Energy Digest

Daily Summaries & Key Takeaways of Power & Energy Updates
Powered by Llama 3.2
Last Updated: November 18, 2026 at 08:02 AM
1

Why AI data centers need storage beyond conventional backup power

Summary

AI data centers require storage systems that can handle rapid load changes, high-density computing, and millisecond-scale intervention, making a single battery architecture inefficient. Advanced storage systems, such as EVE Energy's AIDC offering, are designed to address these requirements, with features like high-power storage, frequency regulation, and rapid discharge rates. These systems are crucial for managing load changes, supporting renewable energy integration, and ensuring reliable power distribution.
Read Full Article →
2

Taiwan introduces bidding framework for storage deployment at existing PV plants

Summary

Taiwan's Ministry of Economic Affairs has introduced a regulatory framework to promote the integration of battery energy storage systems with existing solar photovoltaic installations, with a focus on grid stability, renewable energy optimization, and a more flexible electricity system. The framework establishes a competitive bidding mechanism for eligible solar power facilities to incorporate battery storage, with a minimum energy capacity requirement of 2.61 MWh for every MW of rated storage power. Successful participants will be required to complete battery installation and grid connection within 15 months.
Read Full Article →
4

ADB supports 1 GW solar, storage pipeline in Bangladesh

Summary

The Asian Development Bank (ADB) is expanding its support for solar and battery energy storage projects in Bangladesh, with a three-phase programme covering more than 1 GW of planned capacity, expected to mobilise over $1 billion in private sector investment. The bank will work with Invest Bangladesh and the Bangladesh Power Development Board to assess the suitability of government-owned land for the projects. The programme aims to support Bangladesh's target of generating at least 30% of its electricity from renewable sources by 2040.
Read Full Article →
5

EU reaches provisional deal to accelerate renewable energy permitting

Summary

The European Union has reached a provisional agreement on legislation aimed at streamlining permitting procedures for renewable energy projects and energy infrastructure across the EU, which aims to remove administrative barriers, shorten permitting timelines, and simplify authorization procedures. The agreement requires endorsement by the Council and European Parliament and will be formally adopted after legal review, with EU member states expected to transpose the directive into national law within 18 months. The rules prioritize the roll-out of renewable energy and electricity grids, allowing member states to prioritize these projects if they align with public interest.
Read Full Article →
6

France unveils bidding terms for 500 MW technology-neutral renewables tender

Summary

France's energy regulator has published its opinion on the first round of the PPE3 Neutre technology-neutral renewables tender, which will allocate 500 MW of capacity across solar PV, onshore wind, and hydropower projects. The tender has been criticized for its limited capacity allocation, with the French renewable energy association SER calling for dedicated PV tenders. The new tender framework introduces an unweighted market reference price, which will account for 95% of the evaluation score and intensify competition among bidders.
Read Full Article →
7

Austrian company develops 1.2 kW Stirling-based heat and power system to complement solar PV in winter

Summary

Austrian company Frauscher Motors has developed a biomass-based combined heat and power system that converts heat from a wood-pellet boiler into electricity using a compact Stirling generator, with an efficiency of 28.2%. The system can generate 1.5 MWh of electricity per heating season, with a long-term maintenance-free operating time of 10,000 hours. The system has been operating a demonstration system since March 2026 to evaluate its performance.
Read Full Article →
8

Poland pushes for cybersecurity requirements for renewables grid connections

Summary

Poland's Ministry of Energy has published recommendations for grid operators to incorporate cybersecurity requirements into their rules and agreements with renewable energy producers and energy storage operators. The proposed measures include using supported hardware and software, secure network configurations, and separating operational technology systems from external networks. The goal is to strengthen the security of solar and wind farms and battery energy storage systems connected to Poland's power system.
Read Full Article →
9

New net-zero community will become Michigan’s first virtual power plant

Summary

A new net-zero community in Michigan, Veridian at County Farm, is set to become the state's first virtual power plant, with homes generating and sharing energy among each other to meet their energy needs. The community is powered entirely by solar energy and features homes that make about as much energy as they consume. The development aims to become a model for sustainable living and energy production.
Read Full Article →
10

REPORT: U.S. Exceeds 200 GWh of Energy Storage Capacity Installed to Date

Summary

The U.S. energy storage industry has installed a total of 200 GWh of capacity, exceeding the 200 GWh mark. The industry saw 14.3 GWh of new capacity installed in Q3, bringing the total installed capacity to date. The growth in energy storage is helping stabilize electricity prices and strengthen grid reliability.
Read Full Article →

