Ant Digital Deploys AI Agents for Power Trading and New Energy Operations

Ant Digital unveiled the "Power Trading Agent" and "New Energy Operations Agent" at the 2026 Shanghai SNEC Photovoltaic Exhibition on June 3. Built on its proprietary intelligent agent platform, DTClaw, these tools enable enterprises to deploy AI staff with industry-grade expertise at scale. Ant Digital has already executed scenario implementations alongside Linyang Zhivei and Gintech New Energy, marking the company’s first application of self-developed intelligent agents within the energy sector.

High-frequency trading markets have long been constrained by manual decision-making in new energy power stations. Leveraging the DTClaw platform and the EnergyTS3.0 time series large model, Ant Digital partnered with Linyang Zhivei to launch the inaugural power trading agent. By integrating real-time operational data from 30 GW of power stations, the system establishes a complete workflow encompassing prediction, strategy generation, automated bidding, risk control, and review. This enables 24/7 autonomous trading, cutting labor costs by over 60% and accelerating analysis and strategy generation by more than 20 times.

Simultaneously, Ant Digital collaborated with Gintech New Energy to deploy the first photovoltaic operations agent. AI is embedded throughout the maintenance workflow, linking monitoring, alerts, inspections, diagnosis, work orders, archiving, and prediction. In Gintech’s operations, this integration reduces key anomaly identification and feedback time to under one minute, boosts end-to-end inspection and defect resolution efficiency by 50%-70%, and cuts fault location and decision-making time by 30%-60%, significantly enhancing maintenance speed and accuracy.

Earlier this year, Ant Digital launched DTClaw, a professional intelligent agent platform for enterprise scenarios featuring over 100 core expert-level Skills. The "Power Trading Agent" and "New Energy Operations Agent" have been deeply optimized for complex energy business contexts, creating a versatile team of "AI employees" ready for immediate deployment. Furthermore, driven by the iteration of the self-developed EnergyTS3.0 energy time series large model, the products now lead the industry in four key areas: photovoltaic power generation forecasting, wind power generation forecasting, electricity load forecasting, and day-ahead electricity price forecasting. In several provinces, peak power forecasting accuracy has exceeded 94%.

Industry observers note that these implementations in power trading and operations signify Ant Digital’s expanding AI footprint in the energy sector. As a B2B technology firm, Ant Digital focuses on cutting-edge AI to accelerate global SME adoption of AI technologies. Its LingDT series models, DTMaaS platform, DTClaw intelligent agents, and AI security product ZOLOZ have achieved widespread application across multiple industries. In finance, Ant Digital has partnered with institutions to launch over 100 scenario applications. In energy, the company has already deployed solutions for energy asset management, carbon certificate traceability, and power trading.