cs.AIAug 15, 2026

Large Language Model Assisted Operational Monitoring for Battery Energy Storage System Integrated Power Distribution Networks

Authors: Azmeer Akhtar, Md Fazley Rafy, Anurag K. Srivastava

Organizations: Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV 26505, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Battery energy storage systems (BESS) are increasingly used in distribution networks for voltage regulation and demand response, which increases the volume and complexity of operational telemetry available to grid operators. This paper presents an AI-enabled monitoring framework that connects a large language model (LLM) interface with a structured telemetry database for BESS-integrated distribution system analysis. Operator questions are submitted in natural language and translated into validated SQL queries using predefined database schema information and approved KPI views. Retrieved measurements, including bus voltages, state of charge, active power, and reactive power, are evaluated against engineering constraints for voltage limits, BESS operation, and demand response tracking. The framework is validated using hardware-in-the-loop co-simulation data from a BESS-equipped distribution feeder operating under reactive power-based voltage control and price-driven demand response. Case studies show that the framework generates valid database queries, identifies repeated voltage violations, detects reactive power overshoot, and evaluates active-power tracking performance. The results show that LLM-assisted monitoring can connect structured grid telemetry with automated engineering assessment for BESS operation analysis.

Figures & tables

Fig. 1: LLM-assisted monitoring framework for BESS-integrated distribution system analysis. Operator questions are translated into validated SQL queries, evaluated against engineering constraints, and returned as text, dashboard, or plot/table outputs using operating data from the prior HIL testbed.
Operational MetricEvaluation CriteriaAssessment Output
Voltage RegulationVmin⁡≤Vbus≤Vmax⁡V_{\min}\leq V_{bus}\leq V_{\max} (e.g., 0.95 to 1.05 p.u.)Violation count, vulnerable node ranking
Active-Power Tracking∣Pmeas−Pref∣≤ϵP|P_{meas}-P_{ref}|\leq\epsilon_{P}Tracking error, DR performance status
Reactive-Power Response∣Qmeas−Qref∣≤ϵQ|Q_{meas}-Q_{ref}|\leq\epsilon_{Q} Check Q-overshootReactive tracking status, overshoot flag
Battery Energy StateSOCmin⁡≤SOC≤SOCmax⁡SOC_{\min}\leq SOC\leq SOC_{\max}Available energy headroom, limit compliance
Telemetry ConfidenceLatency ≤τmax⁡\leq\tau_{\max} Cyber-Anomaly Flag =0=0Data-confidence qualifier
TABLE I: Operational Constraint Framework for BESS Monitoring
SQL Column NameData TypeDescription
Metadata and Spatiotemporal Identifiers
tsTimestampTime index for windowed SQL queries.
run_idStringExperimental scenario identifier.
node_idStringFeeder node for localized tracking.
device_idStringBESS or inverter endpoint identifier.
control_modeCategoricalE.g., Volt-VAR, Demand Response.
TABLE II: PostgreSQL Schema Features for LLM Telemetry Queries
MetricDefinitionResult
SQL validityGenerated query is syntactically valid PostgreSQL.20/20
Approved-view complianceQuery uses only approved KPI views and schema fields.20/20
Execution successValid query executes without database error.20/20
Semantic correctnessQuery retrieves the intended KPI, node, time window, or aggregation.19/20
Invalid-query rejectionUnsafe or unsupported prompts are rejected by the validator.7/10
Hallucinated field/view rateQuery references a non-existing field or unapproved view.30%
TABLE III: Batch-Level Validation of LLM-to-SQL Query Generation
TaskManual SQL/dashboard workflowProposed framework
Query formulationOperator writes SQL or selects filtersNatural-language query converted to SQL
Schema useRequires view and field knowledgeUses approved schema context
Data retrievalManual node, device, and time-window selectionValidated query retrieves required telemetry
Constraint checkManual comparison with voltage, SOC, and tracking limitsDeterministic constraint layer evaluates results
Invalid request handlingDepends on user review or database errorValidator blocks unsupported SQL
OutputManual interpretation and plottingText, dashboard, or plot/table assessment
TABLE IV: Functional comparison with a manual monitoring baseline
Fig. 2: Voltage control response at Node 56 during the evaluated run, showing sustained undervoltage excursions below the 0.95 pu lower operating bound.
Fig. 3: Voltage violation event counts per node over the evaluated run, identifying Node 56 as the most frequently violated bus in the feeder.
Fig. 4: Demand response active-power tracking during the evaluated run: reference command ( PrefP_{\mathrm{ref}} ) vs. measured BESS response ( PmeasP_{\mathrm{meas}} ), showing sustained tracking deviation classified as vulnerable.
More in this topic

Power Systems

Power systems research studies the planning, operation, control, and protection of electrical grids and their integration with energy resources.

See all 231 papers

Explore similar work

CardsList

  1. Traceable Fault Diagnosis for Battery Energy Storage Systems via Retrieval-Augmented Multi-Agent O&M Assistant

    Jul 2, 2026Jiangdi Ru, Bing Li, Yage Huang +2Fault DetectionFault Diagnosis

    Corporate Research Center, Midea Group, Foshan528311, People’s Republic of China · New Energy Business Division, Midea Group, Foshan528311, People’s Republic of China

  2. PowerBench: A Benchmark for Agentic Retrieval and Reasoning in Power Systems

    Sep 28, 2026Xijing Wang, Yinsheng Yao, Jinru Ding +5LLM Agent EvaluationAI Agent Benchmarks

    Tongji University · Johns Hopkins University · Shanghai Artificial Intelligence Laboratory +3

  3. Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics

    May 12, 2026Boming Liu, Jin Dong, Jamie LianLLM Agent OrchestrationLLM Tool Use

    Electrification and Energy Infrastructures Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830 USA