In this paper, the multi-objective optimal power flow (MOOPF) problem optimization objectives focus on four optimization objectives: generation cost, emission, real power loss and voltage deviation (VD). Three renewable energy sources with successful industrial applications, including wind energy, solar energy, and tidal energy are introduced. Renewable energy supply is uncertain, so Weibull distribution probability, lognormal probability and Gumbel probability are used to calculate the instability and intermittency of wind energy, solar energy and tidal energy, respectively. The inclusion of four energy supplies on the IEEE-30 test system and the consideration of renewable energy reserves and penalty cost calculation improve the realism of the model. In order to obtain the control parameters that minimize the four optimization objectives, a named multi-objective pathfinder algorithm (MOPFA) based on elite dominance and crowding distance was proposed to solve this multi-objective optimization problem. Simulation results show the feasibility of the model, and MOPFA can get more evenly distributed Pareto front and provide more diverse solutions. A compromise solution was selected by the fuzzy decision system. Comparison with the recently published literature also shows that the proposed model can effectively reduce emissions and other indicators. In addition, the statistical test results show that MOPFA's multi-objective optimization performance ranks first. In solving this complex optimization problem, results show the MOPFA is superior to other multi-objective algorithms in optimization accuracy and speed.

The job-shop scheduling problem is one of the well-known hardest combinatorial optimization problems. The problem has captured the interest of a significant number of researchers, but no efficient solution algorithm has been found yet for solving it to optimality in polynomial time. In this paper, a hybrid social-spider optimization algorithm with differential mutation operator is presented to solve the job-shop scheduling problem. To improve the exploration capabilities of the social spider optimization algorithm (SSO), we incorporate the DM operator (a mutation operator taken from the deferential evolutionary (DE) algorithm) into the framework of the female cooperative operator. The experimental results show that the proposed method effectiveness in solving job-shop scheduling compared to other optimization algorithms in the literature.

Introduction: Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. However, the ELM also has some shortcomings, such as structure selection, overfitting and low generalization performance.Methods: This article a new functional neuron (FN) model is proposed, we takes functional neurons as the basic unit, and uses functional equation solving theory to guide the modeling process of FELM, a new functional extreme learning machine (FELM) model theory is proposed.Results: The FELM implements learning by adjusting the coefficients of the basis function in neurons. At the same time, a simple, iterative-free and high-precision fast parameter learning algorithm is proposed.Discussion: The standard data sets UCI and StatLib are selected for regression problems, and compared with the ELM, support vector machine (SVM) and other algorithms, the experimental results show that the FELM achieves better performance.