Distribution Robust Optimization Strategy for Multiple Microgrids with Shared Energy Storage Based on WGAN-GP Scenario Production

Proposed within the framework of the sharing economy, Shared Energy Storage (SES) aims to enhance the efficiency of Energy Storage Systems (ESS) and drive down costs. This study focuses on an innovative approach to emphasize the multifaceted utilization of individual ESS units and the centralized use of dispersed ESS resources. Renewable Energy Power Plants (REPPs) collaborate to create SES pools, leveraging their ESS assets. Beyond meeting the needs of REPPs, these resources are shared for ancillary services like Secondary Frequency Regulation (SFR) to yield additional benefits. The paper delves into the scheduling techniques for SES. While conventional day-ahead robust optimization algorithms specify ESS power output for each period, they struggle to adjust schedules due to time-dependent constraints like renewable energy output and ESS state limitations. To address this, a distributed SES scheduling method based on optimal operating intervals is proposed. This method introduces an optimal interval variable for Energy Storage State of Charge (SOC) into the traditional three-layer optimization problem, effectively decoupling time-related constraints. Furthermore, a novel Nested Column and Constraint Generation (Nested C&CG) algorithm is presented to solve the mathematical model. Lastly, a revenue sharing model grounded in cooperative game theory is introduced, along with an illustrative example showcasing the efficacy of the proposed approach in managing uncertainties.

Shared energy storage (SES) represents a transformative approach to advancing sustainable energy systems through improved resource utilization and renewable energy integration. In order to enhance the economic benefits of energy storage and prosumers, as well as to increase the consumption rate of renewable energy, this paper proposes a bilevel optimization model for multi-prosumer power complementarity based on SES. The upper level is the long-term energy storage capacity configuration optimization, aiming to minimize the investment and operational costs of energy storage. The lower level is the intra-day operation optimization for prosumers, which reduces electricity costs through peer-to-peer (P2P) transactions among prosumers and the coordinated dispatch of SES. Meanwhile, an improved Nash bargaining method is introduced to reasonably allocate the P2P transaction benefits among prosumers based on their contributions to the transaction process. The case study shows that the proposed model can reduce the SES configuration capacity by 46.3% and decrease the annual electricity costs of prosumers by 0.98% to 27.30% compared with traditional SES, and the renewable energy consumption rate has reached 100%. Through peak–valley electricity price arbitrage, the annual revenue of the SES operator increases by 71.1%, achieving a win–win situation for prosumers and SES. This article, by optimizing the storage configuration and trading mechanism to make energy storage more accessible to users, enhances the local consumption of renewable energy, reduces both users′ energy costs and the investment costs of energy storage, and thereby promotes a more sustainable, resilient, and equitable energy future.

Air-to-air (A2A) communication plays a vital role in low-altitude unmanned aerial vehicle (UAV) networks and demands accurate channel modeling to support system analysis and design. A key challenge in A2A channel modeling lies in extracting reliable cluster characteristics, which are often limited due to the scarcity of measurement data. To overcome this limitation, a cluster characteristic analysis method is proposed for UAV A2A channels in built-up environments. First, we reconstruct virtual urban environments, followed by the acquisition of A2A channel data using ray tracing (RT) techniques. Then, a kernel power density (KPD) clustering algorithm is applied to group the multipath components (MPCs). To enhance the modeling accuracy of intra-cluster angular offsets in both elevation and azimuth domains, a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is further introduced for generative modeling. A comprehensive analysis is conducted on key cluster characteristics, including the intra-cluster number of MPCs, intra-cluster delay and angular spreads, number of clusters, and angular distributions. The numerical results demonstrate that the proposed WGAN-GP-based approach achieves superior angular fitting accuracy compared to conventional empirical distribution methods.

Recently, generative adversarial networks (GANs) are widely applied to increase the amounts of imbalanced input samples in fault diagnosis. However, the existing GAN-based methods have convergence difficulties and training instability, which affect the fault diagnosis efficiency. This paper develops a novel framework for imbalanced fault classification based on Wasserstein generative adversarial networks with gradient penalty (WGAN-GP), which interpolates randomly between the true and generated samples to ensure that the transition region between the true and false samples satisfies the Lipschitz constraint. The process of feature learning is visualized to show the feature extraction process of WGAN-GP. To verify the availability of the generated samples, a stacked autoencoder (SAE) is set to classify the enhanced dataset composed of the generated samples and original samples. Furthermore, the exhibition of the loss curve indicates that WGAN-GP has better convergence and faster training speed due to the introduction of the gradient penalty. Three bearing datasets are employed to verify the effectiveness of the developed framework, and the results show that the proposed framework has an excellent performance in mechanical fault diagnosis under the imbalanced training dataset.

