Figure 9 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
(a) Boxplots and strip plots of the best found ML models on validation dataset. (b) Boxplots and strip plots of the best found ML models on test dataset.
Source publication
Accurate prediction of energy consumption in district heating systems plays an important role in supporting effective and clean energy production and distribution in dense urban areas. Predictive models are needed for flexible and cost-effective operation of energy production and usage, e.g., using peak shaving or load shifting to compensate for he...
Contexts in source publication
Context 1
... the model from the row is statistically better, worse, or has the same performance as the model from the column, the sign will be +, −, or , respectively. Figure 9 shows box and strip plots of the best found median ML models on validation and test datasets. The x-axis denotes the model, and the y-axis denotes the validation or test error depending on the dataset. ...
Context 2
... Figure 9 and Table 10, we can see that NN shows the best results on validation data for all five metrics (MAE, MAPE, RMSE, IA, R²), which indicates correct modeling and the most accurate predictions of the tuned NN model. On the test data, the LR, ENCV, and SVR models show very similar results in MAE, MAPE, and IA, indicating that they have similar prediction performance, but SVR has a slightly higher R². ...
