Stimulate hydropower output of mega cascade reservoirs using an improved Kidney Algorithm

JOURNAL OF CLEANER PRODUCTION

卷:244

Article

Zhou, Yanlai^1,2  Guo, Shenglian¹  Xu, Chong-Yu²  Chang, Fi-John³  Chen, Hua¹  Liu, Pan¹  Ming, Bo¹ 

[1] Wuhan Univ, State Key Lab Water Resources & Hydropower Engn S, Wuhan 430072, Hubei, Peoples R China

[2] Univ Oslo, Dept Geosci, POB 1047 Blindern, N-0316 Oslo, Norway

[3] Natl Taiwan Univ, Dept Bioenvironm Syst Engn, Taipei 10617, Taiwan

关键词: Hydropower production;    Cascade reservoirs;    Optimal operation;    Water-energy nexus;    Artificial intelligence (AI);    Jin-sha river;   

DOI  :  10.1016/j.jclepro.2019.118613

来源: Elsevier

【 摘 要 】

The evolutionary algorithms can solve reservoir operation with a fast convergence rate whereas the major impediments in handling the joint operation of mega cascade reservoirs easily trigger the technical bottlenecks, i.e. trapping into a local optimum, instability and loss of good solutions. This study proposes a methodology that fuses three auxiliary strategies into the Kidney Algorithm (KA) to optimize the hydropower output for conquering the bottlenecks in the KA concerning the joint operation of six mega cascade reservoirs located in the Jin-Sha River basin in China. The proposed theme would contribute to the application of the state-of-the-art evolutionary algorithms in boosting the cleaner hydropower production of mega cascade reservoirs. The three auxiliary strategies are that: firstly, the exploration and exploitation strategy is employed to stimulate the movement of solutions to surmount technical drawback of trapping into a local optimum; secondly, the adaptive strategy is used to automatically adjust algorithm parameter values to overcome the instability problem; lastly, the elitism strategy is introduced to preserve the best solution at every epoch to avoid the loss of good solutions. Our methodology, without expanding or upgrading hydraulic infrastructures, can increase the hydropower production of the six mega cascade reservoirs by 7.8%, as compared with the standard operation policy. The hydropower production can reach 4.8 billion kW.h/year, which can decrease 3.77 billion kg/year in CO2 emission, and bring 217.44 million USD/year in hydropower benefits. The improved KA can considerably increase the reliability and resilience of hydropower output as well as largely decrease the vulnerability of hydropower output. The results suggest that our methodology can stimulate hydropower output to yield more benefits regarding cleaner production, carbon emission reduction and sustainability. (C) 2019 Elsevier Ltd. All rights reserved.

【 授权许可】

Free