Diversified application scenarios and business models are effective ways to improve the utilization and economic benefits of energy storage systems. In response to the current problems of single application scenarios, high idle rates, and imperfect price formation mechanisms faced by energy storage on the power generation side, a robust two-stage optimization operation strategy for shared energy storage is proposed, taking into account leasing demand and multiple uncertainties, from the perspective of the sharing concept. A multi-scenario application framework for shared energy storage is established to provide leasing services for wind farm clusters, as well as auxiliary services for participating in the electric energy markets and frequency regulation markets, and the participation sequence is streamlined. Based on the operating and opportunity costs of shared energy storage, a pricing mechanism for leasing services is designed to explore the driving forces of wind farm clusters participating in leasing services from the perspective of cost assessment. Considering the uncertainty of wind power output and market electric prices, as well as the market operational characteristics, an optimized operation model for shared energy storage in the day-ahead and real-time stages is constructed. In the day-ahead stage, a Stackelberg game model is introduced to depict the energy sharing between wind farm clusters and shared energy storage, forming leasing prices, leasing capacities, and energy storage pre-scheduling plans at different time periods. In the real-time stage, the real-time prediction results of wind power output and electric prices are integrated with scheduling decisions, and an improved robust optimization model is used to dynamically regulate the pre-scheduling plan for leasing capacity and shared energy storage. Based on actual data from the electricity market in Guangdong Province, effectiveness verification is conducted, and the results showed that diversified application scenarios improve the utilization rate of shared energy storage in the power generation side by 52.87%, increasing economic benefits by CNY 188,700. The proposed optimized operation strategy has high engineering application value.

The effect of loss function on conditional generative adversarial networks

In order to facilitate the local sharing of renewable energy, an energy sharing management method of multiple microgrids (MGs) with a battery energy storage system (BESS) and renewable energy sources (RESs) is developed. First, a virtual entity named the energy sharing provider (ESP), which acts as an agent for MGs, is introduced to minimize the power loss cost. Second, a distributed optimal model and a two-level iterative algorithm for the MGs and ESP are proposed, which minimize the total operation cost including purchasing electricity cost, energy storage cost and power loss cost. Based on the energy sharing framework, considering the local objectives of MGs and the objective of ESP, the optimal scheduling can be achieved through the bidirectional interaction between MGs and ESP. During the optimization, the shared information between MGs and ESP is limited to expected exchange power, which protects the privacy of MGs and ESP. Finally, the effectiveness of the proposed model and algorithm in different scenarios is verified through a case study.

Renewable energy is a critical enabler of global efforts to achieve the United Nations’ Sustainable Development Goals (SDGs), serving as a foundation for addressing social, economic, and environmental challenges. This review explores the multifaceted role of renewable energy in driving progress across several SDGs, particularly SDG 7 (Affordable and Clean Energy) and SDG 13 (Climate Action), while also contributing to goals such as poverty alleviation (SDG 1), improved health outcomes (SDG 3), economic growth (SDG 8), and sustainable cities (SDG 11). The transition to renewable energy sources—such as solar, wind, hydropower, and geothermal—offers pathways to reduce global carbon emissions, mitigate climate change, and ensure universal access to clean energy. In addition, renewable energy projects promote economic empowerment through job creation and rural electrification, driving inclusive growth in underserved communities. The integration of renewable energy in urban planning also supports sustainable development in cities. However, the adoption of renewable energy faces barriers such as high initial investment costs, technological limitations, and regulatory challenges. This review discusses strategies to overcome these obstacles, emphasizing the importance of supportive policy frameworks, international cooperation, and public-private partnerships. It highlights successful case studies from countries that have leveraged renewable energy to make significant strides toward the SDGs, offering valuable insights for global implementation. As the world approaches the 2030 deadline for the SDGs, renewable energy remains a vital driver of sustainable development, providing innovative solutions to complex global issues while fostering a cleaner, more equitable future.

Generative adversarial networks (GAN) are currently a hotly debated research topic in the field of machine vision; however, they possess various shortcomings that cannot be overlooked, such as unstable generated samples, collapsed modes, and slow convergence. The present paper combines the advantages of the super-resolution GAN model (SRGAN) and Wasserstein GAN with gradient penalty (WGAN-GP) and proposes a hybrid model, known as super-resolution Wasserstein generative adversarial network with gradient penalty (SRWGAN-GP). The generator of SRWGAN-GP utilizes the residuals block and Wasserstein distance to increase the resolution of the generated samples and solve the shortcomings of the unstable GAN training. Besides, the discriminator of SRWGAN-GP consists of a local discriminator and a global discriminator to enhance image recognition capacity. Finally, the discriminator is extracted for image recognition. The results of comparative experiments indicate that this method can effectively enhance the accuracy of image recognition.

