The emerging of Digital Twin (DT) technology facilitates the further development of industrial automation. However, real-time and accurate DTs modeling and updating require massive communication and computing resource...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
The emerging of Digital Twin (DT) technology facilitates the further development of industrial automation. However, real-time and accurate DTs modeling and updating require massive communication and computing resources, which poses a challenge to limited resources. Edge computing as a distributed computing architecture offers the possibility of high-efficient resource scheduling in DTs. Motivated by this gap, this paper aim to solve the problem of real-time and high fidelity DTs modeling and updating. First, we represent the computing tasks of DTs in the form of Heterogeneous Computing Task Graph (HCTG). Then, a Hierarchical Attention Mechanism (HAT) is proposed to obtain the latent representation vectors of the HCTG. Finally, we design Markov Decision Process (MDP), and propose Deep Reinforcement Learning (DRL)-based computing task scheduling approach (HAT-DRL) to satisfy the minimum total completion time requirement of different DTs. Experimental results demonstrate that the proposed algorithm has promising scheduling performance and outperforms other task scheduling algorithms.
This paper proposes a new distribution system vehicle-to-grid (V2G) optimization research method based on Grey Wolf Optimizer (GWO), aiming to improve the energy management efficiency in smart grids. Combining the pow...
详细信息
ISBN:
(数字)9798350377033
ISBN:
(纸本)9798350377040;9798350377033
This paper proposes a new distribution system vehicle-to-grid (V2G) optimization research method based on Grey Wolf Optimizer (GWO), aiming to improve the energy management efficiency in smart grids. Combining the powerful global search capability of GWO algorithm, this paper designs an improved distribution system optimization model, which can effectively dispatch the charging and discharging behavior of electric vehicles, thereby balancing the grid load and improving energy utilization efficiency. An optimization model containing multiple operating constraints is established and solved by GWO algorithm. Simulation results show that after GWO optimization, the system can significantly reduce the peak and valley load differences, achieve more balanced power distribution, and reduce the operating cost of the distribution system. Specific data analysis shows that compared with traditional optimization methods, the optimization model using GWO algorithm shows great improvements in system response speed, optimization accuracy and energy management effect. This study provides a new technical path for V2G interaction in future smart grids, which will help promote the efficient use of green energy and the further development of smart grids.
This paper proposes a new type of corridor climbing inspection robot, aimed at solving the problems of insufficient power and poor stability of existing robots in complex terrain and steep slope environments. The robo...
详细信息
ISBN:
(纸本)9798350377040;9798350377033
This paper proposes a new type of corridor climbing inspection robot, aimed at solving the problems of insufficient power and poor stability of existing robots in complex terrain and steep slope environments. The robot adopts a design that combines ground rails with linear transmission bodies, optimizes the automatic walking drive device and multi axis displacement robotic arm, and achieves stable inspection with a maximum climbing angle of over 60 degrees. The robot is equipped with a high-resolution image acquisition device and a supplementary light source, combined with image processing and machine learning algorithms, to automatically identify and classify defects and anomalies during inspection. The experimental results show that the robot does not derail or deviate when climbing a 60 degrees slope, with a minimum turning radius of 1.5 meters, image resolution of 1080p, battery life of 8 hours, stable data transmission, automatic recognition accuracy of over 95%, and maintains stable performance after continuous operation for 1000 hours.
The optimal control problem including random variables is difficult to solve. Existing methods typically rely on defining explicit decision functions to make the problem tractable. However, in practical numerical test...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
The optimal control problem including random variables is difficult to solve. Existing methods typically rely on defining explicit decision functions to make the problem tractable. However, in practical numerical testing, we observed that some strongly coupled constraints, such as energy storage level limits, will impose strict restrictions on these simplified decision functions, potentially leading to significantly suboptimal solutions. Motivated by these challenges, this paper proposes a multi-stage robust implicit decision rule for the scheduling problem of energy storage systems. The main idea is to find an explicitly feasible decision function space to guarantee the multi-stage operating feasibility. When random variables are observed, decisions are adaptively optimized within the feasible decision space by solving a straightforward mathematical programming. Explicit decision functions are not required, ultimately enhancing the feasibility and optimality of the stochastic optimization for energy storage systems. Numerical tests are implemented on a real-world microgrid, verifying the effectiveness of the proposed method.
