BluWave-ai Edge provides IoT and SCADA data collection and pre-processing, AI inference, prediction and optimization.
BluWave-ai Center provides user interface and configuration provisioning and management, and AI model training.
The increased adoption of electric vehicles (EVs) in residential areas introduces challenges for distribution utilities who supply the increased energy demand to charge them. The utility needs to plan the infrastructure to manage the increased capacity and find non-wires alternatives to mitigate peak loads so it can avoid costly capital upgrades. BluWave-ai’s EV Everywhere solution eases the transition to high urban EV penetration.
The city of Summerside (in Prince Edward Island, Canada) enjoys a significant wind and solar infrastructure, but still had to import 57% of its energy supply from neighboring NB Power because weather conditions can reduce solar generation by up to 70%, and no wind means no power. At the same time, not having real-time insight into user loads meant Summerside Electric had to constantly over-provision capacity to ensure reliable supply. BluWave-ai’s predictive technology is yielding up to 50% improvement in energy scheduling accuracy over the utility system baseline.
BluWave-ai’s low-risk onboarding allowed us to run a set of AI-enabled tests over several months, in effect test-driving the platform in our own environment. Working shoulder-to-shoulder with BluWave-ai put us in the lead nationwide with a machine learning solution to refine operational efficiencies and offset carbon use.
Bob Ashley Chief Administrative Officer, Summerside Electric, Summerside, Prince Edward Island, Canada
As part of the drive to meet India’s renewable energy target of 450GW capacity by 2030, electricity regulatory commissions are introducing measures which encourage accurate scheduling and introducing a real-time market to improve access to renewable generation sources. For example, consumers, power generators and distribution companies (discoms) now face stricter deviation charges, which increase with the level of inaccuracy in power scheduling. Discoms like Tata Power can improve operating costs with more accurate scheduling of power import, to minimize deviation penalties, and by scheduling short-term purchases on the energy markets when pricing is favorable.
As governments around the world respond to the COVID-19 pandemic, the mitigation and suppression measures being put in place have caused a profound impact on electricity demand. How does an AI platform adapt to a situation completely without historical precedent? BluWave-ai's Senior Director of Technology, Dr. Mostafa Farrokhabadi, offers a timely analysis of energy demands in a large metropolitan area in India during the country's total lockdown in March-April, 2020.
COVID SHUTDOWNS CASE STUDY
North American Clean Energy profiled Summerside Electric in the article, "Trailblazing Island Utility Uses AI for Financial and Environmental Gains".
To help you evaluate and quantify the benefits of the BluWave-ai solution in your unique operation, we offer an opportunity assessment and model-building service as either a first phase of product deployment or a standalone service. Learn more about our deployment process.
Request a Demo
AI MODEL BUILDING AND GOING LIVE
BluWave-ai has built a suite of predictors for energy optimization including: load, wind, solar generation, energy price, peak demand which are deployed worldwide for its customers using BluWave-ai SaaS energy optimization products.
For electricity system load forecasting and dispatch, BluWave-ai’s predictor builds on 5 years of AI platform optimization, operating worldwide delivering over 500 000 real-time AI energy dispatches as of 2022. It has been trained on years of historical system demand data along with weather and other data feeds, providing superior forecast accuracy that will adapt in real-time to system changes to provide continued accuracy.
For the Ontario system, the load predictor has been specifically tuned and trained on publicly available system data, other data and weather feeds from all over the province to accurately predict the system load for the province of Ontario, Canada.