EvaGoNet: An integrated network of variational autoencoder and Wasserstein generative adversarial network with gradient penalty for binary classification tasks

Accurate recognition of characters imprinted on ship bodies is essential for ensuring operational efficiency, safety, and security in the maritime industry. However, the limited availability of datasets of specialized digits and characters poses a challenge. To overcome this challenge, we propose a generative adversarial network (GAN) model for augmenting the limited dataset of special digits and characters in ship markings. We evaluated the performance of various GAN models, and the Wasserstein GAN with Gradient Penalty (WGAN-GP) and Wasserstein GAN with divergence (WGANDIV) models demonstrated exceptional performance in generating high-quality synthetic images that closely resemble the original imprinted characters required for augmenting the limited datasets. And the evaluation metric, Fréchet inception distance, further validated the outstanding performance of the WGAN-GP and WGANDIV models, establishing them as optimal choices for dataset augmentation to enhance the accuracy and reliability of recognition systems.

Scientometric investigations on dual carbon research: Revealing advancements, key areas, and future outlook

As global climate warming and the continued use of fossil energy are unsustainable, it has become imperative to accelerate the development of renewable energy. As one of the largest developing countries, this is especially true for future sustainable development in China; therefore, focusing on renewable energy can significantly reduce its dependence on imported fossil fuels. With policy support, China’s renewable energy industries have had rapid development and are now at the international forefront level in some fields. However, the renewable energy industries are facing challenges, particularly in terms of energy finance. Basically, the renewable energy industry in China is facing a contradictory dilemma because of funding shortages and inefficient investment strategies, due in part to government-centered renewable energy investment and financing. In view of this, the development status, modes and renewable energy investment characteristics, financing and the corresponding polices in China are discussed in detail in this paper. As certain constraints are hampering the promotion of sustainable renewable energy development, based on the analysis of the key issues, optimizing countermeasures and feasible proposals are presented. All in all, this study is of significance for energy finance and for the development of corresponding policies for sustainable renewable energy development in China.

The emergence of the shared energy storage mode provides a solution for promoting renewable energy utilization. However, how establishing a multi‐agent optimal operation model in dealing with benefit distribution under the shared energy storage is still a challenge. Considering the multi‐agent integrated virtual power plant (VPP) taking part in the electricity market, an energy trading model based on the sharing mechanism is proposed to explore the effect of the shared energy storage on multiple virtual power plants (MVPPs). To analyse the relationship among MVPPs in the shared energy storage system (SESS), a game‐theoretic method is introduced to simulate the bidding behaviour of VPP. Furthermore, the benefit distribution problem of the virtual power plant operator (VPPO) is formulated based on the Nash bargaining theory. In the case study, the proposed method is conducted in four VPPs with different resource endowments in terms of techno‐economic and operation efficiency. Results verify that the multiple virtual power plants with a shared energy storage system interconnection system based on the sharing mechanism not only can achieve a win‐win situation between the VPPO and the SESS on an operation cost but also obtain the optimal allocation scheme and improves the operation efficiency of the VPPs.

Single image super-resolution (SISR) is of great importance as a low-level computer vision task. The fast development of Generative Adversarial Network (GAN) based deep learning architectures realises an efficient and effective SISR to boost the spatial resolution of natural images captured by digital cameras. However, the SISR for medical images is still a very challenging problem. This is due to (1) compared to natural images, in general, medical images have lower signal to noise ratios, (2) GAN based models pre-trained on natural images may synthesise unrealistic patterns in medical images which could affect the clinical interpretation and diagnosis, and (3) the vanilla GAN architecture may suffer from unstable training and collapse mode that can also affect the SISR results. In this paper, we propose a novel lesion focused SR (LFSR) method, which incorporates GAN to achieve perceptually realistic SISR results for brain tumour MRI images. More importantly, we test and make comparison using recently developed GAN variations, e.g., Wasserstein GAN (WGAN) and WGAN with Gradient Penalty (WGAN-GP), and propose a novel multi-scale GAN (MS-GAN), to achieve a more stabilised and efficient training and improved perceptual quality of the super-resolved results. Based on both quantitative evaluations and our designed mean opinion score, the proposed LFSR coupled with MS-GAN has performed better in terms of both perceptual quality and efficiency.