Key Takeaways & Executive Findings
- •• • Distributed consensus ACE discovery enables each regulation unit to communicate only with adjacent units, eliminating the single-point failure sensitivity of centralized AGC and reducing computational complexity from O(n²) to O(n) per iteration, which is critical for maintaining frequency stability when communication infrastructure is partially damaged during disasters. • • Heterogeneous unit coordination is achieved through independent PI controllers tuned to each unit's dynamic response: gas turbines and diesel generators with slow ramp rates (governed by time constants T_GT1–T_GT4 and T_DG1–T_DG2) are coordinated with fast-response wind (T_WT), photovoltaic (T_PV), and fuel cell (T_FC) units, preventing the fast units from being curtailed by centralized allocation. • • The latter-half regulation strategy adjusts slow-response unit output to release fast-response unit capacity, reserving frequency regulation margin for subsequent cycles; this is analogous to state-of-charge management in storage systems and directly addresses the capacity depletion problem that occurs when fast units are continuously dispatched under sustained disturbances. • • The proposed method avoids the retraining requirement of multi-agent reinforcement learning approaches (e.g., DDPG, Q-learning) when extreme disasters cause generation unit failure or topology changes, providing a decisive operational advantage where retraining latency of minutes to hours would be unacceptable for real-time frequency control.
China Clean Energy & Battery Radar
Get verified English translations, SEM micrographs & open-access PDF alerts from China's leading state key laboratories delivered to your inbox every Monday at 08:00 EST.
Abstract
Extreme disasters compromise the coordinated frequency regulation of heterogeneous microgrid resources, as centralized automatic generation control (AGC) architectures exhibit single-point vulnerability, high computational burden, and limited scalability. This paper proposes a multi-agent distributed consensus-based cooperative AGC method. A distributed consensus multi-source AGC framework is constructed to enable cooperative secondary frequency regulation. A distributed consensus-based area control error (ACE) discovery algorithm is developed, allowing each regulation unit to communicate only with adjacent units and converge to a global ACE equilibrium. Each unit then participates in frequency regulation through an independently designed PI controller based on its dynamic response characteristics. During the latter half of the regulation period, the output power of slower-response units is adjusted to release the frequency response capability of faster-response units, reserving regulation capacity for subsequent cycles. Simulation models of gas turbines, diesel generators, wind turbines, photovoltaics, and hydrogen fuel cells are established in Matlab/Simulink. Results demonstrate that the proposed AGC method effectively coordinates heterogeneous regulation units, exhibits strong anti-interference capability under extreme disasters, and avoids the need for retraining associated with reinforcement learning approaches. The method offers reduced computational burden, high scalability, and resilience to single-point failures.
1. Introduction
Centralized AGC architectures, while effective under normal operating conditions, exhibit critical vulnerabilities under extreme disasters: they are sensitive to single-point failures, require global communication infrastructure that may be compromised, and impose a computational burden that scales poorly with the number of heterogeneous regulation units. Existing centralized PI controllers generate a total AGC command and then uniformly allocate it to individual units, which inherently limits the regulation capability of fast-response units such as wind turbines and photovoltaics. Game-theoretic approaches demand global communication and high computational complexity, making them impractical for disaster scenarios. Consensus-based methods offer local information exchange but their convergence speed depends on initial conditions and lacks disaster-scenario adaptability. Reinforcement learning methods require retraining when generation unit failures or topology changes occur, consuming substantial time that is unavailable during emergency frequency events.
This paper addresses these bottlenecks by proposing a multi-agent distributed consensus-based cooperative AGC method. A distributed consensus ACE discovery algorithm enables each regulation unit to communicate only with adjacent units and converge to a global ACE equilibrium, eliminating single-point failure sensitivity and reducing computational burden. Each unit participates in frequency regulation through an independently designed PI controller based on its own response speed. During the latter half of the regulation period, the output power of slower-response units is adjusted to reduce the output of faster-response units, reserving fast-unit frequency response capability for the next regulation cycle. The method is validated on a microgrid model comprising gas turbines, diesel generators, wind turbines, photovoltaics, and hydrogen fuel cells in Matlab/Simulink, demonstrating effective coordination of heterogeneous units and strong anti-interference capability under extreme disasters.
