A common problem affecting neural network (NN) approximations of model predictive control (MPC) policies is the lack of analytical tools to assess the stability of the closed-loop system under the action of the NN-based controller. We present a general procedure to quantify the performance of such a controller, or to design minimum complexity NNs with rectified linear units (ReLUs) that preserve the desirable properties of a given MPC scheme. By quantifying the approximation error between NN-based and MPC-based state-to-input mappings, we first establish suitable conditions involving two key quantities, the worst-case error and the Lipschitz constant, guaranteeing the stability of the closed-loop system. We then develop an offline, mixed-integer optimization-based method to compute those quantities exactly. Together these techniques provide conditions sufficient to certify the stability and performance of a ReLU-based approximation of an MPC control law.
翻译:影响模型预测控制(MPC)政策神经网络(NN)近似值的一个常见问题是缺乏分析工具来评估NN控制器操作下闭环系统的稳定性,我们提出了一个一般程序来量化这种控制器的性能,或设计最低复杂性的NNP,使用经纠正的线性单位(ReLUs)来维护特定MPC计划的适当性能。通过量化基于NN和基于MPC的州对投入绘图之间的近似误差,我们首先建立了两个关键数量的合适条件,即最坏的错误和利普西茨常数,保证闭环系统的稳定。然后我们开发了一种离线、混合整数优化法,准确计算这些数量。这些技术共同提供了足以证明基于RELU的近似值的MPC控制法的稳定性和性能的条件。