Skip to main content
Research Q&A
66 main questions · 539+ sub-questions · Linked to thesis evidence
Problem → Framework → Results → Policy
↑↓ Navigate, Esc Clear filters
F1Layer 5 / 10medium~5 min read
How does ENSM compare to the baseline forecasting models?
R²=0.9799 (generation), 0.9131 (capacity), MAE=1.5 GW, RMSE=1.8 GW. <0.1% constraint violations vs 8.2% LSTM. All 17 pairwise tests p<0.001.
Key Takeaway
ENSM statistically outperforms 17 baselines; maintains accuracy to 26-year horizon.
Detailed Explanation
The study demonstrates statistically significant superiority of ENSM across 17 baseline models: In Accuracy Metrics R²=0.9799 (generation forecasting), R²=0.9131 (capacity forecasting), MAE=1.5 GW (Mean Absolute Error), RMSE=1.8 GW (Root Mean Squared Error). As you can see, we are getting a clear idea of the performance of our model w.r.t. other algorithms and we see that we outperform all of them. Energy balance violations are less than 0.1% for ENSM, 8.2% for LSTM, 12.1% for Prophet. Capacity factor bounds are maintained at 100% for ENSM while Prophet 73% and ARIMA 61%. The Diebold-Mariano test results confirm that our predictive accuracy is significantly better than all baselines in all 17 pairwise tests at p<0.001. Moreover, the Wilcoxon signed-rank effect size r=0.72 indicates a large effect size. Finally, the ANOVA shows an F statistic of 47.89 at p<0.001 and we can reject the null hypothesis that all the models perform equally. The ENSM maintains extreme performance accuracy to the 26 year horizon, with R²=0.91 at year 26. In stark contrast, the pure data-driven baselines experience severe degradation in performance (R²=0.43 for LSTM at year 26). This result demonstrates the essential advantage that deriving the architecture out of the theory provides for such planning problems that require long-horizon predictions.
Why It Matters
Research significance: Validates ENSM superiority.
Energy policy relevance: Ensures Turkey forecasts are reliable.
Methodological contribution: 78 pairwise comparisons, ANOVA, Wilcoxon.
Research Graph — Related Questions
F1 How does ENSM compare to the baseline fo…
Sub-questions (10)
F1.1Layer 5 / 10medium~1 min read
What is ENSM R² for generation forecasting?
R²=0.9799.
Key Takeaway
Generation forecast.
Detailed Explanation
ENSM achieves R²=0.9799 for generation forecasting.
Why It Matters
Research significance: Accuracy.
Energy policy relevance: Reliability.
Methodological contribution: F1.
F1.2Layer 5 / 10medium~1 min read
What is ENSM R² for capacity forecasting?
R²=0.9131.
Key Takeaway
Long-horizon.
Detailed Explanation
ENSM achieves R²=0.9131 for capacity forecasting.
Why It Matters
Research significance: Accuracy.
Energy policy relevance: Planning.
Methodological contribution: F1.
F1.3Layer 5 / 10medium~1 min read
What is ENSM MAE?
MAE=1.5 GW.
Key Takeaway
Mean Absolute Error.
Detailed Explanation
ENSM MAE is 1.5 GW for capacity forecasts.
Why It Matters
Research significance: Error metric.
Energy policy relevance: N/A.
Methodological contribution: F1.
F1.4Layer 5 / 10medium~1 min read
How do energy balance violations compare?
<0.1% ENSM vs 8.2% LSTM.
Key Takeaway
Constraint satisfaction.
Detailed Explanation
ENSM <0.1% vs LSTM 8.2% energy balance violations.
Why It Matters
Research significance: Feasibility.
Energy policy relevance: Credibility.
Methodological contribution: F1.
F1.5Layer 5 / 10medium~1 min read
What do the 17 pairwise Diebold-Mariano tests show?
All p<0.001.
Key Takeaway
ENSM > all baselines.
Detailed Explanation
17 pairwise tests: ENSM significantly better than all baselines (p<0.001).
Why It Matters
Research significance: Statistical rigor.
Energy policy relevance: Credibility.
Methodological contribution: F1.
F1.6Layer 5 / 10medium~1 min read
What is Wilcoxon effect size r=0.72?
Large effect per Cohen.
Key Takeaway
ENSM vs baselines.
Detailed Explanation
Wilcoxon r=0.72 indicates large effect size.
Why It Matters
Research significance: Effect size.
Energy policy relevance: N/A.
Methodological contribution: F1.
F1.7Layer 5 / 10medium~1 min read
What is ANOVA F=47.89?
Rejects null of equal models.
Key Takeaway
Model comparison.
Detailed Explanation
ANOVA F=47.89 rejects null that all models perform equally.
Why It Matters
Research significance: Statistical test.
Energy policy relevance: N/A.
Methodological contribution: F1.
F1.8Layer 5 / 10medium~1 min read
How does ENSM perform at year 26?
R²=0.91 vs LSTM R²=0.43.
Key Takeaway
Theory-derived advantage.
Detailed Explanation
ENSM maintains R²=0.91 at year 26; LSTM degrades to R²=0.43.
Why It Matters
Research significance: Long-horizon.
Energy policy relevance: Planning.
Methodological contribution: F1.
F1.9Layer 5 / 10medium~1 min read
What are capacity factor bounds?
100% ENSM vs 73% Prophet, 61% ARIMA.
Key Takeaway
Bounds maintained.
Detailed Explanation
ENSM maintains 100% capacity factor bounds; Prophet 73%, ARIMA 61%.
Why It Matters
Research significance: Feasibility.
Energy policy relevance: N/A.
Methodological contribution: F1.
F1.10Layer 5 / 10medium~1 min read
How many baselines does ENSM outperform?
17 forecasting baselines.
Key Takeaway
All outperformed.
Detailed Explanation
ENSM outperforms all 17 baseline forecasting models.
Why It Matters
Research significance: Benchmark.
Energy policy relevance: Credibility.
Methodological contribution: F1.