Search

This paper reviews the first AIM challenge on mapping camera RAW to RGB images with the focus on proposed solutions and results. The participating teams were solving a real-world photo enhancement problem, where the goal was to map the original low-quality RAW images from the Huawei P20 device to the same photos captured with the Canon 5D DSLR camera. The considered problem embraced a number of computer vision subtasks, such as image demosaicing, denoising, gamma correction, image resolution and sharpness enhancement, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. The proposed solutions significantly improved baseline results, defining the state-of-the-art for RAW to RGB image restoration.

RAW files are widely applied in cameras and scanners as storage because they contain original optical data. Different cameras usually process the RAW files using diverse algorithms that are incompatible. To address the issue, we propose a general transformation method for cross-camera RAW to RGB mapping based on Generative Adversarial Network (GAN). Moreover, we propose a saliency map-aided data augmentation technique and the saliency maps are produced by Saliency GAN (SalGAN). Given RAW file as an input, it jointly predicts the RGB image and corresponding saliency map to enhance perceptual quality in the generated image. The proposed architecture is trained on the Zurich RAW2RGB (ZRR) dataset. Experimental results show that our method can generate more clear and visually plausible images than state-of-the-art networks.

With the increasing amount and type of connected microgrids in the near-term future power networks, how to optimize the operation of a multi-microgrid system efficiently and reliably has become essential for taking full advantage of the complex systems. In this paper, we propose a multi-timescale coordinated optimization strategy for hybrid three-phase/single-phase multi-microgrids. With the consideration of the economy of microgrids and three-phase unbalance constraints of multi-microgrids, a strategy of collecting-distributing fuzzy modified adaptive particle swarm economic optimization is provided. In this day-ahead strategy, the system is constructed as a bi-layer rolling optimizing structure, where the lower layer sets objectives for economic optimization, and the upper layer balances constrained tie-line power of single-phase microgrids based on the optimized results obtained from lower layer. On this basis, by taking day-ahead optimized tie-line power as baseline values, we obtain the real-time power of energy storage systems using an improved nondominated sorting genetic algorithm, which achieves distributed real-time optimization for the multi-microgrid. Simulation results verify that the proposed strategy is feasible.

The microgrid is emerging to be an approach to solve the problem of the reliable supply of electricity and the diverse demand for users. Safe and efficient strategies are required to maintain the microgrid stable when the operating mode changes. The transfer strategies consist of the transition from grid-connected mode to islanded mode and from the islanded mode to grid-connected mode. To begin with, the paper introduces the photovoltaic (PV) — battery energy storage system (BESS) microgrid system and the corresponding control methods of the microsources. Then the smooth mode transfer strategies are presented, which include transfer between islanded mode and grid-connected mode. Finally, the proposed transfer strategies are validated by the experimental results in the China Merchants Group PV-BESS microgrid in Shenzhen.

For hybrid three-phase/single-phase multi-microgrids, a tie-line power optimization strategy based on Stackelberg game considering three-phase unbalance is proposed. In this paper, a topology of hybrid three-phase/single-phase multi-microgrids and the three-phase unbalance constraint are firstly introduced; then the tie-line power optimization strategy based on a one-leader-multi-follower cooperative Stackelberg game is presented, where the regional microgrid central controller is the leader and all microgrid central controllers are followers, all of whom cooperate on perusing the maximum joint profit and reach their optimal economies. Mathematical payoff models are constructed and the strategy are solved by particle swarm optimization algorithm. The proposed optimization improves the algorithm by Stackelberg game, which removes the strong constraint to help it find the optimal solution instead of shunning the local optima. It is practicable with wide application range. Verified by simulation results, the proposed strategy is workable and efficient, which enhances the economy of each microgrid and mitigates three-phase unbalance.