This project will be focused on the effect of private level solar systems on the EDL grid, specifically on the distribution part of the entire EDL network. In order to show the said effects of the integration of solar...
详细信息
Considering the mutual coupling of harmonic in the railway static power conditioner and the impact of different control links on it, a method for establishing the small-signal impedance model of the AC side of the rai...
详细信息
Article propose a hybrid technology of power supply in the electrical interlocking systems development for railway stations. The main feed input is proposed to be carried out from renewable energy sources. Such source...
详细信息
This article presents a mathematical model to find the optimal size of solar Photovoltaics (PVs) and Battery Energy Storage Systems (BESSs) within the distinctive framework of a Renewable Energy Community (REC) with e...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
This article presents a mathematical model to find the optimal size of solar Photovoltaics (PVs) and Battery Energy Storage Systems (BESSs) within the distinctive framework of a Renewable Energy Community (REC) with energy exchanges among PV+BESS system and participants. Our optimization considers dynamic factors, such as electricity pricing and financial aspects including capital investment and operational costs of PV-BESS systems. The replacement costs and efficiencies associated with charging and discharging BESS units are also considered. Mixed Integer Non-Linear Programming (MINLP) is employed to maximize the Net Profit (NP) of the REC. Additionally, we introduce an individual marginal contribution method to allocate incentives among REC participants equitably. This article provides practical insights for Technical Facilitators (TFs) to guide them in selecting the most suitable system size for their energy requirements in the REC. To show real-world applicability, we present the case study of a REC in Roseto Valfortore, a small town in the Province of Foggia, Italy.
The dynamic work environments and workloads lead to uncertainty in disassembly planning of EOL products. Industry 5.0 centers on humans and is driving a new industrial revolution by focusing on smart manufacturing, wh...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
The dynamic work environments and workloads lead to uncertainty in disassembly planning of EOL products. Industry 5.0 centers on humans and is driving a new industrial revolution by focusing on smart manufacturing, which enhances the adaptation of the disassembly process to uncertainty through the flexible scheduling of humans and robots in the HumanCyber-Physical Systems (HCPS). In this study, we present a human-robot interactive disassembly framework for HCPS tailored to recognize and manage uncertain conditions within EOL products. A part damage degree recognition model is trained by combining migration learning and the VGG16 model to achieve online recognition of the uncertain situation of the disassembled object. Fuzzy evaluation indexes of faulty part disassemblability are constructed, and an optimization model for human-robot collaborative disassembly, considering the uncertainty of products, is developed by taking into account the complexity of the disassembly task and the operator's degree of human fatigue. An improved genetic optimization algorithm is applied to obtain an optimal disassembly sequence with humanrobot task allocation. A case study illustrates the feasibility of the proposed method.
Aiming at the problems that the traditional feeder automation (FA) needs to reclose multiple times when dealing with permanent faults, the processing speed is slow and it cannot deal with ground faults, an adaptive in...
详细信息
ISBN:
(纸本)9798350350258;9798350350241
Aiming at the problems that the traditional feeder automation (FA) needs to reclose multiple times when dealing with permanent faults, the processing speed is slow and it cannot deal with ground faults, an adaptive intelligent local feeder automation strategy is proposed. In this strategy, the sectionalizing switches and tie switches are all replaced with primary and secondary integrated circuit breakers, the function of disconnecting the segment switch when no voltage is detected is cancelled, the X time limit and Y time limit are optimized, and acceleration protection is started when detecting voltage and fault. When voltage is detected and disappears again within a short period of time, the switch is opened and reversely locked. Compared with the original strategy, the proposed method only needs one reclosing operation to complete the fault processing, which significantly decrease the fault processing time and has the ability to deal with both short circuit faults and ground faults. Then the action logic of the adaptive intelligent local feeder automation for short circuit fault and ground fault is given, and the feasibility of the strategy is verified. Finally, the adaptive intelligent local feeder automation strategy proposed in this paper is applied to an actual distribution network, and the practical application effect of the method is analyzed.
暂无评论