Tata Consultancy Services Limited

Monika Gajrani

Vinay Kulkarni

Souvik Barat

Prashant Kumar

Harshad Khadilkar

Hardik Meisheri

Vinita Baniwal

Solomon Pushparaj Manuelraj

Subramaniam Dhandapani

Sai Prasad Parmeswaran

This disclosure relates generally to the method and system for dynamically optimizing the operations of logistics management system. The existing methods for optimizing the operational processes in the sorting terminals are not dynamic as the sorting terminal operations are largely manual and experience driven. The proposed method and system describe an actor-based representation of simulatable digital twin of the sorting terminal that enables in-silico quantitative exploration of design space to help human experts arrive at the right decisions related to the logistics management system. The proposed method and system initially construct a high-fidelity simulatable digital twin of the sorting terminal, validate it, set it up with real data, and simulate various adaptation and design alternatives to understand their impacts on the key performance indicator values.

Method and system for dynamically optimizing the operations of logistics management system

Generally, in complex systems such as business organizations and supply chain networks, decisions making and control are challenging due to dynamic environment thereof. The embodiments herein provide method and system that uses reinforcement learning (RL) for exploring policies and deciding control actions, and actor-based modelling and simulation for performing accurate long-term rollouts of the policies, in order to optimize operation of the complex systems. In an embodiment, a method for actor based simulation of complex system includes modeling, actors of the complex system using an actor abstraction, where actors includes RL agents embodied in each subsystem of the complex system, and executes micro-level interactions amongst the subsystems. An emergent macro-behavior of the complex system is simulated by the using the RL agents based on the micro-level interactions. Optimal decisions pertaining to actions of the RL agents are learnt based on the emergent macro-behavior of the complex subsystem.

System and method for actor based simulation of complex system using reinforcement learning

Growing community of inventors

Pune, India

Monika Gajrani