Volume 10,Issue 9
Dynamic Human–AI Authority Allocation for Distribution Network Fault Management under Diagnostic Uncertainty
To address the mismatch between diagnostic credibility and machine authority in distribution network fault management, a dynamic human–AI authority allocation model under diagnostic uncertainty is proposed. Based on candidate fault hypotheses and posterior probabilities, comprehensive diagnostic uncertainty is quantified from data evidence, model outputs, and state information. Decision risk is calculated by considering safety, load-loss, operating-limit violation, switching-operation, and time-related losses of candidate actions under different fault states. Allowable authority is determined according to risk thresholds, safety constraints, action reversibility, and operator availability. Three authority modes are configured: machine-led operation, artificial intelligence (AI) recommendation with human confirmation, and human-led operation with AI assistance. A closed loop is established through human takeover, evidence supplementation, rediagnosis, and offline parameter calibration. Illustrative scenarios are constructed using the IEEE 33-bus distribution network as the network context and compared with fixed authority-allocation strategies. The comparison indicates that machine-led operation is selected under low uncertainty and low risk; when a single factor constrains machine authority, AI recommendation with human confirmation is adopted; and when risk thresholds or safety constraints further restrict authority, human-led operation with AI assistance is applied. Authority allocation based only on diagnostic uncertainty may retain excessive machine authority in low-uncertainty, high-risk scenarios. Diagnostic credibility should therefore not be the sole basis for authorizing autonomous machine actions; diagnostic uncertainty, decision risk, and safety constraints should be jointly considered in dynamic human–AI authority allocation.
[1] Zhang Q, Ma Z, Zhu Y, et al., 2021, A Two-Level Simulation-Assisted Sequential Distribution System Restoration Model With Frequency Dynamics Constraints. IEEE Transactions on Smart Grid, 12(5): 3835–3846.
[2] Yang X, Xu C, Wen J, et al., 2023, Cooperative Repair Scheduling and Service Restoration for Distribution Systems With Soft Open Points. IEEE Transactions on Smart Grid, 14(3): 1827–1842.
[3] Wang G, Lei X, Wu H, et al., 2021, A Comprehensive Network Restoration Model for Active Distribution Network Considering Forecast Uncertainty. IEEE Access, 9: 130997–131005.
[4] Heidari-Akhijahani A, Butler-Purry K, 2024, A Review on Black-Start Service Restoration of Active Distribution Systems and Microgrids. Energies, 17(1): 100.
[5] Yuan Y, Dehghanpour K, Wang Z, et al., 2022, Multisource Data Fusion Outage Location in Distribution Systems via Probabilistic Graphical Models. IEEE Transactions on Smart Grid, 13(2): 1357–1371.
[6] Gao Y, Su X, Zhang H, et al., 2024, A Highly Fault-Tolerant Distribution Network Fault Diagnosis Method Based on Data Check and Graph Convolution Neural Network. Advanced Technology of Electrical Engineering and Energy, 43(2): 95–104.
[7] Ji L, Tian X, Wei Z, et al., 2025, Intelligent Fault Diagnosis in Power Distribution Networks Using LSTM-DenseNet Network. Electric Power Systems Research, 239: 111202.
[8] Parasuraman R, Sheridan T, Wickens C, 2000, A Model for Types and Levels of Human Interaction With Automation. IEEE Transactions on Systems, Man, and Cybernetics—Part A: Systems and Humans, 30(3): 286–297.
[9] Lee J, See K, 2004, Trust in Automation: Designing for Appropriate Reliance. Human Factors, 46(1): 50–80.
[10] Santoni de Sio F, Van den Hoven J, 2018, Meaningful Human Control Over Autonomous Systems: A Philosophical Account. Frontiers in Robotics and AI, 5: 15.
[11] Westphal M, Vössing M, Satzger G, et al., 2023, Decision Control and Explanations in Human-AI Collaboration: Improving User Perceptions and Compliance. Computers in Human Behavior, 144: 107714.
[12] Johnson C, Demir M, McNeese N, et al., 2023, The Impact of Training on Human-Autonomy Team Communications and Trust Calibration. Human Factors, 65(7): 1554–1570.
[13] Chiou E, Lee J, 2023, Trusting Automation: Designing for Responsivity and Resilience. Human Factors, 65(1): 137–165.
[14] Jui J, Hettiarachchi I, Bhatti A, et al., 2025, A Recent Review on Subjective and Objective Assessment of Trust in Human Autonomy Teaming. IEEE Transactions on Human-Machine Systems, 55(5): 819–833.
