Advanced AI technique for optimizing the operation strategy of an industrial heat pump coupled with thermal energy storage

Utilizing industrial chillers and heat pumps units with environmentally friendly refrigerants plays a pivotal role in the green transition. It contributes significantly to the phase-out of fossil fuels. High-capacity heat pumps incur higher operational costs. Meeting peak demand involves underutilized capacity. Combining thermal storage with optimal planning is a prudent solution to address these challenges. This paper presents an innovative and thorough approach to long-term operational planning, designed to determine the optimal size of the unit accurately. This approach also involves a novel procedure that modifies the range of the upper and lower bounds of the algorithm's decision variables. To check the strength of the proposed methodology, the long-term operational planning of an cutting-edge industrial factory-built reversible chiller and heat pump has been considered with three different modes; (1) the nominal-capacity heat pump that lacks storage, (2) the unit with the nominal heat pump integrated with adjustable hot, and cold storage capacity and (3) the unit with adjustable heat pump capacity integrated with adjustable hot and cold storage capacity. An Artificial Neural Network approach has been employed to estimate the unit's performance using experimental data accurately. The implementation of the proposed methodology resulted in a 65 % reduction in operational costs for the optimal case. During low-demand periods, savings of up to 44 % are possible, but as demand increases, management becomes more challenging, and savings decrease to 26 %. This study opens new avenues for the development of more efficient renewable energy systems through more innovative operational planning. • Theory of long-term operational planning is proposed for the optimal sizing of the thermal systems. • With a 39 % and 43 % price decrease, financial equilibrium is achieved after 6 and 5 years for modes 2 and 3, respectively. • During low demand, savings can reach 44%, but as demand rises, management is harder and savings drop to 26%. • The electricity price volatility may reduce operating costs by 38 %, and even in conditions with low volatility by 22 %.