Technical Papers & Research

AI-curated academic research for power system engineers

Curated by Llama 3.2
arXiv eess.SY + cs.LG View all → Showing papers with relevance ≥ 0.70

Grid Operations & Resilience 2 papers

Safely Mitigating Grid Imbalance: A Hybrid Distributional Wide-Margin Recourse Approach
0.80 Relevance

The MADWMPG framework proposes a dual-policy hybrid imitation and safe reinforcement learning method to safely mitigate grid imbalance in active distribution networks. The framework uses a wide-margin constraint barrier recourse module to learn proactively suppress exploratory violations, addressing operational volatility with a novel adaptation of noncrossing quantile regression distributional critics. The framework was trained and tested on a modified multiphase IEEE 123-bus test feeder, demonstrating superiority over conventional reinforcement learning and SRL methods.

Why This Matters
This paper is highly relevant to power system engineers as it proposes a novel approach to safely mitigating grid imbalance, a critical issue in modern power grids, particularly with increasing renewable energy integration. The proposed framework can help grid operators and planners develop more effective strategies for managing grid volatility and ensuring grid stability, making it a valuable contribution to the field of grid operations and resilience.
Abstract PDF
AI Agents Executing an RMS and EMT Ride-Through Workflow on a 2,000-Bus Synthetic Texas Grid: A Case Study with Open-Source Tools
0.80 Relevance

AI agents executed a predefined ride-through workflow on a synthetic Texas grid with open-source tools, assessing a 133 MW battery's performance. The agents failed to meet ride-through criteria due to the battery absorbing reactive power during sags and the data-center load returning late, missing ERCOT's load-return requirement. The agents logged errors, and their performance was compared to results from the same machines, showing a significant difference in RMS and EMT values.

Why This Matters
This paper matters for power industry professionals as it explores the effectiveness of AI agents in executing ride-through workflows on a synthetic grid, providing insights into grid resilience and the impact of energy storage systems like batteries on grid stability. The findings can inform grid operators and planners in designing and optimizing grid systems for better performance under various scenarios.
Abstract PDF

Energy Storage & Markets 3 papers

Capacity Credit of Data-Centre Flexibility: The Role of Workload Scheduling and Usable Battery Energy
0.90 Relevance

Data centres can make different contributions to supply adequacy despite reducing grid demand by the same amount, depending on workload scheduling and usable battery energy. Longer task deadlines increase capacity credit by allowing operators to defer and recover work, while fixed evening commitments and protected backup reserves have limited capacity credit. Assessing recovery deadlines and dispatchable energy is crucial to accurately determining capacity credit.

Why This Matters
This paper's findings on the capacity credit of data-center flexibility through workload scheduling and usable battery energy are directly relevant to the power industry, particularly in the context of capacity markets and utility planning, where the ability to provide dispatchable energy and recover losses is crucial for ensuring supply adequacy and meeting renewable penetration targets. The insights from this paper can inform the development of more effective energy storage and scheduling strategies in the grid.
Abstract PDF
Transmission Expansion and Energy Storage Planning under Great Britain's Uncertain Energy Transition Pathways
0.90 Relevance

Long-term power system planning in Great Britain must account for uncertainty in electricity demand and generation, and coordinated transmission and energy storage planning can significantly reduce costs and improve outcomes. The study's framework integrates multiple energy transition pathways and captures the characteristics of transmission and storage investment over time, finding substantial benefits from joint planning. Coordinated investment can reduce transmission capacity needs by 2%, cumulative load shedding by 97%, and total system cost by 36%.

Why This Matters
This paper is highly relevant for power industry professionals as it addresses a critical aspect of energy system planning, specifically the coordination of transmission expansion and energy storage investment. The findings have practical implications for utilities and grid operators, as they can inform investment decisions and optimize system resilience, particularly in the context of the UK's uncertain energy transition pathways.
Abstract PDF
Grid-Responsive Pricing of Dynamic Wireless Charging with Coupled Residential Demand
0.90 Relevance

Researchers developed a coupled model to optimize dynamic wireless charging tolls and prices, accounting for displaced residential charging and network losses, to reduce grid loading. The proposed model resulted in lower grid loading violations and lower revenue reductions compared to a conventional model. Peak-aware pricing further reduced daily peak loading by 3.7%.

