Energy Economics, Journal Year: 2025, Volume and Issue: unknown, P. 108612 - 108612
Published: May 1, 2025
Language: Английский
Energy Economics, Journal Year: 2025, Volume and Issue: unknown, P. 108612 - 108612
Published: May 1, 2025
Language: Английский
Mathematics, Journal Year: 2025, Volume and Issue: 13(3), P. 373 - 373
Published: Jan. 23, 2025
This review proposes a novel integration of game-theoretical methods—specifically Evolutionary Game Theory (EGT), Stackelberg games, and Bayesian games—with deep reinforcement learning (DRL) to optimize electricity markets. Our approach uniquely addresses the dynamic interactions among power purchasing generation enterprises, highlighting both theoretical underpinnings practical applications. We demonstrate how this integrated framework enhances market resilience, informs evidence-based policy-making, supports renewable energy expansion. By explicitly connecting our findings regulatory strategies real-world scenarios, we underscore political implications applicability results in diverse global systems. integrating EGT with advanced methodologies such as DRL, study develops comprehensive that nature markets strategic adaptability participants. hybrid allows for simulation complex capturing nuanced decision-making processes enterprises under varying conditions uncertainty competition. The systematically evaluates effectiveness cost-efficiency various control policies implemented within markets, including pricing mechanisms, capacity incentives, measures aimed at enhancing competition transparency. analysis underscores potential significantly enhance enabling better withstand shocks sudden demand fluctuations, supply disruptions, changes. Moreover, DRL facilitates promotion sustainable by modeling adoption technologies optimizing resource allocation. leads improved overall performance, characterized increased efficiency, reduced costs, greater sustainability. contribute development robust frameworks support competitive efficient an evolving landscape. leveraging adaptive capabilities policymakers can design regulations not only address current challenges but also anticipate adapt future developments. proactive is essential fostering resilient infrastructure capable accommodating rapid advancements shifting consumer demands. Additionally, identifies key areas research, exploration multi-agent techniques need empirical studies validate models simulations discussed. provides roadmap through policy-driven interventions, bridging gap between game-theoretic
Language: Английский
Citations
3Sustainability, Journal Year: 2025, Volume and Issue: 17(9), P. 3884 - 3884
Published: April 25, 2025
As China’s power market reforms deepen, the scale of operations and number participants have reached new highs, introducing increasingly complex threats heightened risk scenarios. Traditional early warning systems for electricity sales companies are heavily influenced by subjective factors, incomplete data, poor real-time performance, which cannot meet requirements sustainable development. To achieve efficient, full-chain, control, this paper proposes a data-driven method companies, encompassing entire process. Firstly, based on data correlations across process, appropriate sources warnings identified. Key elements then extracted using Principal Component Analysis (PCA), while historical business is adaptively clustered, with levels classified Adaptive Sparrow Optimization Density Peak Clustering Algorithm (DPC-SSA). Lastly, dynamic generated through stacking identification model. The effectiveness practicality proposed validated an analysis real from provincial trading management platform.
Language: Английский
Citations
0Energy Economics, Journal Year: 2025, Volume and Issue: unknown, P. 108578 - 108578
Published: May 1, 2025
Language: Английский
Citations
0Energy Economics, Journal Year: 2025, Volume and Issue: unknown, P. 108612 - 108612
Published: May 1, 2025
Language: Английский
Citations
0