Economic Load Dispatch (ELD) is a key issue in power systems and its goal is to achieve minimum economic costs by allocating the output of generator units when satisfying the load demands and the operating constraints. As the dimension of the variables and the constraints increase, the traditional mathematical method is gradually not suitable for the ELD. This paper proposes an Improved Bird Swarm Algorithm (IBSA) to solve the ELD problem of a power system. By introducing the nonlinear cognitive and social coefficients, the proportion of individual learning and social learning of birds can be dynamically adjusted. In addition, the Levy flight strategy is added to the group between producers and beggars to increase the randomness. The performance of IBSA is verified via two systems consisting of 6 and 15 units, respectively, that take into account generation limitation, ramp rate limit, and prohibited operating zones. From the simulation results, the IBSA has shown excellent performance and robustness, which can be considered as a reliable solution for the ELD.

Accurate load forecasting is conducive to the formulation of the power generation plan, lays the foundation for the formulation of quotation, and provides the basis for the power management system and distribution management system. This study aims to propose a high precision load forecasting method. The power load forecasting model, based on the Improved Seagull Optimization Algorithm, which optimizes SVM (ISOA-SVM), is constructed. First, aiming at the problem that the random selection of internal parameters of SVM will affect its performance, the Improved Seagull Optimization Algorithm (ISOA) is used to optimize its parameters. Second, to solve the slow convergence speed of the Seagull Optimization Algorithm (SOA), three strategies are proposed to improve the optimization performance and convergence accuracy of SOA, and an ISOA algorithm with better optimization performance and higher convergence accuracy is proposed. Finally, the load forecasting model based on ISOA-SVM is established by using the Mean Square Error (MSE) as the objective function. Through the example analysis, the prediction performance of the ISOA-SVM is better than the comparison models and has good prediction accuracy and effectiveness. The more accurate load forecasting can provide guidance for power generation and power consumption planning of the power system.

Short-term traffic flow forecasting is the technical basis of the intelligent transportation system (ITS). Higher precision, short-term traffic flow forecasting plays an important role in alleviating road congestion and improving traffic management efficiency. In order to improve the accuracy of short-term traffic flow forecasting, an improved bird swarm optimizer (IBSA) is used to optimize the random parameters of the extreme learning machine (ELM). In addition, the improved bird swarm optimization extreme learning machine (IBSAELM) model is established to predict short-term traffic flow. The main researches in this paper are as follows: (1) The bird swarm optimizer (BSA) is prone to fall into the local optimum, so the distribution mechanism of the BSA optimizer is improved. The first five percent of the particles with better fitness values are selected as producers. The last ten percent of the particles with worse fitness values are selected as beggars. (2) The one-day and two-day traffic flows are predicted by the support vector machine (SVM), particle swarm optimization support vector machine (PSOSVM), bird swarm optimization extreme learning machine (BSAELM) and IBSAELM models, respectively. (3) The prediction results of the models are evaluated. For the one-day traffic flow sequence, the mean absolute percentage error (MAPE) values of the IBSAELM model are smaller than the SVM, PSOSVM and BSAELM models, respectively. The experimental analysis results show that the IBSAELM model proposed in this study can meet the actual engineering requirements.

The recommendation model based on the knowledge graph (KG) alleviates the problem of data sparsity in the recommendation to a certain extent and further improves the accuracy, diversity, and interpretability of recommendations. Therefore, the knowledge graph recommendation model has become a major research topic, and the question of how to utilize the entity and relation information fully and effectively in KG has become the focus of research. This paper proposes a knowledge graph recommendation model based on adversarial training (ATKGRM), which can dynamically and adaptively adjust the knowledge graph aggregation weight based on adversarial training to learn the features of users and items more reasonably. First, the generator adopts a novel long- and short-term interest model to obtain user features and item features and generates a high-quality set of candidate items. Then, the discriminator discriminates candidate items by comparing the user’s scores of positive items, negative items, and candidate items. Finally, experimental studies on five real-world datasets with multiple knowledge graph recommendation models and multiple adversarial training recommendation models prove the effectiveness of our model.

Identification of community structures is essential for characterizing and analyzing complex networks. Having focusing primarily on network topological structures, most existing methods for community detection ignore two types of non-topological relationships among nodes, i.e., pairwise “must-link” constraints among pairs of nodes and labels of nodes, such as functions they may have. Here, we present a novel semi-supervised and active learning method for community detection to integrate these two types of information of a network so as to increase the accuracy of community identification. Our new method will honor the “must-link” relationship without introducing new parameters and is efficient with a guaranteed convergence. An essential component of the method is a linear representation that is particularly suited to an active learning to help select the most critical nodes that impact community discovery. We present results from extensive experiments on synthetic and real networks to show the superior performance of the new methods over the existing approaches.