Bernard T. AgyemanUniversity of Alberta, Jinfeng LiuUniversity of Alberta, Sirish L. Shah
{"title":"用于灌溉调度的混合整数 MPC 中的 ReLU 代理变量","authors":"Bernard T. AgyemanUniversity of Alberta, Jinfeng LiuUniversity of Alberta, Sirish L. Shah","doi":"arxiv-2409.12082","DOIUrl":null,"url":null,"abstract":"Efficient water management in agriculture is important for mitigating the\ngrowing freshwater scarcity crisis. Mixed-integer Model Predictive Control\n(MPC) has emerged as an effective approach for addressing the complex\nscheduling problems in agricultural irrigation. However, the computational\ncomplexity of mixed-integer MPC still poses a significant challenge,\nparticularly in large-scale applications. This study proposes an approach to\nenhance the computational efficiency of mixed-integer MPC-based irrigation\nschedulers by employing ReLU surrogate models to describe the soil moisture\ndynamics of the agricultural field. By leveraging the mixed-integer linear\nrepresentation of the ReLU operator, the proposed approach transforms the\nmixed-integer MPC-based scheduler with a quadratic cost function into a\nmixed-integer quadratic program, which is the simplest class of mixed-integer\nnonlinear programming problems that can be efficiently solved using global\noptimization solvers. The effectiveness of this approach is demonstrated\nthrough comparative studies conducted on a large-scale agricultural field\nacross two growing seasons, involving other machine learning surrogate models,\nspecifically Long Short-Term Memory (LSTM) networks, and the widely used\ntriggered irrigation scheduling method. The ReLU-based approach significantly\nreduces solution times -- by up to 99.5\\% -- while achieving comparable\nperformance to the LSTM approach in terms of water savings and Irrigation Water\nUse Efficiency (IWUE). Moreover, the ReLU-based approach maintains enhanced\nperformance in terms of total prescribed irrigation and IWUE compared to the\nwidely-used triggered irrigation scheduling method.","PeriodicalId":501175,"journal":{"name":"arXiv - EE - Systems and Control","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"ReLU Surrogates in Mixed-Integer MPC for Irrigation Scheduling\",\"authors\":\"Bernard T. AgyemanUniversity of Alberta, Jinfeng LiuUniversity of Alberta, Sirish L. Shah\",\"doi\":\"arxiv-2409.12082\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Efficient water management in agriculture is important for mitigating the\\ngrowing freshwater scarcity crisis. Mixed-integer Model Predictive Control\\n(MPC) has emerged as an effective approach for addressing the complex\\nscheduling problems in agricultural irrigation. However, the computational\\ncomplexity of mixed-integer MPC still poses a significant challenge,\\nparticularly in large-scale applications. This study proposes an approach to\\nenhance the computational efficiency of mixed-integer MPC-based irrigation\\nschedulers by employing ReLU surrogate models to describe the soil moisture\\ndynamics of the agricultural field. By leveraging the mixed-integer linear\\nrepresentation of the ReLU operator, the proposed approach transforms the\\nmixed-integer MPC-based scheduler with a quadratic cost function into a\\nmixed-integer quadratic program, which is the simplest class of mixed-integer\\nnonlinear programming problems that can be efficiently solved using global\\noptimization solvers. The effectiveness of this approach is demonstrated\\nthrough comparative studies conducted on a large-scale agricultural field\\nacross two growing seasons, involving other machine learning surrogate models,\\nspecifically Long Short-Term Memory (LSTM) networks, and the widely used\\ntriggered irrigation scheduling method. The ReLU-based approach significantly\\nreduces solution times -- by up to 99.5\\\\% -- while achieving comparable\\nperformance to the LSTM approach in terms of water savings and Irrigation Water\\nUse Efficiency (IWUE). Moreover, the ReLU-based approach maintains enhanced\\nperformance in terms of total prescribed irrigation and IWUE compared to the\\nwidely-used triggered irrigation scheduling method.\",\"PeriodicalId\":501175,\"journal\":{\"name\":\"arXiv - EE - Systems and Control\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Systems and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.12082\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Systems and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.12082","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
ReLU Surrogates in Mixed-Integer MPC for Irrigation Scheduling
Efficient water management in agriculture is important for mitigating the
growing freshwater scarcity crisis. Mixed-integer Model Predictive Control
(MPC) has emerged as an effective approach for addressing the complex
scheduling problems in agricultural irrigation. However, the computational
complexity of mixed-integer MPC still poses a significant challenge,
particularly in large-scale applications. This study proposes an approach to
enhance the computational efficiency of mixed-integer MPC-based irrigation
schedulers by employing ReLU surrogate models to describe the soil moisture
dynamics of the agricultural field. By leveraging the mixed-integer linear
representation of the ReLU operator, the proposed approach transforms the
mixed-integer MPC-based scheduler with a quadratic cost function into a
mixed-integer quadratic program, which is the simplest class of mixed-integer
nonlinear programming problems that can be efficiently solved using global
optimization solvers. The effectiveness of this approach is demonstrated
through comparative studies conducted on a large-scale agricultural field
across two growing seasons, involving other machine learning surrogate models,
specifically Long Short-Term Memory (LSTM) networks, and the widely used
triggered irrigation scheduling method. The ReLU-based approach significantly
reduces solution times -- by up to 99.5\% -- while achieving comparable
performance to the LSTM approach in terms of water savings and Irrigation Water
Use Efficiency (IWUE). Moreover, the ReLU-based approach maintains enhanced
performance in terms of total prescribed irrigation and IWUE compared to the
widely-used triggered irrigation scheduling method.