Why This Matters
This paper is relevant for power system engineers as it presents a novel approach to pricing dynamic wireless charging, which has implications for energy market analysis and utility planning, particularly in the context of renewable integration and peak demand management. The authors' work can inform the development of pricing strategies that balance the needs of electric vehicle charging, grid stability, and network resilience.
Abstract PDF

Other 5 papers

Deep Reinforcement Learning for Heat Pump and Underfloor Heating Control: An End-to-End Case Study
0.80 Relevance

Deep Reinforcement Learning (DRL) offers a data-driven control approach for efficiently managing underfloor heating (UFH) systems and heat pumps (HPs), optimizing energy consumption and thermal comfort. A DRL-based controller was developed and deployed in a real residential building, successfully maintaining indoor temperatures within comfort limits while dynamically adjusting HP supply temperature and UFH valve positions. The findings demonstrate the feasibility of deploying DRL controllers in occupied buildings.

Why This Matters
This paper matters for power industry professionals as it presents a novel approach to optimizing building heating systems, which can be directly applied to grid operations and resilience, particularly in the context of integrating renewable energy sources and managing demand response. The findings on the deployment of DRL controllers in occupied buildings can inform strategies for managing thermal comfort and energy efficiency in smart grids.
Abstract PDF
MARS: Feature-guided physics-informed deep learning for real-time battery health and lifetime prediction
0.80 Relevance

MARS proposes a feature-guided physics-informed deep learning framework for real-time battery health and lifetime prediction, achieving improved state-of-health (SOH) accuracy with mean absolute error/root mean square error values of 0.72%/0.92% and 0.63%/0.80% on NASA and CALCE benchmarks. The framework couples a dual-branch temporal encoder with an adaptive Kalman filter, providing calibrated prediction intervals for SOH estimation and conditional RUL prediction. The system's conditional RUL prediction intervals achieve high coverage probabilities, with 100.00% and 99.24% coverage on NASA and CALCE, respectively.

Why This Matters
This paper matters for power industry professionals as it proposes a method for accurate and robust estimation of battery state-of-health and remaining useful life, which is crucial for safe and cost-effective operation of electrified transportation systems and grid resilience, particularly in the context of renewable integration and grid operations. The results can inform grid operators and utility planners in optimizing battery management and developing strategies for integrating renewable energy sources.
Abstract PDF
Data-driven model reduction: An identification perspective using Generalized Bases of Orthonormal Functions
0.80 Relevance

A data-driven model order reduction approach is proposed using Generalized Bases of Orthonormal Transfer Functions to identify a revised equation error formulation. The model is parameterized using GBOFs, and the frequency-domain fit is adjusted by selecting the basis poles, which are guided by a fit indicator. This approach aims to reduce the order of a system while maintaining an accurate representation.

Why This Matters
This paper's data-driven model reduction approach using Generalized Bases of Orthonormal Transfer Functions has practical significance for power system engineers, enabling more efficient and accurate analysis of power system dynamics in grid operations and resilience applications, such as optimizing power flow and stability in high-speed grid environments.
Abstract PDF
Benchmarking a Grid Foundation Model for AC Optimal Power Flow: Feasibility and Warm-Start Results on Synthetic Texas and South Carolina Grids
0.80 Relevance

Predictions from the GridSFM-Open model were found to be feasible AC-OPF operating points in some cases, but not necessarily feasible, with large gaps in others. Even with fine-tuning, the model's predictions were only marginally useful as initial values for a nonlinear solver, with some grids requiring significant speedups to converge. The model's performance varied between grids, with one grid showing faster convergence when seeded with fine-tuned predictions.

Why This Matters
This paper is relevant to power system engineers as it evaluates the feasibility and warm-start results of a learning-based surrogate model for AC optimal power flow, which can be applied to improve the efficiency and resilience of grid operations, particularly in scenarios where nonlinear solvers may struggle to converge. The findings can inform the development of more robust and efficient grid management strategies for utilities and grid operators.
Abstract PDF
Solver-Free and Cost-Aware Online Scheduling of AI Data Center Tasks
0.80 Relevance

The proposed online optimization rule assigns tasks a start period to optimize energy cost, shifting flexible tasks to low-price periods while keeping high-priority tasks on schedule. Simulations show that the rule keeps GPU and CPU use within capacity while scheduling tasks at low cost, achieving a lower cost than a multi-timescale optimization benchmark. The rule also reduces computation time by eliminating the need for a solver.

Why This Matters
This paper's focus on optimizing energy cost and scheduling tasks in AI data centers is highly relevant to power industry professionals, particularly those involved in utility planning and grid operations, as it addresses a pressing need to balance the intermittent nature of renewable energy sources with the growing demand for computing resources. The proposed solver-free online optimization rule could be applied to optimize energy costs in data centers with high-priority tasks, which is essential for grid operators and energy market analysts.
Abstract PDF

Was this digest helpful?