Loading authentic research manuscript (Pages 1–5)...
LI Yanyan, XUE Xian (2026). Distributed Consensus-Based Multi-Source Cooperative AGC Method for Microgrids Under Extreme Disasters. Acta Energiae Solaris Sinica. https://doi.org/10.19912/j.0254-0096.tynxb.202608_9691
Research & Educational Purpose Only: The translations, structured abstracts, analytical annotations, and data reports provided by SinoGreenTechare intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoGreenTech claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the convergence rate of the distributed consensus ACE discovery algorithm, and how does it degrade under communication delays or packet loss typical of disaster scenarios?
The paper does not report explicit convergence rate metrics (e.g., iterations to convergence, settling time) or quantify degradation under communication delays. The algorithm is designed for local information exchange among adjacent units, which inherently reduces communication burden compared to centralized or game-theoretic approaches. However, the absence of empirical convergence data under stressed communication conditions represents a gap that requires further validation before deployment in disaster-prone microgrids.
How does the proposed method handle the loss of a regulation unit (e.g., a gas turbine failure) without requiring retraining, and what is the impact on ACE convergence?
The distributed consensus framework enables each unit to discover ACE through local communication with adjacent units. When a unit fails, the remaining units continue to exchange information and converge to a new global ACE equilibrium without retraining, unlike reinforcement learning methods that require retraining when generation unit failures or topology changes occur. The paper states that the method has strong anti-interference capability under extreme disasters, but does not quantify the convergence time or frequency deviation following unit loss.
What are the specific time constants for each heterogeneous unit model, and how do they affect the coordination strategy?
The paper provides transfer function models: gas turbine G_GT(s) = (1+T_GT1 s)(1+T_GT2 s)/((1+T_GT3 s)(1+T_GT4 s)); diesel generator G_DG(s) = 1/((1+T_DG1 s)(1+T_DG2 s)); wind turbine G_WT(s) = 1/(1+T_WT s); photovoltaic G_PV(s) = 1/(1+T_PV s); fuel cell G_FC(s) = 1/(1+T_FC s). Specific numerical values for T_GT1–T_GT4, T_DG1–T_DG2, T_WT, T_PV, and T_FC are not provided in the extracted text. The coordination strategy uses these time constants to design independent PI controllers and to schedule slow-response units to release fast-response unit capacity in the latter half of the regulation period.
How does the latter-half regulation strategy compare quantitatively to conventional AGC in terms of frequency nadir improvement and regulation capacity reservation?
The paper does not report quantitative frequency nadir improvement or regulation capacity reservation metrics. The strategy is described qualitatively: during the latter half of the regulation period, the output power of slower-response units is adjusted to reduce the output of faster-response units, reserving fast-unit frequency response capability for the next regulation cycle. Without empirical data on frequency deviation reduction or reserved capacity (e.g., MW or percentage), the industrial impact cannot be assessed from the extracted text.
What is the computational burden of the proposed distributed consensus method compared to centralized AGC and reinforcement learning approaches?
The paper claims reduced computational burden and high scalability as advantages of the distributed consensus method, because each unit communicates only with adjacent units and does not require global communication or centralized optimization. In contrast, centralized methods suffer from computational complexity and single-point failure sensitivity, and reinforcement learning methods require retraining when topology changes. However, the paper does not provide quantitative computational metrics (e.g., execution time, number of operations, or scalability curves) to substantiate these claims.