[15] Van den Bosch K, Van Diggelen J, Verdult S, et al., 2025, Measuring Meaningful Human Control in Human-AI Teaming: Effects of Team Design in AI-Assisted Pandemic Triage. AI and Ethics, 5(3): 3329–3353.
[16] McGrath M, Duenser A, Lacey J, et al., 2025, Collaborative Human-AI Trust (CHAI-T): A Process Framework for Active Management of Trust in Human-AI Collaboration. Computers in Human Behavior: Artificial Humans, 6: 100200.
[17] Srivastava D, Lilly J, Feigh K, 2025, Exploring the Role of Judgement and Shared Situation Awareness When Working With AI Recommender Systems. Cognition, Technology & Work, 27(1–2): 1–18.
[18] Lin J, Tomlin N, Andreas J, et al., 2024, Decision-Oriented Dialogue for Human-AI Collaboration. Transactions of the Association for Computational Linguistics, 12: 892–911.
[19] Liang K, Wang H, Pozo D, et al., 2024, Power System Restoration With Large Renewable Penetration: State-of-the-Art and Future Trends. International Journal of Electrical Power & Energy Systems, 155: 109494.
[20] Hu Y, Qian F, Li H, et al., 2024, Island Fault Recovery Method of Distribution Network Based on Flexible Interconnection Device With Energy Storage. Distribution & Utilization, 41(2): 21–27.
[21] Saaklayen M, Liang X, Faried S, et al., 2024, Soft Open Point-Based Service Restoration Coordinated With Distributed Generation in Distribution Networks. IEEE Transactions on Industry Applications, 60(2): 2554–2566.
[22] Sun L, Huang Z, Yi K, et al., 2024, Coordinated Optimization of Repair Scheduling and Service Restoration for Distribution Network Considering the Damaged Roads. IEEE Transactions on Industry Applications, 60(4): 5407–5422.
[23] IEC 60870-5-104, 2016, Telecontrol Equipment and Systems—Part 5-104: Transmission Protocols—Network Access for IEC 60870-5-101 Using Standard Transport Profiles.
[24] Wu X, Zhao H, Xu W, et al., 2024, Fault Diagnosis of the Distribution Network Based on the D-S Evidence Theory Bayesian Network. Frontiers in Energy Research, 12: 1422639.
[25] Ibrahim A, Sadanandan S, Ghaoud T, et al., 2024, Incipient Fault Detection in Power Distribution Networks: Review, Analysis, Challenges, and Future Directions. IEEE Access, 12: 112822–112838.
[26] Guo Z, Ji X, Wang H, et al., 2024, Active Distribution Network Fault Diagnosis Based on Improved Northern Goshawk Search Algorithm. Electronics, 13(7): 1202.
[27] Xu C, Cheng X, Zhuang X, et al., 2025, Fault Diagnosis of Distribution Network Based on Time Constraint Intuition Fuzzy Petri Nets. Measurement: Energy, 5: 100034.
[28] Xie D, Xu Y, Zhang C, 2023, Robust Service Restoration of Distribution Systems Towards Coordinated Parallel Network Reconstruction and Cold Load Pick-Up. International Journal of Electrical Power & Energy Systems, 152: 109187.
[29] Igder M, Liang X, Mitolo M, 2022, Service Restoration Through Microgrid Formation in Distribution Networks: A Review. IEEE Access, 10: 46618–46632.
[30] Gawlikowski J, Tassi C, Ali M, et al., 2023, A Survey of Uncertainty in Deep Neural Networks. Artificial Intelligence Review, 56(Suppl 1): 1513–1589.
[31] Shannon C, 1948, A Mathematical Theory of Communication. Bell System Technical Journal, 27(3): 379–423.
[32] Baran M, Wu F, 1989, Network Reconfiguration in Distribution Systems for Loss Reduction and Load Balancing. IEEE Transactions on Power Delivery, 4(2): 1401–1407.
[33] Ji X, Zhang S, Zhang Y, et al., 2021, Fault Section Location for Distribution Network Based on Improved Electromagnetism-Like Mechanism Algorithm. Automation of Electric Power Systems, 45(22): 157–166.
[34] Saad M, Kim C, Munir N, 2022, Single-Phase Auto-Reclosing Scheme Using Particle Filter and Convolutional Neural Network. IEEE Transactions on Power Delivery, 37(6): 4775–4785.
[35] Yang L, Qin Y, 2023, Research on Rolling Co-Optimization of Fault Repair and Service Restoration in Distribution Network Based on Combined Drive Methodology. Electric Power Systems Research, 220: 109373.
