No abstract

Mayfly algorithm is a new intelligent optimization algorithm with unique optimization capabilities recently proposed. It has strong research value, but there are also insufficient explorations, and it is easy to fall into the problem of local optimization. This paper aims to improve the optimization performance of the mayfly algorithm and explore its application value in practical engineering optimization problems. An improved mayfly algorithm based on the median position of the group is proposed. In its velocity update, the median position of the group is introduced with emphasis, and a non-linear gravity coefficient is introduced at the same time. Through the benchmark test function, its superiority in exploitation, convergence speed and accuracy and the improvement of exploration are verified. At the same time, the simulation model of the hydro-turbine governor using MATLAB/Simulink is established, and 10% frequency disturbance experiments of this model are carried out separately in two typical working conditions. The experiments results show that the optimal ITAE index value of the system obtained by the improved mayfly algorithm is smaller, and 16.5 and 18.1 iterations to complete on average. In addition, the experiments results reveal that the PID parameters optimized by the improved mayfly algorithm can make the dynamic performance of the regulation system better than other popular swarm intelligence algorithms, where the overshoot decreased by more than 3.1%, and the adjustment time also decreased in different degrees. The proposal of the median position of the group provides a new idea for the improvement of the swarm intelligence optimization algorithm. Meanwhile, a new effective method for optimizing the PID parameters of the hydro-turbine governor has been found.

In this paper, the downlink packet scheduling problem for cellular networks is modeled, which jointly optimizes throughput, fairness and packet drop rate. Two genie-aided heuristic search methods are employed to explore the solution space. A deep reinforcement learning (DRL) framework with A2C algorithm is proposed for the optimization problem. Several methods have been utilized in the framework to improve the sampling and training efficiency and to adapt the algorithm to a specific scheduling problem. Numerical results show that DRL outperforms the baseline algorithm and achieves similar performance as genie-aided methods without using the future information.

Electronic nose (E-nose) systems have a good effect on the identification of distinct odours. However, the properties of chemical gas sensors indicate that ageing, poisoning, fluctuation of environmental conditions (moisture, temperature, etc.) and a lack of fabrication repeatability, etc. have a large impact on the sensitivity and accuracy of sensors, which leads to sensor data drift. Although previous studies have indicated the feasibility and validity of deep learning in drift compensation of gas sensor data, the actual performances of these deep learning models are less impressive compared with some existing methods. Thus, we intend to further explore a novel deep learning model for drift compensation for E-noses. In this paper, we investigate the drift compensation effect of E-nose data based on a deep belief network (DBN) and constructed a Gaussian deep belief classification network (GDBCN) model by cascading a Gaussian-Bernoulli restricted Boltzmann machines based DBN with a softmax classifier layer to compensate for sensor drift at the decision level. The merits of our method are as follows: 1) it is a unified classification model for drift auto-compensation at the decision level rather than a feature extractor; 2) it couples unsupervised and supervised techniques by modelling the intrinsic distribution of the data from different domains in an unsupervised manner and fine-tunes the model parameters by leveraging the label information of the source domain; 3) the supervised fine-tuning process for the coupled GDBCN model fits well with the nature of the supervised task and guarantees that the parameters of the DBN will be useful for classification; 4) the GDBCN model is a classification model and thus automatically compensates for drift without manually setting specific model rules for domain alignment before classification. Experimental results on real sensor datasets demonstrate the effectiveness and superiority compared with several existing control methods.

No abstract