Search

Unmanned Aerial Vehicle (UAV) inspection has gradually replaced manual inspection of transmission tower, which produces many images. While it is laborious and time-consuming to manually analyze these images, there are also challenges in automatically detecting small-size defective components such as bolts in transmission tower images, due to problems including complex background, small size, and many similar objects of bolts. In this paper, by virtue of multi-scale features and context information, we propose a deep neural network named Camp-Net (Context Information and Multi-Scale Pyramid Network) to identify bolts defect in transmission tower images. First, multi-scale feature fusion combines deep features and shallow features in convolutional networks to detect small-size bolts. Second, context information fusion puts the information around bolts into the detection network to remove the disturbance of complex background and similar objects. An image dataset containing defective bolts and normal bolts is constructed for model training and testing. Experimental results show that bolts with loose pins and bolts without pins among fittings in transmission tower can be accurately identified with the proposed model. The Average Precision (AP) of defective bolts detection of this model can be 11.4% higher than that of the commonly used high performance model, Faster R-CNN. [ABSTRACT FROM AUTHOR]

As a networked cyber physical system, smart grid plays an important role in improving energy efficiency, which has higher prediction accuracy requirement for load forecasting to realize intelligent dispatching. The existing works of load forecasting have considered the external factors to improve prediction accuracy, but ignored their varying and different impacts in different time. In order to solve this problem, firstly, a new method is designed to select external meteorological factors and construct new features to deal with the different impacts of external factors in different seasons. Secondly, a fuzzy processing method of calendar factor is proposed to explore the varying impact of the calendar factor in the holiday period. Finally, our proposed method is combined with LSTM and other three typical machine learning models, and experiments are performed on a load data set from the real power system. The results show that our proposed method can improve the prediction accuracy of the typical machine learning based models. Especially for LSTM, the MAPEs reach to 3.8% and 3.1% in winter and summer, with the improvements of 0.6% and 0.3% respectively. [ABSTRACT FROM AUTHOR]

Cyberattack emerges as a critical concern in Internet-of-Things integrated power systems. Cybersecurity capabilities of power systems rely on a deep understanding of potential cyberattacks for identifying and protecting against cyber vulnerabilities. The common assumption of system network information in most existing works is suspicious, which fails to hold in practical fields. This paper proposes a novel data-driven false data injection attack method, where only easily accessible measurement data are required, i.e., power injections at buses, flows of lines and the tie line information (connection relationship and power measurement data). In the proposed method, generative adversarial network (GAN) is adopted to extract the physical model using historical measurement data, and a self-attention mechanism is integrated to further capture the power flow laws in the data. After offline training, the effective false data can be constructed in a timely fashion without system network information. The effectiveness of the proposed attack method is validated using the IEEE14 and IEEE118 systems, in which the constructed false data injection attack can evade the system residual detection with an average success rate over 90% under different levels of measuring errors. [ABSTRACT FROM AUTHOR]

Probabilistic solar irradiance forecasting has received widespread attention in recent years, as it provides more uncertainty information for the future photovoltaic generation. In this study, a hybrid probabilistic solar irradiance prediction method is proposed, which combines a deep recurrent neural network and residual modeling. Specifically, the long short‐term memory‐based point prediction using historical records and related features is applied to obtain deterministic forecasts. Next, these deterministic forecasts are employed as inputs to estimate the residual distributions. Furthermore, maximum likelihood estimation is utilized to compute the parameters of the residual distribution. Finally, the point prediction and residual distribution jointly generate the final probabilistic forecasting results. Compared with other deterministic and probabilistic forecasting models, the proposed method yields promising results on a publicly available dataset. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

This paper proposes an electric business centre location model solved by centre–decentre quantum particle swarm optimization (CDQPSO). Firstly, a location model is built taking real factors into accounts such as the cost of business centres and consumers, the competitive relationship between newly built and existing ones, and their service qualities. Secondly, in order to solve the location model, a CDQPSO algorithm is proposed by the combination of centralized–decentralized learning and the motion mode of the quantum bound state particle. Benchmark experiments on the proposed CDQPSO and existing PSO algorithms indicate that the proposed algorithm has better performance. Finally, CDQPSO is applied to solve the locations of business centres. Compared with the existing methods, the new-built business centre of our proposed method can provide consumers with higher transportation convenience and service quality. Moreover, the power company can reduce the construction cost of business centres and improve social benefits. [ABSTRACT FROM AUTHOR]

An accurate, real-time estimation of the states of a power distribution system is highly desirable but hard to achieve because of the complexity of the network and the relative inefficiency of the measuring system. To increase the efficiency, this paper analyzes the mathematical relationship between the measurement errors and estimation errors of the state vector using the classic weighted least square method. Then a heuristic algorithm is proposed to improve the accuracy by optimizing the deployment of the real-time measuring points, which is based on the deterministic factors of the measuring points/branches over the system state. The basic implementation starts with an initial measurement set and replaces the least important branches in the set with the most important branches outside the set using iterative optimization. The algorithm was tested in the IEEE 14-bus and 33-bus distribution systems and achieved 50% increase in accuracy at much lower computational cost compared with exhaustive search. Moreover, the proposed algorithm has also been compared with representative and widely used evolution algorithms such as particle swarm optimization and quantum-behaved particle swarm optimization. This comparison shows that our method can achieve stable and comparable accuracy with a speed at least 10 times higher. The performance of our method can be even better with increasing network size. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

The establishment of a multistage multiobjective substation siting and sizing planning model, taking into account various constraints such as load flow constraint, maximum capacity constraint, and maximum power supply radius constraint makes possible substation planning between multiple years to be adjusted to achieve an optimal overall plan. Through multiple optimization objectives, it is possible to prevent the plan from becoming useless because of excessive changes in power supply affiliation during the multistage optimization process. To find the optimal solution for the model, a repair operator is proposed and used with an improved multiobjective genetic algorithm to repair the decision variables for each chromosome corresponding to one stage so as to satisfy the constraints while ensuring that population diversity evolves heuristically to the optimal solution. Moreover, a tournament selection operator based on crowding distance is adopted, which can prevent the algorithm from premature convergence and make populations trend to the Pareto frontier. Experimental results show that the proposed model and algorithm can efficiently solve the issue of rolling planning between multiple target years and achieve a joint optimal planning. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

With the development of 5G and the Internet of Things (IoT), mobile terminals are widely used in various applications under multicast scenarios. However, due to the limited computation resources of mobile terminals, reducing the computation cost of members in group key distribution processes of dynamic groups has become an important issue. In this paper, we propose a computation-efficient group key distribution (CEGKD) protocol. First, an improved secret sharing scheme is proposed to construct faster encryption and decryption algorithms. Second, the tree structure of logical key hierarchy (LKH) is employed to implement a simple and effective key-numbering method. Theoretical analysis is given to prove that the proposed protocol meets forward security and backward security. In addition, the experiment results show that the computation cost of CEGKD on the member side is reduced by more than 85% compared with that of the LKH scheme. [ABSTRACT FROM AUTHOR]

In a real interactive service system, a smart meter can only read the total amount of energy consumption rather than analyze the internal load components for users. Nonintrusive load monitoring (NILM), as a vital part of smart power utilization techniques, can provide load disaggregation information, which can be further used for optimal energy use. In our paper, we introduce a new method called linear-chain conditional random fields (CRFs) for NILM and combine two promising features: current signals and real power measurements. The proposed method relaxes the independent assumption and avoids the label bias problem. Case studies on two open datasets showed that the proposed method can efficiently identify multistate appliances and detect appliances that are not easily identified by other models. [ABSTRACT FROM AUTHOR]