A hybrid model of system dynamics and genetic algorithm to increase crude palm oil production in Malaysia

Palm oil industry in Malaysia is facing a stagnant growth in terms of crude palm oil (CPO) production as compared to Indonesia due to three issues namely (i) the scarcity of plantation area, (ii) labour shortage, and (iii) the rising demand from palm-based biodiesel industry. Focusing on these issues, previous studies have been adopted various approaches. However, these non-hybridized methods have some shortcomings
and can be improved by hybridization method. Hence, the objective of this research is to determine the optimal policy options to increase CPO production in Malaysia. In this research, a hybrid model of system dynamics (SD) and genetic algorithm (GA) was developed to determine the optimal policy in increasing the CPO production in Malaysia. Five policy variables namely mechanization adoption rate, average replanting, biodiesel mandates in transportation, industrial and 4 other relevant sectors were examined to determine optimal policy values. These five policy variables were tested in three scenarios: year 2017, year 2020, and in phases until 2050. From all the scenarios, the phase optimization emerged as the most effective in producing suitable policy variable values in order to obtain the best possible value of CPO production in year 2050 up to 20 GA population runs. The hybrid of SD-GA through phase optimization process is capable to recommend policies that are plausible to be implemented to avoid unwarranted shock to the industry. Furthermore, the hybrid model provides the ability of identifying the policy variables related to the objective function at any specific time line. From the managerial perspectives, this research helps the stakeholders in palm oil industry towards making a better future investment
decision.