# GridStor Transforms Energy Price Forecasting

> How GridStor, a leader in energy storage, transformed its electricity price forecasting to optimize storage and sales with Nixtla's TimeGPT, reducing operational costs by 50% and enhancing strategic decision-making

Canonical HTML: https://www.nixtla.io/success-stories/gridstor

## Customer

- Name: GridStor
- Industry: Energy and Utilities

Discover how GridStor leveraged Nixtla's TimeGPT to generate precise, long-term electricity price forecasts, reduce AWS costs by 50%, and drive smarter operational decisions

## Key results

- **50% Cost Reduction:** TimeGPT cut GridStor's operational expenses by reducing reliance on costly AWS instances
- **1 sec Forecast Workflow:** Integrated API delivers forecasts in seconds, significantly accelerating decision-making
- **+15% Accuracy Improvement:** Enhanced long-term and hourly forecasts provided GridStor with reliable data for strategic planning

## Overview

GridStor, headquartered in Portland, Oregon, is a rapidly growing developer, owner, and operator of grid-scale battery energy storage systems (BESS). The company focuses on integrating renewable energy sources to enhance grid reliability and efficiency.

Backed by Goldman Sachs Asset Management, GridStor is well-capitalized to pursue its mission of building a more resilient and sustainable energy infrastructure across the United States. In the past year, it expanded aggressively into ERCOT and CAISO regions, including a new 150 MW/300 MWh facility in Texas
To succeed in increasingly volatile electricity markets, GridStor needed a forecasting solution that could keep pace with changing dynamics. With Nixtla, GridStor transformed its ability to make financially sound, data-backed decisions in real time

## The Critical Nature of Energy Price Forecasting

In today's renewable-driven power markets, electricity prices are more volatile than ever. With daily price changes up to 20× greater than stock market fluctuations, and intraday price spikes exceeding 1000% volatility, accurately forecasting these dynamics is mission-critical for energy storage operators like GridStor
- Need to decide when to charge (when power is cheap) and when to discharge (when prices spike)
- Even a 1% improvement in forecast accuracy can save millions in operational costs
- Traditional forecasting models struggled with extreme price volatility driven by renewable generation

## TimeGPT: Transforming Forecasting Precision

GridStor partnered with Nixtla to leverage TimeGPT, an AI-driven time series forecasting engine. By integrating vast supply-demand data from ERCOT markets and renewable output into TimeGPT's models, GridStor gained the ability to predict price fluctuations with far greater precision and horizon than traditional methods
- Significantly improved accuracy for month-ahead hourly forecasts, previously a major challenge
- Enhanced visibility into future prices allows optimal battery charging/discharging scheduling
- Enabled long-term planning with quarterly and yearly price trends for new project development

## Business Outcomes

Studies show that advanced forecasting and optimization can increase battery revenue by 10–20%
- **Operational Efficiency**
  - 50% reduction in cloud computing costs
  - Streamlined forecasting with automated AI processes
- **Strategic Forecasting**
  - Rapid 1-second forecast generation
  - Significantly improved month-ahead hourly forecasts
- **Improved Long-Term Planning**
  - Data-driven decisions for new project development
  - Better visibility for long-term business planning

## Testimonial

> TimeGPT's onboarding is remarkably smooth and fast. Within seconds, we have actionable predictions ready to go. This is extremely impactful for our business. TimeGPT has been a game-changer for our budgeting process, operations, and board-level reporting. The speed, accuracy, and reliability have made it an essential part of our mission-critical workflows

Brett Rudder, Senior Manager of Market Analytics, GridStor