With the fast proliferation of residential microgrids integrated into the power grid, it is crucial to develop a low cost and high efficiency microgrid central control (MGCC) for promoting the large-scale application of residential microgrids. Considering various users' demand, we develop a novel MGCC based on the multi-level communication model. The MGCC integrates many functional modules, including black start, seamless transfer, power prediction, operation optimization control, and energy management. The experiment based on the CETLAB microgrid platform verifies the proposed MGCC and strategies. The control device development of the residential microgrids with the photovoltaic and energy storage system (PV-ESS), promotes the smart grid construction, electric power market reform, and national energy policy.

Wind/PV/Battery micro-grid hybrid simulation research on operational control is an important link in the development of renewable energy power generation technology. This paper establishes a model of micro power unit control system based on RTDS and a digital physical hybrid simulation model of micro power unit control system based on RTDS and controller, constructs a Wind/PV/Battery micro-grid experimental platform, and its electrical topology structure, system structure and communication architecture are given. In this paper, switching and operational control strategy of micro-grid are proposed, and through experiment to verify. This paper first verifies the feasibility of the digital physical hybrid simulation, and then designs a variety of conditions for simulation of grid-connected/islanded mode switching. The results show that micro grid experimental platform can be in a state of equilibrium under different conditions and keep running smoothly during the adjustment process, the effectiveness of the proposed control strategy is verified. Through research and construction of this platform, the performance of the control strategy can be tested and debugged on the physical platform, and the control parameters can be modified in real time, at the same time, it provides important practical basis for practical engineering design.

With the fast proliferation of microgrids (MGs) integrated into the power grid, several nearby MGs with common benefit have been coupled to be multi-microgrids (MMGs), which is a significant stage for developing to the smart grid. A suitable control structure and corresponding control device need to be proposed for the MMGs operating efficiently. However, mostly microgrid (MG) control devices are still restricted to the single MG and have limited application without the common design. We develop control devices with a prodigious popularization value for the MMGs based on the hierarchical control structure. According to the proposed four-layer control architecture (scheduling layer, central control layer, integrated terminal layer and bottom layer), the hardware and software design suitable for the MMGs control devices and its multi-time scale communication architecture have been presented. Furthermore, the appearance design and interface exploitation were introduced as well. Experimental results are provided to demonstrate the validity of the proposed MMGs control structure and devices, which could contribute to the large-scale application of MMGs control devices and provide a reference for other MMGs projects.

Microgrids (MGs) is developing at an incredible speed in recent years, combined by multiple microgrids, multi-microgrids (MMGs) gradually become a new form of power grids. A stabilized and effective black start strategy for MMGs is in an urgent demand. In this paper, we analyze the topology and control system of the residential type MMGs with three-phase/single-phase (TP/SP) architecture. Then, we present the black start strategy based on the hierarchical control scheme is presented, including the stand-alone operation strategy, and the grid-connected operation strategy. After the selection of the main power supplies, the master MG is determined. When the synchronous connection condition is met, the slave SMGs which execute the stand-alone algorithm connect to the master MG who provides the voltage and frequency support. Meanwhile, the control algorithm transfers to the grid-connected algorithm, with the grid dispatching value set to zero. Finally, experimental results of the MMGs platform in the Clean Energy Technology Laboratory (CETLAB) are presented to verify the effectiveness and feasibility of the proposed black start strategy.

With the large-scale development of microgrids-(MGs), adjacent area could formulate multi-microgrids (MMGs) due to the mutual connection and supply, stimulating the problem about efficient and economic operation in multi-microgrids and becoming one of the pivotal technologies. This paper presents distributed predict optimal operation algorithm and control strategies considering the situation of grid integration and stand alone for the multi-microgrids with series structure. As for the operation when the multi-micgrids is connected, we take time-sharing price into consideration for maximum benefit while we comprehensively premeditate the rate and time of load power supply to satisfy the users' demands in autonomous situation. Based on sources and loads prediction, we build economy optimal objective function in every layer of multi-microgrids, uniting the central controller of every sub-microgrid to realize the receding-horizon optimal operation. Case study results verify the feasibility and better economy of the proposed method.