RLCore Unveils RLTune: An Adaptive Optimization Platform for Water and Wastewater Infrastructure at ACE26

Continuous-learning optimization software helps utilities reduce chemical and energy consumption by 15–25% while improving operational efficiency and resilience 

WASHINGTON--(BUSINESS WIRE)--RLCore today announced RLTune, a real-time continuous optimization platform designed to revolutionize how water and wastewater facilities operate in dynamic, nonlinear environments. Unveiled at the American Water Works Association’s ACE26 conference, RLTune introduces a new level of control: a continual learning intelligence layer that works alongside existing controls and dynamically optimizes plant performance, leading to significant efficiency gains, cost savings and operational resilience.

Industrial systems operate in dynamic environments where conditions are constantly changing — from daily fluctuations in energy prices and chemical costs, to influent variability, equipment wear and staffing constraints. Yet, most control approaches still rely on fixed gains or models that don't learn from their environments. This forces operators to manually manage any gaps — leading to operational inefficiencies, lost optimization opportunities and increased burden on plant operators. Analysts estimate that over $1 trillion is lost annually to controllable inefficiencies across all industrial processes.

RLTune sits on a plant’s existing control stack and applies constrained reinforcement learning to continuously improve control decisions under real operating conditions. RLTune learns from live plant environments and continually optimizes industrial processes in real-time to achieve operator defined, plant-level KPIs. Live deployments of RLTune have led to 15-25% improvements in chemical and energy consumption, 95% increase in response time, >90% process efficiency and significant improvements in operational responsiveness & stability.

"Working with RLCore has made a positive difference in how we run Drayton Valley operation,” said Shelley Terry, GM of Infrastructure, Drayton Valley. “We’re seeing better performance and fewer surprises in the control room. Chemical use is down and water conservation is up. On top of that, their automation frees up operator time, letting them focus on higher-value work. For me, it comes down to this: RLCore does what they said they would do, and that matters."

Frank Mannarino, Senior Vice President, EPCOR Water Services agrees: “RL Core’s work directly contributed to the optimization of our operations and cost savings at our wastewater treatment plant. Their approach showed how advanced control and AI can be introduced in a way that is aligned with how utilities actually operate.”

Key Capabilities Include:

• Continuous Learning and Adaptation: Automatically adjusts to seasonal variability, influent changes, equipment wear, and process disturbances without requiring manual retuning cycles.
• No Digital Twins or Complex Physics Models Required: Learns directly from real plant environments, accelerating deployment timelines and reducing implementation complexity using a constrained, safe-by-design form of reinforcement learning.
• Guardrailed Optimization: Allows operators to set guardrails and define incremental autonomy as trust increases. Operators retain explicit override authority at all times.
• Data Logging: Logs live operational data for visibility and quantifies variability and operating patterns with no impact on plant operations.
• Vendor-Agnostic: Integrates with plant via OPC-UA connectivity and is compatible with SCADA, DCS, PLCs, historians, and IoT gateways.
• On-premise and Cyber-Secure: Data remains on-site and never leaves the plant without your explicit authorization.

“Industrial control systems have remained largely static for decades despite operating in highly dynamic environments,” said Ganesh Rao, CEO and Co-Founder of RLCore. “RLTune changes that paradigm. It doesn’t just monitor or recommend. It continuously learns and acts, enabling plants to improve performance in real time without requiring costly overhauls or complex modeling efforts.”

“This is a fundamental shift in how industrial optimization can be approached,” said Martha White, CTO and Co-Founder of RLCore. “Advances in reinforcement learning now allow systems to continuously learn and adapt from real-world operational environments in ways that were not previously practical.”

RLCore refers to this emerging category as Real-Time Autonomous Optimization (RTAO) — a new approach to industrial optimization where systems continuously learn and improve directly within live operating environments.

To learn more about RLTune, visit RLCore at the Innovation Hub at booth 119 for live demos and expert consultations during the American Water Works Association’s (ACE26) conference June 21-24, 2026 in Washington, D.C.

The learn more about RLTune watch here: https://rlcore.ai/product

To learn more about RLCore watch here: https://rlcore.ai/

About RLCore

RLCore is building the adaptive optimization layer for industrial infrastructure. Founded in October 2024, RLCore is comprised of internationally recognized experts in reinforcement learning and business leaders with extensive experience scaling product and technology organizations. Its flagship platform, RLTune, continuously learns from live operating environments and optimizes performance on top of existing control systems. Deployed across municipal, wastewater and industrial facilities, RLTune helps operators build resilience, reduce chemical / energy consumption, improve process stability, and adapt to changing operating conditions in real time. Unlike traditional optimization approaches, RLTune requires no digital twins, complex physics models, or major infrastructure changes. Operators remain in control through configurable guardrails, full transparency, and instant override capabilities, while on-premise deployment ensures plant data remains securely on-site. RLCore's vision is to enable industrial systems that continuously learn, adapt, and improve outcomes in real time.