In recent years, due to the wide utilization of direct current (DC) power sources, such as solar photovoltaic (PV), fuel cells, different DC loads, high-level integration of different energy storage systems such as batteries, supercapacitors, DC microgrids have been gaining more importance. Furthermore, unlike conventional AC systems, DC microgrids do not have issues such as synchronization, harmonics, reactive power control, and frequency control. However, the incorporation of different distributed generators, such as PV, wind, fuel cell, loads, and energy storage devices in the common DC bus complicates the control of DC bus voltage as well as the power-sharing. In order to ensure the secure and safe operation of DC microgrids, different control techniques, such as centralized, decentralized, distributed, multilevel, and hierarchical control, are presented. The optimal planning of DC microgrids has an impact on operation and control algorithms; thus, coordination among them is required. A detailed review of the planning, operation, and control of DC microgrids is missing in the existing literature. Thus, this article documents developments in the planning, operation, and control of DC microgrids covered in research in the past 15 years. DC microgrid planning, operation, and control challenges and opportunities are discussed. Different planning, control, and operation methods are well documented with their advantages and disadvantages to provide an excellent foundation for industry personnel and researchers. Power-sharing and energy management operation, control, and planning issues are summarized for both grid-connected and islanded DC microgrids. Also, key research areas in DC microgrid planning, operation, and control are identified to adopt cutting-edge technologies. This review explicitly helps readers understand existing developments on DC microgrid planning, operation, and control as well as identify the need for additional research in order to further contribute to the topic.

The utilization of renewable energy sources (RESs) has become significant throughout the world, especially over the last two decades. Although high-level RESs penetration reduces negative environmental impact compared to conventional fossil fuel-based energy generation, control issues become more complex as the system inertia is significantly decreased due to the absence of conventional synchronous generators. Some other technical issues, high uncertainties, low fault ride through capability, high fault current, low generation reserve, and low power quality, arise due to RESs integration. Renewable energy like solar and wind are highly uncertain due to the intermittent nature of wind and sunlight. Cutting edge technologies including different control strategies, optimization techniques, energy storage devices, and fault current limiters are employed to handle those issues. This paper summarizes several challenges in the integration process of high-level RESs to the existing grid. The respective solutions to each challenge are presented and discussed. A comprehensive list of challenges and solutions, for both wind and solar energy integration cases, are well documented. Finally, the future recommendations are provided to solve the several problems of renewable energy integration which could be key research areas for the industry personnel and researchers.

A better understanding of injury severity risk factors is fundamental to improving crash prediction and effective implementation of appropriate mitigation strategies. Traditional statistical models widely used in this regard have predefined correlation and intrinsic assumptions, which, if flouted, may yield biased predictions. The present study investigates the possibility of using the eXtreme Gradient Boosting (XGBoost) model compared with few traditional machine learning algorithms (logistic regression, random forest, and decision tree) for crash injury severity analysis. The data used in this study was obtained from the traffic safety department, ministry of transport (MOT) at Riyadh, KSA, and contains 13,546 motor vehicle collisions along 15 rural highways reported between January 2017 to December 2019. Empirical results obtained using k-fold (k = 10) for various performance metrics showed that the XGBoost technique outperformed other models in terms of the collective predictive performance as well as injury severity individual class accuracies. XGBoost feature importance analysis indicated that collision type, weather status, road surface conditions, on-site damage type, lighting conditions, and vehicle type are the few sensitive variables in predicting the crash injury severity outcome. Finally, a comparative analysis of XGBoost based on different performance statistics showed that our model outperformed most previous studies.

The rapid growth of transportation sector and related emissions are attracting the attention of policymakers to ensure environmental sustainability. Therefore, the deriving factors of transport emissions are extremely important to comprehend. The role of electric vehicles is imperative amid rising transport emissions. Electric vehicles pave the way towards a low-carbon economy and sustainable environment. Successful deployment of electric vehicles relies heavily on energy consumption models that can predict energy consumption efficiently and reliably. Improving electric vehicles’ energy consumption efficiency will significantly help to alleviate driver anxiety and provide an essential framework for operation, planning, and management of the charging infrastructure. To tackle the challenge of electric vehicles’ energy consumption prediction, this study aims to employ advanced machine learning models, extreme gradient boosting, and light gradient boosting machine to compare with traditional machine learning models, multiple linear regression, and artificial neural network. Electric vehicles energy consumption data in the analysis were collected in Aichi Prefecture, Japan. To evaluate the performance of the prediction models, three evaluation metrics were used; coefficient of determination ( R²), root mean square error, and mean absolute error. The prediction outcome exhibits that the extreme gradient boosting and light gradient boosting machine provided better and robust results compared to multiple linear regression and artificial neural network. The models based on extreme gradient boosting and light gradient boosting machine yielded higher values of R², lower mean absolute error, and root mean square error values have proven to be more accurate. However, the results demonstrated that the light gradient boosting machine is outperformed the extreme gradient boosting model. A detailed feature important analysis was carried out to demonstrate the impact and relative influence of different input variables on electric vehicles energy consumption prediction. The results imply that an advanced machine learning model can enhance the prediction performance of electric vehicles energy consumption.

The potential effects of autonomous vehicles (AVs) on greenhouse gas (GHG) emissions are uncertain, although numerous studies have been conducted to evaluate the impact. This paper aims to synthesize and review all the literature regarding the topic in a systematic manner to eliminate the bias and provide an overall insight, while incorporating some statistical analysis to provide an interval estimate of these studies. This paper addressed the effect of the positive and negative impacts reported in the literature in two categories of AVs: partial automation and full automation. The positive impacts represented in AVs’ possibility to reduce GHG emission can be attributed to some factors, including eco-driving, eco traffic signal, platooning, and less hunting for parking. The increase in vehicle mile travel (VMT) due to (i) modal shift to AVs by captive passengers, including elderly and disabled people and (ii) easier travel compared to other modes will contribute to raising the GHG emissions. The result shows that eco-driving and platooning have the most significant contribution to reducing GHG emissions by 35%. On the other side, easier travel and faster travel significantly contribute to the increase of GHG emissions by 41.24%. Study findings reveal that the positive emission changes may not be realized at a lower AV penetration rate, where the maximum emission reduction might take place within 60–80% of AV penetration into the network.