The work aims to study the sustainable utilization of agricultural waste, so as to achieve the overall profit optimization of the supply chain while reducing the pollution to the environment. In the context of random demand, considering different incentives of production cooperatives to retailers, the optimal state of production cooperatives, retailers and demand markets was analyzed, and the corresponding multi-period supply chain network equilibrium model was established using variational inequalities. From the perspective of multi-cycle, the balanced benefits of the agricultural waste supply chain network was optimized, which could provide an effective solution for cooperatives and retailers to reach an equilibrium state for a long time in the future. It not only realizes the sustainable utilization value of multi-cycle agricultural waste, but also promotes the development of circular economy. At the same time, it also achieves the goals of balancing the supply chain network, optimizing the overall profit of the supply chain, and reducing environmental pollution.