CVaR Prediction Model of the Investment Portfolio Based on the Convolutional Neural Network Facilitates the Risk Management of the Financial Market

In summary, firstly, a method for establishing a portfolio model is proposed based on the risk management theory of the financial market. Then, a prediction model for CVaR is established based on the convolutional neural network, and the improved particle swarm algorithm is employed to solve the model. The actual data analysis is implemented to prove the feasibility of CVaR prediction model based on deep learning and particle swarm optimization algorithm in financial market risk management. The test results show that the investment portfolio CVaR prediction model based on the convolutional neural network can obtain the optimal solution in the 18th generation at the fastest after using the improved particle swarm algorithm, which is more effective than the traditional algorithm. The CVaR prediction model of the investment portfolio based on the convolutional neural network facilitates the risk management of the financial market.

Bi-Level Optimization Dispatch of Integrated-Energy Systems With P2G and Carbon Capture

The power-to-gas (P2G) technology transforms the unidirectional coupling of power network and natural gas network into bidirectional coupling, and its operational characteristics provide an effective way for wind and solar energy accommodation. The paper proposes a bi-level optimal dispatch model for the integrated energy system with carbon capture system and P2G facility. The upper model is an optimal allocation model for coal-fired units, and the lower model is an economic dispatch model for the integrated energy system. Moreover, the upper model is solved by transforming the model into a mixed-integer linear programming problem and calling CPLEX, and the lower model is a multi-objective planning problem, which is solved by improving the small-habitat particle swarm algorithm. Finally, the simulation is validated by the MATLAB platform, and the results show that the simultaneous consideration of carbon capture system and P2G facility improves the economics of the integrated energy system and the capacity of wind and solar energy accommodation.

Optimal Allocation of a Hybrid Photovoltaic Biogas Energy System Using Multi-Objective Feasibility Enhanced Particle Swarm Algorithm

This paper aims to investigate a hybrid photovoltaic (PV) biogas on-grid energy system in Al-Ghabawi territory, Amman, Jordan. The system is accomplished by assessing the system’s reliability and economic viability. Realistic hourly measurements of solar irradiance, ambient temperature, municipal solid waste, and load demand in 2020 were obtained from Jordanian governmental entities. This helps in investigating the proposed system on a real megawatt-scale retrofitting power system. Three case scenarios were performed: loss of power supply probability (LPSP) with total net present cost (TNPC), LPSP with an annualized cost of the system (ACS), and TNPC with the index of reliability (IR). Pareto frontiers were obtained using multi-objective feasibility enhanced particle swarm optimization (MOFEPSO) algorithm. The system’s decision variables were the number of PV panels (Npv) and the number of biogas plant working hours per day (tbiogas). Moreover, three non-dominant Pareto frontier solutions are discussed, including reliable, affordable, and best solutions obtained by fuzzy logic. Double-diode (DD) solar PV model was implemented to obtain an accurate sizing of the proposed system. For instance, the best solution of the third case is held at TNPC of 64.504 million USD/yr and IR of 96.048%. These findings were revealed at 33,459 panels and 12.498 h/day. Further, system emissions for each scenario have been tested. Finally, decision makers are invited to adopt to the findings and energy management strategy of this paper to find reliable and cost-effective best solutions.

Optimal Control of Hybrid Energy Storage System of New Energy Power Generation System Based on Improved Particle Swarm Algorithm

