Distributed Generation & Alternative Energy Journal

Digital Twin-Enabled Smart Energy Management for Mega Sports Events

2025-09-09T11:40:35+02:00

Mega sports events pose major energy management challenges due to their scale, and varying energy requirements. This paper suggests and assesses a digital twin powered smart energy management system for minimizing energy consumption, and maximizing grid stability of such events. The approach employs real-time data collection, and multi-domain energy system modeling with sophisticated predictive analytics with load forecasting based on Long Short-Term Memory (LSTM), along with multi-objective optimization techniques. Based on the evaluation with simulated event data, the deployed system exhibited significant improvements by decreasing average energy consumption by 23.2%, and apeak demand by 28.3%, respectively. Subsequently it is also observed that the self-consumption energy rate increase to 72% compared to conventional methods. Additionally, the system was responsible for substantial operational cost savings of about 30% as well as an impressive 37.5% decrease in carbon footprints. The load forecasting model showed a Mean Absolute Percentage Error (MAPE) value of 4.8%. The findings emphasize the potential capabilities of digital twin technology toward effective, sustainable, and resilient energy management for temporary, large-scale events.

Research on Intelligent Control Technology for Cooperative Game Implementation in Source-Grid-Load-Storage Systems Based on Reinforcement Learning

2026-01-09T11:41:55+01:00

As the penetration rate of renewable energy sources such as wind and solar power continues to rise, coordinated control among multiple entities including generation, transmission, load and storage has become crucial for ensuring the economic efficiency and security of power systems. However, the uncertainty of renewable energy output, the multi-period coupling characteristics of flexible resources, and the inconsistency of benefits among entities make it challenging for traditional optimization methods to simultaneously address real-time responsiveness, robustness, and fairness. To address this, this paper proposes an intelligent control method for power generation, grid, load, and storage that integrates Proximal Policy Optimization (PPO) with cooperative game theory. First, a Markov decision model suitable for multi-source, multi-load systems is constructed. The continuous action space of flexible resources enables coordinated control of thermal power, energy storage, and adjustable loads. Subsequently, a penalty for deviation from cooperative payoffs is embedded in the reward function, ensuring that policy optimization simultaneously satisfies overall economic efficiency and inter-agent profit coordination requirements. Multi-scenario simulations on IEEE 33-node and IEEE 30-node systems demonstrate that this method achieves rapid and stable convergence, significantly reduces operational costs, smooths power fluctuations, and maintains sustainable SOC for energy storage. Compared to conventional methods, it exhibits stronger robustness and higher cooperative incentive effects under uncertain conditions.

Reinforcement Learning-Driven Microgrid Dispatch Under Extreme Weather Events: A Risk-Averse Decision Architecture for Coastal Cities

2026-01-08T08:22:11+01:00

Resilience in action through the growing effects of weather events that threaten the stability of coastal energy infrastructure systems and microgrids with risks not manageable by traditional dispatch techniques. Discuss Risk Averse Reinforcement Learning Decision Architecture (RARLDA), proposed with the intention of integrating risk responsiveness into traditional dispatch plans. Discuss the uniqueness of RARLDA over existing conventional reinforcement learning models through its adaptation from average performance measures into risk-aware decision-making with primary attention devoted to maximum wind speed, rainfall intensity, and temperature. Adopt a qualitative research methodology through the utilization of the “Top 100 Cities Weather Dataset” with the purpose of developing risk indices specific for coastal areas. The research also makes use of median imputation techniques for the elimination of any gaps in the dataset with additional focus on Z score normalization for maximum reliability of the dataset. Calculate the risk indices based on the use of the percentile-based thresholds, together with the use of the Conditional Value at Risk penalization, incorporating them into the RL reward function. The validity of the framework can be shown through the simulation outcome, thereby providing the measure of novelty and performance, where the value of the mean reward is calculated to be 9.84, the mean accuracy defined at 75.95%, and the mean risk index threshold derived at 0.070, thereby outdoing other techniques based upon stability and adaptability. Finally, the conclusion could be derived based upon the contribution to the field, thereby providing the insights into the integration of the risk associated with the climate change into the learning process itself, thereby providing the notion of a qualitatively verified and risk-sensitive model within the field of Resilient and Graceful Management of Energy Systems within the Coastal Cities.

