Harsh Bakulchandra Patel

Title: Harsh Bakulchandra Patel and Water Network Control Innovation.

Introduction

Harsh Bakulchandra Patel is an inventor based in Etobicoke, Canada. His work includes an invention applying hybrid reinforcement learning to control a water distribution network. Patel is associated with Autodesk, Inc.

Latest Patents

Patel is credited with 1 patent: “Hybrid reinforcement learning (RL) to control a water distribution network.” The patent describes a method and system that use historical operating states, residential water demand, tank levels, and energy tariffs to guide network control. The system evaluates rewards that account for tank-level constraints, energy costs, and the number of pump toggles. A query-based model identifies control points, while a reinforcement-learning agent uses prior states and rewards to determine pump-speed setpoints. It also selects time slots and generates hybrid setpoints intended to maintain tank levels, reduce energy costs, and comply with toggle-count limits.

Career Highlights

Patel’s listed professional affiliation is Autodesk, Inc. His patent focuses on using data-driven control and reinforcement learning to address operational considerations in water distribution systems.

Collaborations

The provided information identifies Yuan Zhou and Shu Wang as Patel’s coworkers. Their specific contributions to the patent or related work are not specified.

Conclusion

Harsh Bakulchandra Patel’s patent presents a reinforcement-learning approach to coordinating pump operation, tank levels, energy costs, and control schedules in water distribution networks.