Salient object detection (SOD) has been widely used in practical applications, such as multisensor image fusion, remote sensing, and defect detection. Recently, SOD from RGB and thermal (T) has been rapidly developed due to its robustness to extreme situations, such as low illumination and occlusion. However, existing methods all utilize a dual-stream encoder, which significantly increases the computation burdens and hinders real-world deployment. To this end, we propose a real-time One-stream Semantic-guided Refinement Network (OSRNet) for RGB-T SOD. Specifically, we first fuse the RGB and T via concatenation, addition, and multiplication operations to dig the complementary information between each modality. The efficient early fusion not only facilitates the information exchange between each modality but also avoids the cumbersome dual-stream encoder structure. Then, the lightweight decoder is proposed, making the high-level semantic information filter the low-level noisy features and gradually refine the final prediction. Also, we apply deep supervision to make the training procedure more stable and fast. Due to the early fusion strategy, OSRNet can run at a real-time speed (53–60 fps) on a single GPU. Extensive quantitative and qualitative experiments show that our network outperforms 11 state-of-the-art methods in terms of seven evaluation metrics. Our codes have been released at https://github.com/huofushuo/OSRNet .

With the exploration of deep decarbonization around the world, the contradiction between the low-carbon operation and energy supply in energy systems has been aggravating. There is an urgent need to tap the interactive potential between source and demand sides. In view of the current lack of efficient incentive measures for low-carbon energy consumption, an integrated demand response exchange (IDRX) mechanism is proposed to promote the coordinated low-carbon dispatching on source-demand side for integrated electricity-gas system (IEGS). The value model of IDRX for emission reduction is built to measure the ability of multi-energy load aggregators (MELAs) for decarbonization, and guide the IEGS operator to trade with the appropriate MELAs. An IDRX market clearing model is established based on non-cooperative game theory to allocate the decarbonization benefits among the entities in IEGS, thereby motivating the low-carbon demand response of users. Combined with the optimal operation of carbon capture power plant and power-to-gas (CCPP-P2G) on the source side, a two-stage low-carbon dispatching model for IEGS is established. Case studies are carried out with seasonal and uncertainty scenarios to verify the effectiveness of IDRX in emission mitigation and highlight the economic benefits of the proposed low-carbon dispatching model.

With the exploration of deep decarbonization around the world, it has become a broad consensus that the carbon trading mechanism can promote the low-carbon operation of the energy system by exploring the underlying driver of emissions. The end-users, as the motivator of emission in the integrated electricity-gas system (IEGS), have not been developed so far to participate in the carbon market and help emissions abatement. This paper proposes a bi-level carbon trading scheme on demand side considering the energy consumption level of users and low-carbon demand response. In the upper-level market, an optimal step-based carbon prices customization model is built to impose differentiated incentives on users, thereby balancing the emission mitigation and social welfare. In the lower-level market, a carbon trading mechanism based on the competitive auction program is proposed, then an optimal carbon trading strategy is studied to maximize the consumer surplus and further motivate the low-carbon energy consumption. On the source side, a low-carbon dispatching model of IEGS considering the flexible carbon capture power plant and power-to-gas (CCPP-P2G) is established. Moreover, the Benders decomposition algorithm is used to solve the bi-level optimal model. Case studies verify the feasibility of carbon trading on demand side and demonstrate the environmental and economic benefits of the proposed bi-level carbon trading mechanism.

As with rapid development of the electric vehicle (EV) industry, charging infrastructures are built fast. However, the unreasonable deployments with increasing EVs contribute to a long queuing time for charging demand of EVs, especially in the peak hours. How to navigate a specific EV to economically satisfy its charging demand, while relieve the traffic burden, is an urgent problem. To address that, a price incentive based charging navigation strategy for electric vehicles is proposed. Unlike previous charging navigation studies that mainly focus on the EVs-transportation-power systems modeling, it considers the spatial-temporal influence of EVs' charging decision, especially the simultaneous charging requests. Specifically, the charging navigation framework with the collaborative working mode of EV- charging station-information exchange center (IEC)-intelligent transportation system (ITS) is established first. Following this, spatio-temporal distribution of the charging demand is obtained through the origin-destination (OD) analysis. After this, an event-driven dynamic queue model is constructed. It contributes to the modeling of the charging strategy, together with the proposed reservation opportunity cost mechanism. Finally, the simulation results indicate that the presented charging navigation strategy cannot only reduce the EV's charging cost but also improve the utilization rate of charging facilities, which verify its effectiveness.

With the penetration rate of distributed generator and distributed energy storage growing, the frequency stability of micro-grid is severely affected. In this paper, a self-adaptive secondary frequency regulation (FR) strategy based on virtual synchronous generator (VSG) for a micro-grid containing wind turbine, photovoltaic array, and electric vehicle cluster is proposed. First, modified VSG control is applied to renewable energy units and electric vehicle cluster, where non-error frequency regulation is realized by introducing proportional-integral control into power-frequency controller of VSGs. Secondly, the FR reserve capacity of wind turbine, photovoltaic array, and electric vehicle are predicted in real time through their respective characteristics. Then, a self-adaptive adjustment strategy for secondary FR parameters of VSGs is designed to control the FR power of VSGs according to real-time predicted FR capacity. Finally, the coordinated FR strategy of VSGs and conventional unit is proposed considering the situation of insufficient FR capacity of VSGs. Through the analysis of simulation results, the reasonability and validity of proposed self-adaptive FR strategy for multiple VSGs have been verified.