Products, research & craft
not portfolio filler.

This paper presents a benchmarking study of metaphor-less metaheuristic algorithms for solving the Traveling Salesman Problem (TSP), a classic NP-hard combinatorial optimization task. Unlike conventional metaheuristics inspired by natural metaphors, metaphor-less algorithms focus purely on mathematical operators to balance exploration and exploitation without reliance on analogies or algorithm specific control parameters. The study evaluates eight such algorithms-including BMR, BWR, Rao-1/2/3, Jaya, and Runge-Kutta optimization on benchmark TSP instances from TSPLIB. Additionally, improved versions of these algorithms using adaptive mutation strategies are proposed and analyzed. Performance is measured in terms of solution quality, convergence rate, stability, and resource efficiency. Experimental results demonstrate that BMR and BWR, especially with enhanced mutation (EM), consistently outperform other methods in accuracy and convergence while maintaining low computational overhead.

Transitioning from fossil fuels to renewable energy sources, more so solar energy, is highly indispensable for meeting the global demand for energy and fighting against climate change. However, intermittency and uncertainty in the solar generation process pose serious challenges to grid integration and energy planning. Supervised learning, which includes Support Vector Machines and neural networks; unsupervised learning, including clustering, LDA; meta-heuristics optimization algorithms like PSO, and GA are very powerful tools. Other couplings also include machine learning and new technologies such as IoT, Quantum Computing, and XAI offering scalable and interpretable solutions for real-time monitoring, material discovery, and grid management. Future directions are geared toward the synergy of ML with quantum computing, hybrid approaches, and cloud-based analytics to drive innovation, reduce costs, and promote the global deployment of solar energy. This review shows the key contribution of ML to the development of solar energy systems toward a sustainable and efficient energy future