Real-time Analytics
i GRID LAB needed to collect and analyze renewable-energy, demand, battery, and EV data quickly enough to predict surplus power and automate device control, while proving the concept fast in a rapidly changing energy market.
Reported impact
i GRID LAB built the proof of concept in 6 months, published first results 1 month later, expanded to around 500 solar facilities and about 100,000 households, and created a commercial platform to support regional green power circulation and future GX cities.
i GRID LAB built the R.E.A.L. New Energy Platform on AWS to predict and control surplus renewable power using IoT data and AI. Distributed Energy Resource data—including solar generation, demand, storage-battery status, and EV charging and discharging—is collected from edge devices with AWS IoT Greengrass and stored in the cloud for high-speed time-series processing with Amazon Timestream. AI functions migrated onto Amazon SageMaker then combine that operational data with external inputs such as electricity market prices to forecast excess solar generation, determine optimal EV charging and discharging timing, and create automated control scenarios. The result is a serverless-oriented platform that can move from proof of concept to commercialization quickly while supporting regional power-circulation use cases, logistics decarbonization, and broader green-transformation programs.
Solar, demand, battery, and EV telemetry is collected from edge devices through AWS IoT Greengrass into the cloud, processed as time-series data in Amazon Timestream, combined with external information such as electricity market prices in SageMaker-based AI models, and then used to generate automatic control scenarios for distributed energy resources.
A platform for the proof of concept was built in just 6 months from the start of the project.
Additionally, they migrated AI functions ... to Amazon SageMaker.
The R.E.A.L. New Energy Platform ... collects information on things such as solar power generation volume and power, demand, storage batteries, and EV charging/discharging status, and the data is stored in the cloud.
The company adopted AWS IoT Greengrass for the data collection from edge devices and Amazon Timestream for high-speed processing of large amounts of time series data.
they collected and analyzed electricity usage and other data from approximately 100,000 households.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The company page states "従業員数 153名（2026年6月末現在）", which maps to SMB under the enrichment policy.
Related
AWS Sample Feb 17, 2025 Noodoe Recognizing the potential of generative AI, Noodoe aimed to enhance its product line by integrating AI-powered capabilities. Roman Kleinerman, vice president of products at Noodoe, explains, “We envisioned that within a… According to a Harvard Business School study , charging stations in the US typically achieve 78 percent… Amazon Bedrock · Amazon CloudWatch · Amazon EC2 
NVIDIA Sample Sep 30, 2026 EPRI EPRI needed to run advanced AI for sensitive utility documents and weather-planning workflows locally, because energy-sector research data could not leave controlled environments and shared compute delays limited how… 150 tokens/sec aggregate across 10 concurrent Power Chat users DGX Spark · Dell Pro Max with GB10 · NVIDIA CBottle 
Accenture Sample Aug 13, 2026 Duke Energy Duke Energy needed to go beyond current US EPA regulations and replace slow physical inspection-based leak surveys with a rigorous end-to-end way to detect, monitor, and remediate methane emissions across its natural… net-zero methane goals for 2030 Azure-based cloud platform · analytics · artificial intelligence 