With the rapid popularization and development of renewable energy, solar photovoltaic power generation systems have become an important energy choice. Convolutional neural network (CNN) models have been widely used in photovoltaic power forecasting, with research focused on problems such as long training times, forecasting accuracy and insufficient speed, etc. Using the advantages of swarm intelligence algorithms such as global optimization, strong adaptability and fast convergence, the improved Aquila optimization algorithm (AO) is used to optimize the structure of neural networks, and the optimal solution is chosen as the structure of neural networks used for subsequent prediction. However, its performance in processing sequence data with time characteristics is not good, so this paper introduces a Long Short-Term Memory (LSTM) neural network which has obvious advantages in time-series analysis. The Cauchy variational strategy is used to improve the model, and then the improved Aquila optimization algorithm (IAO) is used to optimize the parameters of the LSTM neural network to establish a model for predicting the actual photovoltaic power. The experimental results show that the proposed IAO-LSTM photovoltaic power prediction model has less error, and its overall quality and performance are significantly improved compared with the previously proposed AO-CNN model.

This paper presents the simulation and hardware implementation of a hill-climbing (HC) modified fuzzy-logic (FL) maximum power point tracking (MPPT) control scheme used in photovoltaic (PV) power systems with the direct control method. The conventional HC method is used to improve the FL search method and eliminate their drawbacks. The main difference of the proposed method to the existing MPPT control method includes that it offers fast and accurate tracking to the maximum power point under uniform radiation or partial shading conditions as compared to the conventional FL method, and it eliminates the proportional-integral control loop. Contributions are made in several aspects such as converter design, simulation, controller programming, and experimental setup. Simulation and experimentation results are provided to demonstrate the validity of the proposed hill-climbing modified fuzzy-logic controller.

Environmental pollution and greenhouse gas emissions are becoming significant environmental issues in China, thus the sustainable development and revival of the country is impossible using the conventional path of encouraging economic growth at the expense of the environment. In response to the global warming, the prices of the traditional energy rise considerably, and a series of environmental problems, China must improve its own mode of economic development. Hundreds of Chinese cities have billions of square meters of buildings and most industry and the annual energy demand is an astronomical figure. China’s government is facing increasing pressure in the low carbon international backdrop, and the low carbon city becomes the inevitable developmental direction of Chinese city in the foreseeable future. The description is first centered on energy structure/energy consumption per unit/urbanized status, and urban energy consumption status, and then concerned with the efforts and measures of Chinese government, to realize the energy saving. Finally, we present the developmental prospect and barriers and the promotion measures related to the low carbon city under the government policy, financial incentives and funding supports, etc.

It is well known that the fixed pitch vertical axis wind turbine (FP-VAWT) has some disadvantages such as the low start-up torque and inefficient output efficiency. In this paper, the variable pitch vertical axis wind turbine (VP-VAWT) is analyzed to improve the output characteristics of FP-VAWT by discussing the force of the six blade H type vertical axis wind turbine (VAWT) under the stationary and rotating conditions using built the H-type VAWT model. First, the force of single blade at variable pitch and fixed pitch is analyzed, respectively. Then, the resultant force of six blades at different pitch is gained. Finally, a variable pitch control method based on a six blade H type VP-VAWT is proposed, moreover, the technical analysis and simulation results validate that the variable pitch method can improve the start-up torque of VAWT, and increase the utilization efficiency of wind energy, and reduce the blade oscillation, as comparable with that of FP-VAWT.

In this paper, a novel particle swarm optimization maximum power point tracking (MPPT) control method is presented to gain the maximum power point of photovoltaic (PV) power, which is based on the direct current voltage superposition principle to predict the output characteristic of a PV array at partial shading. The proposed control method conveniently can be used in the real-time MPPT control strategy for large-scale PV systems, and with the implementation of the collect circuit it is easy to gain the global peak of multiple PV arrays, thereby resulting in lower cost and higher overall efficiency. The proposed method is proved by using simulation results.