Lenovo Schedules Laptop Manufacturing Using Deep Reinforcement Learning

Abstract

Lenovo Research teamed with members of the factory operations group at Lenovo’s largest laptop manufacturing facility, LCFC, to replace a manual production scheduling system with a decision-making platform built on a deep reinforcement learning architecture. The system schedules production orders at all LCFC’s 43 assembly manufacturing lines, balancing the relative priorities of production volume, changeover cost, and order fulfillment. The multiobjective optimization scheduling problem is solved using a deep reinforcement learning model. The approach combines high computing efficiency with a novel masking mechanism that enforces operational constraints to ensure that the machine-learning model does not waste time exploring infeasible solutions. The use of the new model transformed the production management process enabling a 20% reduction in the backlog of production orders and a 23% improvement in the fulfillment rate. It also reduced the entire scheduling process from six hours to 30 minutes while it retained multiobjective flexibility to allow LCFC to adjust quickly to changing objectives. The work led to increased revenue of US $1.91 billion in 2019 and US $2.69 billion in 2020 for LCFC. The methodology can be applied to other scenarios in the industry.

A Review on Reinforcement Learning in Production Scheduling: An Inferential Perspective

“…These algorithms, ranked from most to least frequently employed, include Qlearning, temporal difference TD(λ) algorithm, SARSA, ARL, informed Q-learning, dual Q-learning, approximate Q-learning, gradient descent TD(λ) algorithm, revenue sharing, Q-III learning, relational RL, relaxed SMART, and TD(λ)-learning. In the field of DRL, many value-based approaches have been employed, such as DQN (Deep Q-Learning Networks), loosely-coupled DRL, multiclass DQN, and the Q-network algorithm [48][49][50][51][52][53][54][55][56][57][58].…”