Resumen
Currently, energy and environmental efficiency are critical aspects in wastewater treatment plants (WWTPs). In fact, WWTPs are significant energy consumers, especially in the active sludge process (ASP) for the N-ammonia removal. In this paper, we face the challenge of simultaneously improving the economic and environmental performance by using a reinforcement learning approach. This approach improves the costs of the N-ammonia removal process in the extended WWTP Benchmark Simulation Model 1 (BSM1). It also performs better than a manual plant operator when disturbances affect the plant. Satisfactory experimental results show significant savings in a year of a working BSM1 plant.