This paper investigates the dispatch process of electric vehicles (EVs) when virtual power plants (VPPs) respond to electricity market demand and proposes an EV dispatch model that considers willingness to participate. The model considers the range anxiety and battery aging anxiety of EVs in the response scheduling process, which effectively improves the willingness of EVs to respond to scheduling. The model mainly involves three aspects: charging station siting, determination of EV incentive electricity price and realization of distributed dispatching. First, this paper proposes a three-step weighted mean clustering method to plan charging station siting, which reduces the driving distance of EVs when responding to grid dispatching, thus reducing range anxiety. At the same time, we studied the effect of different modifications in practical applications. Subsequently, we established an incentive price model for EVs to achieve reasonable quantitative compensation for the battery aging problem that occurs during the dispatch process. Finally, we propose a distributed scheduling strategy to improve the willingness of EVs to respond. This study is validated using real-world data from the city of Chicago. The proposed method reduces the average response distance of EVs in Chicago by 0.188 km and increases the participation willingness of EVs by 0.3243. These results demonstrate the advantages of the proposed approach in alleviating range anxiety and enhancing EVs’ willingness to participate in grid dispatch, offering valuable insights for largescale EV integration into grid interactions.

The increasing complexity of modern microgrid operations, driven by high renewable energy integration and growing prosumer participation, demands innovative optimization approaches. This paper proposes a novel behaviorally informed tri‐level optimization framework that integrates goal‐setting theory (GST) with distributionally robust optimization (DRO) and reinforcement learning (RL) to enhance prosumer engagement, system efficiency, and adversarial resilience. The upper level employs GST to motivate prosumers with structured energy‐saving and trading goals, the middle level optimizes cost, emissions, and resource allocation, while the lower level ensures robustness against adversarial uncertainties using Wasserstein‐based DRO. A multi‐agent RL approach is incorporated for adaptive decision‐making under uncertainty. Extensive simulations on a community‐scale microgrid reveal a 25% cost reduction, 30% increase in prosumer engagement, and improved resilience against adversarial scenarios. This research bridges behavioral psychology and energy optimization, introducing a human‐centric paradigm that improves microgrid sustainability, participation, and robustness.

This article explores social manufacturing (SM) within cyber–physical–social systems (CPSSs), leveraging artificial intelligence (AI) to revolutionize energy prosumer networks. We introduce a blockchain-enabled operation and management mechanism for energy systems, incorporating energy aggregators for efficient transaction audits and employing consortium blockchain and proof-of-work for enhanced security. Guided by social governance principles and utilizing the soft actor–critic (SAC) approach for handling renewable generation and load demand uncertainties, our method offers a resilient and cost-effective solution. Simulated case studies reveal a 16.7% reduction in audit costs and a 2.4% increase in peer-to-peer transactions, highlighting improved network synergy. Our approach also reduces redundant trading by 6.5%and cuts operational costs by up to 6%, demonstrating the effectiveness of blockchain in improving cost-efficiency and enhancing social governance and security in energy manufacturing systems. The findings of this study contribute a novel vista to the ongoing discourse in SM, illustrating the formidable potential of advanced information and AI technologies in amplifying the operational acumen of contemporary manufacturing ecosystems.

Electric vehicles (EVs) exhibit significant uncertainty in responding to grid dispatch due to the influence of EV users’ judgments and other subjective factors, which affect grid scheduling. These subjective factors are difficult to model using conventional methods. Therefore, this article proposes a flexible EV scheduling strategy based on the ride-hailing dispatch model. This strategy adopts an “order-grabbing” mechanism, where the dispatch center broadcasts demand and EVs respond based on their current status. By dynamically adjusting the dispatch price, the strategy incentivizes EV participation, enhancing flexibility in EV-grid interactions. First, the initial dispatch price is set according to grid demand and EV battery capacity, and dispatch information is sent to EV users. A credit compensation mechanism is introduced to link EVs’ historical response with their rewards, thereby standardizing response behavior. Subsequently, a response willingness model is developed to associate the dispatch price and other influencing factors with response capacity, providing a basis for price adjustments. MATLAB simulations demonstrate that the proposed method successfully completed scheduling in four different scenarios after 1–3 rounds of dynamic price adjustments, demonstrating the feasibility of the strategy. The final average response error using the proposed method was 25 kWh, representing a 61.53% reduction compared to the benchmark method, while scheduling costs decreased by 10.81%, validating both the accuracy and economic efficiency of the strategy. Compared to existing studies, this article innovatively applies the ride-hailing model’s concepts of broadcast demand and order-grabbing response to effectively address the subjective uncertainty of EV users in the response process.

The uncertainty of distributed resource (DR) aggregation responses has become a key bottleneck restricting the reliable scheduling of virtual power plants (VPPs). To mitigate this uncertainty, this paper explores the strong coupling between residential behavior and the adjustable capability of distributed resources, and proposes a dynamic aggregation strategy that accounts for such coupling. First, the concept of Behavior-sensitive Distributed Resources (BDRs) is proposed and defined, where resources whose adjustable capability is significantly influenced by the number of residential users are categorized as BDRs. By applying the Discrete Fourier Transform (DFT), this study, for the first time, reveals the daily periodic characteristics of BDRs. Subsequently, a segmented confidence interval estimation method is introduced, which, in conjunction with the daily periodicity of BDRs, enables precise characterization of adjustable capability across different time periods, thus improving the accuracy of response capability modeling. An improved two-stage greedy aggregation algorithm is then designed to simultaneously reduce the uncertainty of VPP adjustable capability after aggregation and optimize economic performance. Finally, the strategy is validated using real-world data from a resource set that includes three representative types of BDRs: electric vehicle (EV) charging stations, commercial lighting (CL), and office building heating, ventilation, and air conditioning (HVAC) systems. The results demonstrate that, compared to existing approaches, the proposed aggregation strategy reduces VPP response uncertainty by over 22.63% and lowers aggregation cost by an average of 8.44%, thereby confirming its advantages in enhancing both grid reliability and economic efficiency.