Artificial intelligence models development for profitability factor prediction in concentrated solar power with dual...

Area of Science:

• Renewable Energy Systems
• Solar Thermal Engineering
• Energy Economics

Background:

• Hybrid concentrating solar power (CSP) plants integrate thermal energy storage (TES) and biomass backup to improve reliability and efficiency.
• TES manages energy during low sunlight or high demand, while biomass ensures continuous heat generation when TES is depleted.

Purpose of the Study:

• To develop and utilize three tree optimizers (fine, medium, and coarse) to predict the profitability factor (PF) for hybridized CSP systems.
• To evaluate the economic viability of CSP plants combined with TES and biomass technologies under various operating scenarios.

Main Methods:

• Three operating cases (PT-BC-NB, PT-OS1-MB, PT-OS2-FB) were analyzed using five TES capacities (0-20 h).
• Input variables included capital costs (power island, solar field, TES, biomass boiler) and economic parameters (biomass cost escalation, electricity price escalation).

Main Results:

• Tree optimizers accurately predicted the PF.
• The OS2-No TES configuration achieved the highest profitability (mean PF: 0.009 USD/kWh), nearing grid parity.
• Increasing TES capacity reduced additional revenues but enhanced energy supply stability and reduced biomass consumption.

Conclusions:

• Hybrid CSP systems with biomass backup demonstrate significant economic potential, particularly configurations nearing grid parity.
• TES optimization is crucial for balancing revenue generation with energy supply reliability and biomass consumption.
• The developed tree optimizers provide a robust tool for assessing the profitability of complex hybrid renewable energy systems.