Empowering digital twins with large language models for global temporal feature learning

Journal of Manufacturing Systems, Journal Year: 2024, Volume and Issue: 74, P. 83 - 99

Published: March 8, 2024

Language: Английский

---

Accuracy improvement of the load forecasting in the district heating system by the informer-based framework with the optimal step size selection

Energy, Journal Year: 2024, Volume and Issue: 291, P. 130347 - 130347

Published: Jan. 17, 2024

Language: Английский

---

District heating load patterns and short-term forecasting for buildings and city level

Energy, Journal Year: 2023, Volume and Issue: 289, P. 129866 - 129866

Published: Dec. 6, 2023

District heating (DH) load forecasting for buildings and cities is essential DH production planning demand-side management. This study analyzes compares the hourly patterns a city five different types of over an entire year. The various operating modes introduce nonlinear dependencies between outdoor temperature. We compare prediction accuracies multiple linear regression (MLR) artificial neural network (ANN) models. Without dependencies, both ANN MLR provide good, almost identical accuracies. In case superior to MLR. However, novel clustering method eliminates improves accuracy on par with ANN. methods can automatically adapt nonlinearities. advantage combining that it simpler than designing method, although manual work required. addition, more insight into how depends factors compared 'black box' developed methodology be widely applied building- city-level analyses in systems combined or without domestic hot water consumption.

Language: Английский

---

Comparative study of univariate and multivariate strategy for short-term forecasting of heat demand density: Exploring single and hybrid deep learning models

Energy and AI, Journal Year: 2024, Volume and Issue: 16, P. 100343 - 100343

Published: Jan. 24, 2024

Accurate short-term forecasting of heating energy demand is needed for achieving optimal building management, cost savings, environmental sustainability, and responsible consumption. Furthermore, prediction contributes to zero-energy performance in cold climates. Given the critical importance this study evaluated six prevalent deep-learning algorithms predict load, including single hybrid models. The overall best-performing predictors were models using Convolutional Neural Networks, regardless whether they multivariate or univariate. Nevertheless, while performed better first hour, univariate often more accurate final 24 hours. Thus, predictor timestep was a Network-Recurrent Network model with coefficient determination (R²) 0.98 lowest mean absolute error. Yet, Network-Long Short-Term Memory an R² 0.80. Also, accuracy reduced faster per hour compared These findings suggest that may be suited early predictions, later time steps. Hence, combining can enhance at various timesteps high fidelity offering comprehensive tool management.

Language: Английский

---

Short-term power load forecasting based on hybrid feature extraction and parallel BiLSTM network

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 119, P. 109631 - 109631

Published: Sept. 3, 2024

Language: Английский

---

Digital twin modeling for district heating network based on hydraulic resistance identification and heat load prediction

Energy, Journal Year: 2023, Volume and Issue: 288, P. 129726 - 129726

Published: Dec. 1, 2023

Language: Английский

---

Makine Öğrenmesinde Sektörel Veri Entegrasyonu: Emlak Gayrimenkul Yatırım Ortaklığı Hisse Senedi Fiyat Tahmini

Selçuk Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, Journal Year: 2025, Volume and Issue: 56, P. 147 - 161

Published: April 30, 2025

Bu çalışmanın temel amacı, Emlak Konut Gayrimenkul Yatırım Ortaklığı (EKGYO) hisse senedi fiyatlarını tahmin etmek amacıyla sektörel veriler ve gelişmiş makine öğrenimi modellerini kullanmaktır. EKGYO fiyatları ile makroekonomik göstergeler arasındaki güçlü korelasyonlar, genel ekonomik şartların gayrimenkul sektörünün finansal performansı üzerindeki etkilerini gözler önüne sermektedir. Çalışmada, USD/TL kuru, konut fiyat endeksi, yurt içi üretici endeksi (Yİ-ÜFE) ipotekli satışları gibi önemli incelenmiş bu ilişki detaylı bir şekilde analiz edilmiştir. Ampirik bulgular, Kalman Filtresi modelinin en düşük ortalama mutlak hata (MAE), kare (MSE) kök (RMSE) değerleri yüksek doğruluğunu sağladığını göstermektedir. durum, verilerdeki dalgalanmaları yönetebilme doğru tahminler sunabilme potansiyelini ortaya koymaktadır. karşılaştırıldığında biraz daha oranlarına sahip olmasına rağmen ETS de iyi performans sergilediği görülmüştür. Buna karşın, Neural Prophet modeli, mevsimsellik trendleri yakalamaya yönelik tasarımına rağmen, karmaşık veri setlerinde veya kısa vadeli tahminlerde bazı sınırlamaları işaret eden sahiptir.

---

Rolling discrete grey periodic power model with interaction effect under dual processing and its application

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 254, P. 124487 - 124487

Published: June 13, 2024

Language: Английский

---

Time series forecasting of microalgae cultivation for a sustainable wastewater treatment

Process Safety and Environmental Protection, Journal Year: 2025, Volume and Issue: unknown, P. 106845 - 106845

Published: Jan. 1, 2025

Language: Английский

---

Financial asset allocation strategies using statistical and machine learning models: Evidence from comprehensive scenario testing

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 113193 - 113193

Published: May 1, 2025

Language: Английский

---