Search

Stock price predict is a challenging problem because stock data has the characteristics of high noise, dynamic, nonlinear and non-parametric. In this study, we proposed a new stock price forecasting method using autoregressive integrated moving average (ARIMA) model and gated recurrent unit (GRU) network. Firstly, the stock sequence is processed by the differential operation to stabilize the stock sequence. Secondly, the residual of each stock sequence is obtained by using the ARIMA model. Thirdly, according to the prespecified threshold of residual, each stock sequence is divided into training sets which are of different sizes. Finally, the GRU network is used to predict stocks price. The experimental results show that the accuracy of our method for predicting stocks price is better than that of recurrent neural networks, long-short term memory and gated recurrent unit.

The National Natural Science Foundation, China (Grant No.: U1137605), the Collaborative Innovation Center of Research and Development of Renewable Energy in the southwest area in China (No.: 05300205020516009), the Project on Co-establishing China-Laos Joint Lab for Renewable Energy (No.: 2015DFA60120), and UOW VC Postdoctoral Fellowship.

The aim of this paper is to optimize the thermal performance (system output energy, thermal efficiency, and heat loss of cavity absorber) of parabolic trough solar collector (PTC) systems in order to improve its thermal performance, based on the genetic algorithm-back propagation (GA-BP) neural network model. There are a number of undefined problems, fuzzy or incomplete information and a complex thermal performance of the PTC systems. Therefore, the thermal performance prediction of the PTC systems based on GA-BP neural network model was developed. Subsequently, the metrics performances have been adopted to comprehensively understand the algorithm and evaluate the prediction accuracy. Results revealed that the GA-BP neural network model can be successfully used to predict the complex nonlinear relationship between the input variables and thermal performance of the PTC systems. The cosine effect has a great influence on the thermal performance; thereby the geometrical structure of the PTC systems w...

To expand the use of wind energy, this paper proposed an off-grid ice storage system driven by distributed wind energy using ice storage to partly replace batteries with wind-electric-cold conversion. The current research aimed to achieve stable and efficient conversion of wind-electric-cold through control method. A system energy transfer model was established to study the energy utilizing efficiencies between the variable speed compressor direct drive mode and the battery floating charge mode under different wind conditions. An optimized variable step-size duty cycle maximum power point tracking (MPPT) algorithm based on the system impedance variation was proposed, then the average wind-electric conversion efficiency increased from 31.6% to 40.58%. Mode-switching control based on the parameters of the wind condition definition was designed to improve electric-cold conversion efficiency to 205.8% on the premise of reducing the battery charge and discharge loss by switching the battery on or off in advance. The superiority of the control method was verified by experiments, finally, the system energy efficiency ratio (EER) reached 0.59 in the case of continuous and stable operation under outdoor wind conditions.

A theoretical analytical method for optical properties of cavity absorber was proposed in this paper and the optical design software TracePro was used to analyze the optical properties of triangular cavity absorber. It was found that the optimal optical properties could be achieved with appropriate aperture width, depth-to-width ratio, and offset distance from focus of triangular cavity absorber. Based on the results of orthogonal experiment, the optimized triangular cavity absorber was designed. Results showed that the standard deviation of irradiance and optical efficiency of optimized designed cavity absorber were 30528 W/m2and 89.23%, respectively. Therefore, this study could offer some valuable references for designing the parabolic trough solar concentrator in the future.