Resilience Improvement for Distributed Renewable Energy Grids: Integration of UAV-Assisted Live-Line Inspection and Real-Time Systems

2025-11-11T03:34:09+01:00

In the context of global energy transition, distributed renewable energy grids face key issues of insufficient resilience due to frequent equipment failures, complex operating environments, and limitations of traditional operation and maintenance methods. The core objective of this study is to enhance the resilience of this type of power grid, integrate unmanned aerial vehicle assisted live inspection and real-time fault diagnosis technology, and construct a full process solution. In the inspection process, a multi rotor drone equipped with high-definition cameras, infrared thermal imaging devices, and partial discharge sensors is used to conduct uninterrupted inspections of power grid equipment at a flight altitude of 20∼150 m and a speed of 3∼8 m/s. Multiple sources of data such as equipment appearance defects and hot spot distribution are collected 2–4 times a week, covering areas that are difficult for manual access. This significantly improves the efficiency of traditional inspections and provides high timeliness data support for fault diagnosis. Fault diagnosis fusion deep learning technology embeds the Convolutional Block Attention Module (CBAM) into the YOLOv7 model to enhance feature focus, constructs a dual channel Generative Adversarial Network (GAN) combined with Long Short-Term Memory (LSTM) to capture fault timing patterns, and designs a sliding window error correction mechanism to counteract noise interference. In the experiment, the accuracy and recall of this method reached 88.62% mAP@0.5 Significantly superior to existing methods such as BVLOS and SIS. The research results provide strong technical support for the safe and stable operation of distributed renewable energy grids, which helps to improve the reliability and anti-interference ability of the grid, promote the sustainable development of distributed renewable energy grids, and is of great significance for ensuring energy security and addressing climate change.

A Distribution Network Operational Situation Perception Technology Based on Graph Convolutional Neural Network-Enhanced Digital Twin Model

2025-11-20T16:52:47+01:00

Currently, traditional monitoring methods based on physical models and SCADA static data struggle to achieve real-time insight, trend prediction, and proactive early warning of system operational states. To accurately perceive the operational situation and locate faults in distribution networks, this study introduces a distribution network operational situation perception approach grounded in graph convolutional neural network-enhanced digital twin model. This method enhances the traditional digital twin model with graph convolutional neural networks to achieve accurate positioning and fault analysis of distribution network operational situations. The research findings demonstrate that, compared to the traditional random forest algorithm, the new method improves positioning accuracy by approximately 10.5%. Meanwhile, the average positioning error of the new method is reduced by about 3.4 compared to the traditional random forest algorithm. Furthermore, using a single graph convolutional neural network results in a 7.5% decrease in positioning accuracy and a 2.1 increase in positioning error compared to the improved model proposed in this study. Stability testing shows that when the learning rate is set to 0.0003 or 0.0005, the accuracy of the model reaches 98% after 100 iterations of training. The robustness verification shows that under the interference scenario of injecting 2% false data, the accuracy, recall, F1 score, and precision of the model remain above 98%. Thus, employing the new improved model can significantly enhance the fault positioning accuracy for distribution network operational situations. This holds considerable research significance for achieving effective operational situation perception and positioning in distribution networks.

Research on Microgrid Power Dispatch Optimization Based on an Improved Parrot Optimization Algorithm in Cloud Environments

2025-12-16T16:00:39+01:00

To address the issues of high operational costs and load factors in microgrids under current renewable energy conditions, this study proposes a grid scheduling strategy based on a parrot optimization algorithm incorporating chaotic and adaptive weighting. First, a scheduling model based on power operation costs and load rates in cloud-based microgrids is constructed. Second, logistic chaos is employed during the initialization of the parameter optimization algorithm to increase population diversity, whereas an adaptive weight adjustment strategy balances global and local exploration capabilities. Finally, simulation experiments validate the algorithm’s performance. Compared with the ACO, PSO, and PO algorithms, it reduces costs and power load factors by 63.4%, 45.7%, 8.3%, and 6%, respectively, in scenarios with small numbers of users and by 37.4%, 34.4%, 23.6%, and 6%, respectively, in scenarios with large numbers of users. 23.6%, 9.51%, 9.51%, and 1.18%, respectively. This demonstrates its ability to effectively reduce operational costs and lower power load rates, indicating significant practical value.

Low-Voltage Ride-Through Technology of Distributed Photovoltaic Inverters Based on Model Predictive Current Control

2026-01-15T16:35:54+01:00

This paper proposes a low-voltage ride-through (LVRT) control strategy for distributed photovoltaic (PV) inverters based on model predictive current control (MPCC). A complete system model is established from the three-phase L-filter plant to its dq-frame representation, followed by discrete-time prediction and switching-state optimization. An LVRT-oriented current reference allocation mechanism is integrated to enable rapid active power curtailment and dynamic reactive injection during grid voltage sags. Unlike conventional PI–SVPWM schemes, the proposed MPCC directly evaluates all voltage vectors each sampling period, eliminating cascaded loops and improving transient response. Simulation studies verify that the method ensures stable current tracking under deep voltage disturbances, reduces harmonic distortion, suppresses DC-link fluctuations, and achieves fast post-fault recovery. A 1 kW hardware prototype further demonstrates real-time feasibility, achieving sub-millisecond dynamic reaction, low THD during LVRT, and significantly reduced overshoot compared with PI-controlled benchmarks. These results confirm that MPCC provides an effective and robust LVRT solution for modern grid-connected PV systems, offering improved dynamic performance, enhanced power quality, and strong grid-code compliance.