Related Chinese Research & Cross-Citations
Wind Turbine Gearbox Fault Diagnosis Method Based on Improved CNN-XGBoost Fusion Model Under Gramian Angular Difference Field
Gearbox failures account for 20–30% of total wind turbine faults and incur maintenance costs equivalent to 10–15% of overall turbine value. Conventional vibration diagnostic pipelines—complementary ensemble empirical mode decomposition with singular value energy spectrum, time-varying filtering empirical mode decomposition, and Teager energy spectrum analysis—remain bounded below 90% accuracy and depend on expert-driven feature engineering that is sensitive to non-stationary operating conditions and noise. This study proposes an intelligent diagnostic architecture that converts one-dimensional gearbox vibration signals into two-dimensional images via Gramian angular difference field (GADF) transformation, preserving intrinsic temporal correlation and time-frequency structure while exploiting matrix sparsity to suppress interference. An improved convolutional neural network (CNN) extracts multi-dimensional features: a convolutional block attention module (CBAM) is embedded in the convolutional layers to weight critical channels and focus on fault-sensitive spatial regions, and a modified βc-ACONC activation function replaces ReLU to mitigate neuron necrosis and enable selective activation. The extracted composite features are then fed into an XGBoost network whose hyperparameters are optimized by an improved sparrow search algorithm (ISSA). Validation on a laboratory wind turbine gearbox dataset yields diagnostic accuracy exceeding 99%, demonstrating robust fault identification capability under complex operating conditions.
Joint Forecasting of Wind and Photovoltaic Power Considering Complementarity
The inherent spatiotemporal complementarity between wind and solar resources offers a theoretical basis for improving renewable power forecasting accuracy. This study proposes a joint wind-photovoltaic (PV) power forecasting strategy that explicitly exploits this complementarity. A bidirectional long short-term memory (BiLSTM) neural network serves as the baseline forecasting model, and a novel sorting and comparative optimization (SCO) algorithm is developed to optimize the model's hyperparameters. The SCO algorithm ranks individuals in ascending order and compares adjacent fitness values to escape local optima, a known deficiency in conventional metaheuristics such as genetic algorithms and particle swarm optimization. For wind farms and PV plants exhibiting significant complementarity, the joint forecasting strategy first aggregates their power outputs, normalizes the combined signal, and then feeds it into the optimized BiLSTM model. Experimental results demonstrate that the proposed SCO-BiLSTM model reduces the eMAPE by 10.313% compared with PSO-BiLSTM. Furthermore, joint forecasting under SCO-BiLSTM lowers the eRMSE by 27.443% relative to standalone PV power forecasting. The study also establishes that forecasting accuracy improves with stronger wind-solar complementarity but degrades as the forecasting horizon extends. These findings confirm that exploiting complementarity in joint forecasting substantially enhances predictive performance for renewable energy integration.
Ultra-Short-Term Wind Power Forecasting Based on Fluctuation Continuation Scenario Identification
Existing ultra-short-term wind power forecasting methods exhibit limited performance due to insufficient extraction of fluctuation information and inadequate analysis of evolution patterns. This paper proposes an ultra-short-term wind power forecasting method based on fluctuation continuation scenario identification. First, the coupling mechanism of wind power fluctuations under multiple turbulence processes is investigated, and historical wind power dynamics are decoupled into a combination of nonlinear and linear fluctuation components. A fluctuation continuation concept is introduced, and the future continuation scale of wind power fluctuations is derived from nonlinear and linear decoupling parameters, thereby classifying fluctuation continuation scenarios. A sparse neural network (SNN) oriented to high-dimensional sparse features is constructed to identify historical fluctuation continuation scenarios, and ultra-short-term power forecasting is conducted separately for each scenario. Validation using measured wind speed and power data from three wind farms shows that, compared with baseline models, the proposed model improves root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by at least 1.46%, 2.44%, and 14.67%, respectively, demonstrating superior accuracy and stability. The method addresses the limitations of signal decomposition techniques that lack physical interpretability and are sensitive to hyperparameters, and overcomes the high-dimensional sparsity challenges faced by traditional scenario identification models.
