Author

Mingyu Ou

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Aug 2026

A joint trading mechanism for energy credits and electricity in virtual power plants

With the urgent need to achieve carbon neutrality goals and the rapid development of distributed energy resources, traditional electricity markets face challenges in effectively integrating environmental and economic values, lacking unified mechanisms to simultaneously clear energy and environmental transactions. This study proposes an energy credits–electricity joint trading mechanism for virtual power plants that achieves co-equilibrium through explicit coupling between energy and environmental value markets. First, a multi-dimensional energy credit quantification model is established, integrating energy type, time period, trading volume, and behavioral characteristics to differentiate environmental contributions. An optional reputation assessment enhancement covering prediction accuracy, fulfillment reliability, response timeliness, trading frequency, and anomaly behavior can be integrated for virtual power plant (VPP) operators requiring behavioral differentiation. Second, a unified joint clearing model is constructed that co-optimizes energy and credit trading, employing the alternating direction method of multipliers (ADMM) to decompose large-scale optimization problems into parallelizable prosumer and market coordination subproblems. Simulation results across single-day, multi-day (5-day cycle), and seasonal scenarios demonstrate that the mechanism successfully distinguishes prosumer performance: renewable energy prosumers accumulate substantial positive credits (136.2 credits over 5 days), while fossil fuel users incur credit deficits (−25.1 credits single-day), achieving system-level carbon credit balance over multi-day settlement cycles. The proposed mechanism effectively realizes the principle of “green contributors benefit, polluters pay” and provides a practical pathway for integrating environmental value in electricity markets.

Mingyu Ou, Feng Liu, Menglong Sun et al. · Frontiers in Energy Research · 0 citations

Open access Aug 2026

Edge-native intelligent scheduling for virtual power plants: A multi-scale perception and constrained reinforcement learning approach

The proliferation of distributed energy resources at the edge of distribution networks provides substantial flexibility for virtual power plant (VPP) operation. However, existing methods often rely on aggregate load information and homogeneous scheduling policies. They, therefore, overlook device-specific response characteristics, heterogeneous response times, and operational safety constraints. This paper presents EDGE-VPP, an end-to-end scheduling framework that connects fine-grained load perception with safety-aware decision-making across multiple temporal scales. At the perception layer, a Load Decomposition Transformer (LDT) uses learnable multi-frequency positional encodings and device-specific attention heads. It jointly detects appliance states and disaggregates device power from aggregate measurements. At the coordination layer, a three-tier cloud–edge–device architecture assigns sub-second emergency response to devices, minute-level economic dispatch to edge controllers, and hour-ahead planning to the cloud. Bidirectional information exchange mitigates conflicts among these control layers. At the optimization layer, multi-constraint proximal policy optimization factorizes continuous and discrete actions. Adaptive Lagrange multipliers enforce voltage and current limits, while two value estimators stabilize policy learning. Experiments on REDD, UK-DALE, and a self-constructed VPP dataset show that LDT reduces mean absolute error by up to 6.86% and improves the F1-score by 3.51% over the Transformer baseline. The complete EDGE-VPP framework also achieves the lowest operating cost and the fewest constraint violations among the evaluated scheduling methods.

Yuandong Jiang, Mingyu Ou, Jiangnan Li · AIP Advances · 0 citations