• Energy Research

Nowadays, the environmental pollution and degradation in China has become a serious problem with the rapid development of Chinese heavy industry and increased energy generation. With sustainable development being the key to solving these problems, it is necessary to develop proper techniques for monitoring environmental quality. Compared to traditional environment monitoring methods utilizing expensive and complex instruments, we recognized that social media analysis is an efficient and feasible alternative to achieve this goal with the phenomenon that a growing number of people post their comments and feelings about their living environment on social media, such as blogs and personal websites. In this paper, we self-defined a term called the Environmental Quality Index (EQI) to measure and represent people’s overall attitude and sentiment towards an area’s environmental quality at a specific time; it includes not only metrics for water and food quality but also people’s feelings about air pollution. In the experiment, a high sentiment analysis and classification precision of 85.67% was obtained utilizing the support vector machine algorithm, and we calculated and analyzed the EQI for 27 provinces in China using the text data related to the environment from the Chinese Sina micro-blog and Baidu Tieba collected from January 2015 to June 2016. By comparing our results to with the data from the Chinese Academy of Sciences (CAS), we showed that the environment evaluation model we constructed and the method we proposed are feasible and effective.

Abstract This paper presents a multi agent-based simulation framework for modeling spatial distribution of plug-in hybrid electric vehicle ownership at local residential level, discovering “plug-in hybrid electric vehicle hot zones” where ownership may quickly increase in the near future, and estimating the impacts of the increasing plug-in hybrid electric vehicle ownership on the local electric distribution network with different charging strategies. We use Knox County, Tennessee as a case study to highlight the simulation results of the agent-based simulation framework.

Oil is the primary source of energy, therefore, oil consumption forecasting is essential for the necessary economic and social plans. This paper presents an alternative time series prediction method for oil consumption based on a modified Adaptive Neuro-Fuzzy Inference System (ANFIS) model using the Multi-verse Optimizer algorithm (MVO). MVO is applied to find the optimal parameters of the ANFIS. Then, the hybrid method, namely MVO-ANFIS, is employed to forecast oil consumption. To evaluate the performance of the MVO-ANFIS model, a dataset of two different countries was used and compared with several forecasting models. The evaluation results show the superiority of the MVO-ANFIS model over other models. Moreover, the proposed method constitutes an accurate tool that effectively improved the solution of time series prediction problems.