Techno-economic implications and cost of forecasting errors in solar PV power production using optimized deep learning models

Journal Article · Thu Mar 27 00:00:00 EDT 2025 · Energy

DOI:https://doi.org/10.1016/j.energy.2025.135877· OSTI ID:2587373

Al-Dahidi, Sameer ^[1]; Alrbai, Mohammad ^[2]; Rinchi, Bilal ^[1]; Alahmer, Hussein ^[3]; Al-Ghussain, Loiy ^[4]; Hayajneh, Hassan S. ^[5]; Alahmer, Ali ^[6]

---

1. German Jordanian University, Amman (Jordan)
2. University of Jordan, Amman (Jordan)
3. Al-Balqa Applied University, Al-Salt (Jordan)
4. Argonne National Laboratory (ANL), Argonne, IL (United States)
5. Purdue University Northwest, Hammond, IN (United States)
6. Tuskegee University, AL (United States)

Accurate solar Photovoltaic (PV) power forecasting is important for enhancing both the performance and economic feasibility of PV systems. This study evaluates several deep learning models, including Dense Neural Networks (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and a hybrid LSTMCNN model, for predicting PV power production one day in advance. Prior to optimization, the models exhibited relatively high errors, with the best model (DNN) achieving a Root Mean Square Error (RMSE) of 31.13 kW and a coefficient of determination (R²) of 62.15 %. After employing Bayesian optimization, the LSTM-CNN model demonstrated the best performance, with the RMSE reduced to 9.79 kW and R² improved to 97.62 %, showcasing significant enhancement in predictive accuracy. Here, the economic evaluation considered three cases: rewards for underestimation (0.08 USD/kWh), no rewards, and penalties for both over-and underestimation (120 % of the utility tariff). In the rewards scenario, the LSTM-CNN model reduced the Levelized Cost of Electricity (LCOE) by 4 %, while in the penalty scenario, a backup diesel generator would have increased the LCOE by 49 %. Additionally, the LSTM-CNN model minimized financial losses, achieving the lowest penalties and maximizing net cash flow compared to other models, demonstrating its overall technical and economic superiority.

• Research Organization: Argonne National Laboratory (ANL), Argonne, IL (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: AC02-06CH11357
• OSTI ID: 2587373
• Journal Information: Energy, Journal Name: Energy Vol. 323; ISSN 0360-5442
• Publisher: Elsevier BV
• Country of Publication: United States
• Language: English

Related Subjects

Deep learning
Forecasting accuracy
Imbalance rewards and penalties
Levelized cost of electricity
Photovoltaic power forecast
Techno-economic evaluation