Opticaster is Tesla’s intelligent software designed to maximize economic benefits and sustainability objectives for distributed energy resources. As the fundamental machine learning and optimisation engine for Tesla energy software, it forecasts and optimises energy in real-time. Facility managers, business owners and renewable developers use Opticaster to reduce energy spend, increase renewable energy consumption and deliver clean power to the grid during times of need. Opticaster is part of Autonomous Control, Tesla's suite of optimisation software solutions.
Opticaster has accumulated over a hundred million hours of operational experience, delivering tens of millions of dollars in value from opex savings and grid service revenue to thousands of Tesla customers globally.
Machine Learning and Optimisation
Tesla’s team of experienced machine learning engineers, optimisation engineers and grid service experts have created a library of sophisticated algorithms that drive the complex optimal battery dispatch behaviour for both Opticaster and Autobidder products.
Algorithms are based on numerous mathematical techniques including classical statistics, machine learning and numerical optimisation. The library includes the functionality to perform:
Opticaster strategies are continuously benchmarked and upgraded based on the latest improvements and updates to energy consumption patterns. Opticaster’s adaptive intelligent control empowers customers to reach their business goals with zero supervision required over the energy storage system.
Automated Utility Savings
Opticaster puts managing energy spend on autopilot by autonomously shifting energy usage to less expensive times and reducing peak demand charges. It intelligently navigates complicated rate structures across many utility territories and energy markets. Additionally, Opticaster ensures that energy consumers adhere to operational constraints for capturing energy storage incentive value.
Current supported rate structures include but are not limited to:
Daily, monthly and annual demand charges
Time-of-use energy and demand rates
Real-time energy rates
Grid-level demand charges
Grid Service Participation
In addition to optimising site-level energy spend, Opticaster enables customers to use their energy assets to provide valuable services to the grid. Opticaster solves complex use cases that combine multiple revenue streams while also respecting site export limits, throughput and backup constraints.
Once a site is enrolled in an aggregation or grid service program, Opticaster ingests special price signals sent to site over-the-air. For example, a demand response dispatch may be called 24 hours ahead of time. The dispatch signal is sent to the local site controller where Opticaster will ingest it and adjust the day’s optimal dispatch schedule to generate the most value through co-optimised dispatch. Opticaster is fundamental to Tesla-controlled Virtual Power Plant (VPP) operations in Massachusetts and South Australia.
Every Tesla site comes Opticaster-enabled across Powerwall, Powerpack and Megapack product lines. Opticaster enables highly efficient edge computing, which ensures high availability and fast response of autonomous control regardless of cellular connectivity. Performance improvements and customised price schedules can be seamlessly pushed down to site from Tesla’s secure cloud infrastructure if necessary. Through its coordinated local and server-side architecture, Opticaster offers a very flexible, reliable solution in an ever-changing energy landscape.