends. In this article, we will discuss a research paper that compares two deep learning models, Long Short-Term Memory (LSTM) and Bidirectional LSTM (BLSTM), for short-term forecasting of univariate electric consumption time series. The objective is to assess the robustness of these models by using four different datasets with varying contexts and scales.
Background
Electricity consumption prediction is an important task in many areas such as energy efficiency, market dynamics, and smart grid management. Accurate predictions are essential for efficient resource allocation and cost savings. Traditional methods such as linear regression or autoregressive integrated moving average (ARIMA) have been used for electricity consumption forecasting but they often lack accuracy when dealing with complex data patterns or nonlinear relationships between variables. Deep learning models offer more accurate results by taking into account multiple factors at once and can be applied to various types of problems including time series forecasting.
Methodology
In this study, the researchers compared two deep learning models: Long Short-Term Memory (LSTM) and Bidirectional LSTM (BLSTM). These models were evaluated on four different datasets with varying contexts and scales: the power consumption of a household in France, a university building in Santarém, Brazil, the Tétouan city zones in Morocco, and the aggregated electric demand in Singapore. To evaluate the performance of the models several metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared (R2) were calculated using a time series cross-validation scheme. Additionally, Friedman's test was applied to normalized RMSE results to determine if there is a statistically significant difference between LSTM and BLSTM.
Results
The results show that BLSTM outperforms LSTM with a statistically significant difference (p = 0.0455). This indicates that bidirectional weight updating significantly improves the performance of LSTM when dealing with different scales of electric power consumption. Furthermore, this study provides valuable insights into the application of deep learning models for electric consumption prediction and highlights the effectiveness of BLSTM compared to L
Electric consumption prediction methods are investigated for many reasons such as decision-making related to energy efficiency as well as for anticipating demand in the energy market dynamics. The objective of the present work is the comparison between two Deep Learning models, namely the Long Short-Term Memory (LSTM) and Bi-directional LSTM (BLSTM) for univariate electric consumption Time Series (TS) short-term forecast. The Data Sets (DSs) were selected for their different contexts and scales, aiming the assessment of the models' robustness. Four DSs were used, related to the power consumption of: (a) a household in France; (b) a university building in Santar\'em, Brazil; (c) the T\'etouan city zones, in Morocco; and (c) the Singapore aggregated electric demand. The metrics RMSE, MAE, MAPE and R2 were calculated in a TS cross-validation scheme. The Friedman's test was applied to normalized RMSE (NRMSE) results, showing that BLSTM outperforms LSTM with statistically significant difference (p = 0.0455), corroborating the fact that bidirectional weight updating improves significantly the LSTM performance concerning different scales of electric power consumption.
