The forecasting of load is important basic work of power system operation and control. Accurate short-term load probability forecasting is very essential for power grid scheduling. The conventional forecasting methods...
详细信息
ISBN:
(数字)9781728101996
ISBN:
(纸本)9781728102009
The forecasting of load is important basic work of power system operation and control. Accurate short-term load probability forecasting is very essential for power grid scheduling. The conventional forecasting methods are mostly to get deterministic forecasting result. The information derived from a deterministic forecasting model is not comprehensive because the electricity load is highly stochastic. The load probability prediction can get an interval of appropriate size, which provides more information to the power system. This paper proposes a Long Short-term Memory (LSTM)-based load probability forecasting model to obtain the forecasting of the electricity load for each hour of the next week. This model was trained and tested with the collected data set whose resolution was 1 hour. In addition, the model also considers the impact of meteorological factors on the electricity load during construction, so the inputs of the model correspond to the electricity load data and meteorological data for a period of time.
Aiming at the key technical problems of cable tunnel inspection robot, this paper builds the control system of cable tunnel inspection robot based on NVIDIA Jetson TX2 and STM32F407. By designing a motion mechanical s...
详细信息
Aiming at the key technical problems of cable tunnel inspection robot, this paper builds the control system of cable tunnel inspection robot based on NVIDIA Jetson TX2 and STM32F407. By designing a motion mechanical structure to meet the requirements of the inspection robot walking freely on the fixed track of the tunnel, designing a positioning scheme based on Radio Frequency Identification (RFID) to enable the robot to quickly and accurately acquire the location information, and designing a multi-channel audio and video processing scheme to enable the robot to have online diagnosis, video coding, audio coding and decoding and multimedia streaming capabilities. The experimental results confirm the feasibility of the proposed scheme.
As a rapidly developing renewable energy source, effective active power dispatching for wind power has become common. For offshore wind farms with high maintenance costs, balanced fatigue loads among wind turbines nee...
详细信息
As a rapidly developing renewable energy source, effective active power dispatching for wind power has become common. For offshore wind farms with high maintenance costs, balanced fatigue loads among wind turbines need to be considered in order to reduce the number of maintenances. Based on this target, this paper proposes an optimized power distribution function to balance the fatigue difference among wind turbines. At the same time, this paper adopts the structure of the unsupervised multi-agent system (MAS) in the offshore wind farm, the communication between wind turbines is used to complete the allocation of power commands. The simulation results show that the wind farm with MAS structure can effectively deliver the power commands. And the optimized power distribution function can reduce the fatigue difference of the wind turbines after long-term operation.
This paper aims to study video image fusion through two types of image fusion algorithms: pixel level and feature level, which can solve camera shake during video shooting, image blur caused by interference, target oc...
详细信息
ISBN:
(数字)9781728101996
ISBN:
(纸本)9781728102009
This paper aims to study video image fusion through two types of image fusion algorithms: pixel level and feature level, which can solve camera shake during video shooting, image blur caused by interference, target occlusion. Based on the above proposed methods, a video is optimized by wavelet transform fusion algorithm, Laplacian pyramid fusion algorithm and the scale-invariant feature transform (SIFT) fusion algorithm, respectively. Moreover, three indexes are used to evaluate the images obtained by using these two types of fusion algorithms. A human-computer interaction interface is constructed by utilizing MATLAB toolbox, and the simulation of video image fusion is completed in the interface, which proves that the fusion algorithm can achieve a good result than another two algorithms.
Considering the performance of offshore wind turbine often degrades due to dynamic ice load in cold regions, we optimize the pitch controller to minimize the unfavorable influence of the ice load. The design of pitch ...
Considering the performance of offshore wind turbine often degrades due to dynamic ice load in cold regions, we optimize the pitch controller to minimize the unfavorable influence of the ice load. The design of pitch controller is based on the proposed nonlinear models of offshore wind turbine and dynamic ice load. However, on account of the nonlinear system and random wind speed, it is a challenge for pitch control using traditional Proportional-Integral controller to keep the high operating quality. Hence, the optimization based on particle swarm optimization is proposed in this paper, which tunes the parameters of the controller effectively. More importantly, simulation results demonstrate that the proposed optimization performs better in constant generation power and reduction of tower top displacement comparing with the tradition controller.
With the development of microgrid technology, the installed capacity is increasing rapidly. To ensure the economy and reliability of the microgrid integrated with wind, photovoltaic and gas, the installed capacity sho...
详细信息
ISBN:
(数字)9781728101996
ISBN:
(纸本)9781728102009
With the development of microgrid technology, the installed capacity is increasing rapidly. To ensure the economy and reliability of the microgrid integrated with wind, photovoltaic and gas, the installed capacity should be configured rationally. In order to solve the problem of capacity allocation, this paper proposes an optimization model based on game theory, where the relationship among the distributed generations (DGs) and the power supply rules are considered. With particle swarm algorithm, the Nash equilibrium of the game model for the microgrid is worked out, as the reference for the decision-making of DG capacity allocation problem. Last, a case study is analyzed to verify the correction and the optimization of the proposed game model.
Solar energy driven photoelectrochemical(PEC) water splitting is a clean and powerful approach for renewable hydrogen production. The design and construction of metal oxide based nanoarray photoanodes is one of the pr...
详细信息
Solar energy driven photoelectrochemical(PEC) water splitting is a clean and powerful approach for renewable hydrogen production. The design and construction of metal oxide based nanoarray photoanodes is one of the promising strategies to make the continuous breakthroughs in solar to hydrogen conversion efficiency of PEC cells owing to their owned several advantages including enhanced reactive surface at the electrode/electrolyte interface, improved light absorption capability, increased charge separation efficiency and direct electron transport pathways. In this Review, we first introduce the structure,work principle and their relevant efficiency calculations of a PEC cell. We then give a summary of the state-of the-art research in the preparation strategies and growth mechanism for the metal oxide based nanoarrays, and some details about the performances of metal oxide based nanoarray photoanodes for PEC water splitting. Finally, we discuss key aspects which should be addressed in continued work on realizing high-efficiency metal oxide based nanoarray photoanodes for PEC solar water splitting systems.
The interaction between matter and squeezed light has mostly been treated within the approximation that the field-correlation time is small. Methods for treating squeezed light with more general correlations currently...
详细信息
The interaction between matter and squeezed light has mostly been treated within the approximation that the field-correlation time is small. Methods for treating squeezed light with more general correlations currently involve explicitly modeling the systems producing the light. We develop a general purpose input-output theory for a particular form of narrowband squeezed light, a squeezed wave-packet mode, that only concerns the statistics of the squeezed field and the shape of the wave packet. This formalism allows us to derive the input-output relations and the master equation. We also consider detecting the scattered field using photon counting and homodyne measurements, which necessitates the derivation of the stochastic master equation. The non-Markovian nature of the field manifests itself in the master equation as a coupled hierarchy of equations. We illustrate these with consequences for the decay and resonance fluorescence of two-level atoms in the presence of such fields.
暂无评论