Multi-Classifier Open Adversarial Network for Rolling Bearing Fault Diagnosis in Wind Turbine Generator Systems
Rolling bearings in wind turbine generator systems operate under variable speed and load conditions that induce significant data distribution shifts between training and field data, while unknown fault modes absent from the source domain are frequently misclassified as known classes. This study proposes a multi-classifier open adversarial network (MCOAN) for open-set fault diagnosis. Within an adversarial domain adaptation framework, a K-way classifier and an additional K+1-way one-vs-all classifier independently estimate target-sample similarity to the source domain. These similarity scores drive a dynamic weighting mechanism that adaptively reweights target samples during open-set adversarial training and supplies per-sample dynamic thresholds for known/unknown discrimination, thereby promoting cross-domain alignment of shared-class features while suppressing negative transfer from unknown samples. A non-adversarial domain classifier is introduced to stabilize dynamic weight estimation. Validation on two datasets demonstrates high-precision shared-class distribution alignment and unknown-class recognition with favorable robustness. The method removes reliance on empirically preset thresholds that plague conventional open-set back-propagation approaches, where a fixed threshold of 0.5 in the binary cross-entropy adversarial loss provides no per-sample adaptivity. By coupling K-way and K+1-way similarity estimates, MCOAN achieves simultaneous known-class alignment and unknown-class separation without prior knowledge of the unknown-class cardinality, addressing a persistent bottleneck in wind turbine drivetrain condition monitoring where unanticipated bearing failure modes emerge under field conditions.
Unsupervised Automated Identification Method for Abnormal States of Wind Turbine Gearboxes
Addressing the scarcity of labeled data for training classification models in wind turbine planetary gearbox anomaly identification, this study proposes an unsupervised automated detection method. Log Mel-band energy features are extracted from raw vibration signals and fed into an unsupervised anomaly recognition model centered on a U-net autoencoder. A health-state threshold is established based on reconstruction error between model input and output, enabling anomaly identification. The method is validated using factory gearbox test data and operational data from a wind farm in Yangtouya, Shanxi. For factory gearboxes, dual validation is performed using a spectrum amplitude modulation-based signal processing method. Results demonstrate that the proposed method achieves 93.34% recognition accuracy on both factory and wind farm test sets, confirming its capability to automatically and correctly separate abnormal wind turbine gearboxes. The approach eliminates reliance on labeled fault data, offering a scalable solution for full-lifecycle health monitoring, from factory acceptance testing to in-service early anomaly detection, adaptable across different operating conditions and turbine models.
Improved Adaptive Super-Twisting Sliding Mode Control for Permanent Magnet Synchronous Motors
Adaptive super-twisting sliding mode control (ASTSMC) for permanent magnet synchronous motors (PMSM) suffers from prolonged convergence and insufficient disturbance rejection under complex operating conditions. This paper proposes an improved ASTSMC incorporating a fixed-time disturbance observer (FTDO). A power term is introduced into the adaptive super-twisting controller to accelerate convergence far from the origin, while the discontinuous sign function is replaced by a continuous h(s) function to mitigate chattering. The FTDO ensures disturbance estimation converges within a fixed time independent of initial states, overcoming the limitations of traditional and finite-time observers. The estimated disturbance is fed forward to the sliding mode controller for compensation, enhancing robustness. The FTDO design is based on an auxiliary state variable z and its derivative, with error dynamics analyzed via Lyapunov stability. Comparative simulations against conventional disturbance observers and sliding mode controllers validate the proposed strategy. The results demonstrate shorter convergence time, improved dynamic performance, and superior disturbance rejection, making the approach suitable for high-performance servo systems. The method addresses the critical need for robust, fast-response control in electric vehicles, rail transit, and aerospace applications where PMSM drives face significant uncertainties and external disturbances.