Precision animal feed formulation: An evolutionary multi-objective approach

Abstract

Most livestock producers aim for optimal ways of feeding their animals. Conventional algorithms approach optimum feed formulation by minimizing feed costs while satisfying constraints related to nutritional requirements of the animal. The optimization process needs to be performed every time a nutritional requirement is changed due to the nonlinear relationship between the relaxation of the different nutritional requirements and the feed cost. Consequently, decision-making becomes a time-consuming trial and error process. In addition, the nonlinear relationship changes depending on the type of materials used, their nutritional compositions and costs as well as the animal's nutritional requirements. Therefore, in this work, we formulated a multi-objective feed formulation problem comprising of two objects -a) minimizing feed cost and b) minimizing deviation from the specified requirements. The problem is solved using a population-based evolutionary multi-objective optimization algorithm (NSGA-II) that results in an optimal set of comprised solutions in a single run. The availability of the entire set of comprised solutions facilitates the understanding of the relationship between different nutritional requirements and cost, thus leading to a more efficient decision-making process. We demonstrated the applicability of the proposed method by performing experimental simulations on several cases of dairy and beef cattle feed formulation.

Effect of Feeding Improved Grass Hays and Eragrostis tef Straw Silage on Milk Yield, Nitrogen Utilization, and Methane Emission of Lactating Fogera Dairy Cows in Ethiopia

“…Moreover, Hussien et al [ 62 ] reported even lower milk yields (1.4 kg/d) for Fogera dairy cows fed a natural grass hay basal diet supplemented with concentrate in separate feeding. This variation might be due to the TMR feeding system used in this study that can increase the precision-feeding of dairy cows [ 63 ]. There is no TMR-based lactating dairy cow feeding system for indigenous dairy cows in tropical regions to compare the milk composition result of this study.…”

Technological Advancements and Economics in Plant Production Systems: How to Retrofit?

“…Thus, in NSGA-II, the environmental selection is made using non-dominated sorting followed by crowding distance, which is supposed to provide convergence and diversity. Non-dominated sorting and crowding distance are used in NSGA II to obtain the Pareto dominance of final tradeoff solutions ( Uyeh et al, 2019a ). The parameters of the optimization algorithm were set as follows:…”

“…The average run time for the proposed algorithm was 180 s. The simulations were done on a 3.59 GHz AMD Ryzen 5 3500X 6-Core processor, 16 GB random access memory, and 256 GB solid-state drive with Windows 10 operating system in MATLAB ( Matlab and Simulink, 2012 ). We conducted several simulations using guidelines from a previous manuscript ( Deb et al, 2002 ) that proposed the algorithm and our experience working with this algorithm ( Uyeh et al, 2018 , 2019a , b ). We finetuned and gradually increased the generations (iteration) until we got no further improvements.…”

Grid Search for Lowest Root Mean Squared Error in Predicting Optimal Sensor Location in Protected Cultivation Systems

“…This is done to improve monitoring and control of micro-climate parameters and sometimes facilitate remote-controlled and autonomous cultivation. Decisions may be made based on various actuators used to regulate heating, lighting, cooling, dosing of CO 2 and fertilizers, dehumidification, irrigation, screening, fogging, as examples ( Nelson, 1991 ; Uyeh et al, 2019 , 2021 ; Bhujel et al, 2020 ; Gadekallu et al, 2021 ). These actuators operate based on sensors providing feedback on measured data for the control loop set points configured in a computing device ( Stanghellini, 2013 ; Graamans et al, 2018 ).…”

“…Multiclass models have been used to develop multivariate statistical methods in agriculture ( Guzmán et al, 2019 ) and Principal Component Analysis - whale optimization-based neural networks to classify diseases in plants ( Li et al, 2010 ). Others include algorithms and systems for improved decision-making and optimizations ( Nelson, 1991 ; DeFacio et al, 2002 ; Vox et al, 2010 ; Park and Park, 2011 ; Uyeh et al, 2019 ; Gadekallu et al, 2021 ). Machine learning provides opportunities to solve complex tasks such as optimal sensor placement because of its capabilities to efficiently compute vast and complex datasets with a high success ratio and fewer errors ( Syed and Hachem, 2019a , b ).…”