Multi-objective power scheduling (MOPS) aims to address the simultaneous minimization of economic costs and different types of environmental emissions during electricity generation. Recognizing it as an NP-hard problem, this article proposes a novel multi-agent deep reinforcement learning (MADRL)-based optimization algorithm. Within a custom multi-agent simulation environment, representing power-generating units as collaborative types of reinforcement learning (RL) agents, the MOPS problem is decomposed into sequential Markov decision processes (MDPs). The MDPs are then utilized for training an MADRL model, which subsequently offers the optimal solution to the optimization problem. The practical viability of the proposed method is evaluated across several experimental test systems consisting of up to 100 units featuring bi-objective and tri-objective problems. The results demonstrate that the proposed MADRL algorithm has better performance compared to established methods, such as teaching learning-based optimization (TLBO), real coded grey wolf optimization (RCGWO), evolutionary algorithm based on decomposition (EAD), non-dominated sorting algorithm II (NSGA-II), and non-dominated sorting algorithm III (NSGA-III).

The transportation sector is recognized as one of the largest contributors to the problems of global warming and environmental pollution, and is responsible for a great deal of global energy consumption, which is heavily dependent upon scarce crude oil reserves. Different countries have adopted promotional policies to replace conventional internal combustion engine vehicles with electric vehicles as a means of mitigating global warming. Nevertheless, the current market share of eco-friendly vehicles remains stagnant in many parts of the world. This study aims to investigate the impact and relative importance of financial, technical, and political measures on the market penetration of electric vehicles using an agent-based simulation. More specifically, a series of agent-based simulation experiments is carried out following the statistical experimental design scheme to systematically assess the diffusion of electric vehicles. Affected by various factors and measures, the choice behavior of individual agents is modeled with a multinomial logit utility function of experimental factors. The simulated data are analyzed using different analysis methods, including full factorial analysis, response surface methodology, and support vector machine, in order to scrutinize the effects of different measures. It is advocated that factors affecting the choice of vehicle by individuals, including two-way interactions among various measures as well as policy measures such as purchase subsidies and tax breaks, have more significant effects on the widespread adoption of electric vehicles than do technical improvements in terms of battery charging times and driving mileage. This implies that the adoption of such measures needs to be carefully designed in order to account for potential interactions among individual measures as well as their main effects on the diffusion of electric vehicles.

Brain tumors, whether benign or malignant, present a complex and multifaceted challenge in healthcare, affecting individuals across various age groups. Predicting the vulnerability of brain tumors using health risk factors and symptoms is crucial, yet there have been limited research studies, particularly those integrating artificial intelligence (AI) technology. This research explores machine learning models such as support vector machines (SVMs), multi-layer perceptrons (MLPs), and logistic regression (LR) for the early detection of brain tumors. Evaluation metrics, including accuracy, precision, recall, and F1-score, are employed to assess model performance. The results indicate that the SVM outperforms other models, providing a robust foundation for predictive accuracy. To enhance accessibility and usability, the research also integrates these models into a mobile application predictor. The application is beneficial for assisting individuals in early detection by identifying potential risk factors and symptoms that may lead to a brain tumor. In conclusion, the integration of machine learning through a mobile application represents a transformative approach to personalized healthcare. By empowering individuals with cutting-edge technology, this research strives to enhance early detection and decision-making regarding potential brain tumor risks and symptoms, ultimately contributing to improved patient outcomes and quality of life.