Big Data Driven Agricultural Products Supply Chain Management: A Trustworthy Scheduling Optimization Approach

Big data is promoting the development of supply chain design and management. The problem of trustworthy scheduling by using big data is challenging, and it significantly influences the performance of agricultural products supply chain (APSC) management. Currently, there are various approaches to optimize scheduling of APSC, but most of them can only tackle the problem with primary objectives (time and cost) or are limited to small-scale supply chains. The efficient approaches have not been provided for scheduling of APSC in big data environment. This paper aims at proposing a novel trustworthy scheduling optimization approach for APSC by using big data. First, a new management architecture is provided for revealing underexploited values from big data to support the scheduling of APSC. Second, a novel scheduling model is presented to guarantees the trustworthiness of an agricultural product supply chain. At last, an evolutionary algorithm is developed to optimize the scheduling of large-scale supply chains with complex structure. Experiments are performed in 12 various scale test instances of APSC with at most 1 000 000 customer reviews and a 45 000-D search space. The results compiled demonstrate the effectiveness of the proposed approach.