In order to ensure the stability and reliability of power supply and realize day and night power generation, wind and solar complementary power generation systems are built in areas with abundant solar and wind energy resources. However, the system investment cost is too high. Because of this, there are wind, light intermittent, and non-intermittent power generation systems. For issues such as stability, an energy storage system needs to be configured to stabilize power fluctuations. This paper aims to study the optimization control of hybrid energy storage system of new energy power generation system based on improved particle swarm algorithm. In this paper, the application of particle swarm algorithm to power system reactive power optimization has been researched in two aspects. Through optimization methods, reasonable adjustment of control variables, full use of equipment resources of the power grid, to improve voltage quality and reduce system operation network to ensure the stability of the voltage system. In addition, this paper selects the IEEE30 node test system and simulation data analysis, takes the hybrid energy storage system as the optimization object, and optimizes the reactive power of the newly improved particle swarm algorithm. The experiments in this paper show that the improved algorithm has a good effect in reactive power optimization, increasing the performance of the hybrid energy storage system by 27.02%. MPSO algorithm is also better than basic PSO algorithm. It can be seen from the figure that in the PSO algorithm, the algorithm basically tends to be stable after more than 40 iterations, and finally the algorithm converges to 0.089.

Software Defect Prediction Based on Hybrid Swarm Intelligence and Deep Learning

In order to improve software quality and testing efficiency, this paper implements the prediction of software defects based on deep learning. According to the respective advantages and disadvantages of the particle swarm algorithm and the wolf swarm algorithm, the two algorithms are mixed to realize the complementary advantages of the algorithms. At the same time, the hybrid algorithm is used in the search of model hyperparameter optimization, the loss function of the model is used as the fitness function, and the collaborative search ability of the swarm intelligence population is used to find the global optimal solution in multiple local solution spaces. Through the analysis of the experimental results of six data sets, compared with the traditional hyperparameter optimization method and a single swarm intelligence algorithm, the model using the hybrid algorithm has higher and better indicators. And, under the processing of the autoencoder, the performance of the model has been further improved.

Analysis of the Distributed Immune Inspection Equipment Sensor Scheduling Model Based on Adaptive Dynamic Probabilistic Particle Swarm Optimization

Based on the analysis of bacterial parasitic behavior and biological immune mechanism, this paper puts forward the basic idea and implementation method of an embedding adaptive dynamic probabilistic parasitic immune mechanism into a particle swarm optimization algorithm and constructs particle swarm optimization based on an adaptive dynamic probabilistic parasitic immune mechanism algorithm. The specific idea is to use the elite learning mechanism for the parasitic group with a strong parasitic ability to improve the ability of the algorithm to jump out of the local extreme value, and the host will generate acquired immunity against the parasitic behavior of the parasitic group to enhance the diversity of the host population’s particles. Parasitic behavior occurs when the number of times reaches a predetermined algebra. In this paper, an example simulation is carried out for the prescheduling and dynamic scheduling of immune inspection. The effectiveness of prescheduling for immune inspection is verified, and the rules constructed by the adaptive dynamic probability particle swarm algorithm and seven commonly used scheduling rules are tested on two common dynamic events of emergency task insertion and subdistributed immune inspection equipment failure. In contrast, the experimental data was analyzed. From the analysis of experimental results, under the indicator of minimum completion time, the overall performance of the adaptive dynamic probability particle swarm optimization algorithm in 20 emergency task insertion instances and 20 subdistributed immune inspection equipment failure instances is better than that of seven scheduling rules. Therefore, in the two dynamic events of emergency task insertion and subdistributed immune inspection equipment failure, the adaptive dynamic probabilistic particle swarm algorithm proposed in this paper can construct effective scheduling rules for the rescheduling of the system when dynamic events occur and the constructed scheduling. The performance of the rules is better than that of the commonly used scheduling rules. Among the commonly used scheduling rules, the performance of the FIFO scheduling rules is also better. In general, the immune inspection scheduling multiagent system in this paper can complete the prescheduling of immune inspection and process dynamic events of the inspection process and realize the prereactive scheduling of the immune inspection process.

Prediction Model of Soil Electrical Conductivity Based on ELM Optimized by Bald Eagle Search Algorithm

Soil electrical conductivity is one of the indispensable and important parameters in fine agriculture management, and a suitable soil electrical conductivity can promote good plant growth. Prediction model of soil electrical conductivity is constructed to effectively obtain the conductivity values of soil, which can provide a reference basis for irrigation and fertilization management and prediction evaluation in fine agriculture. Prediction model of soil electrical conductivity based on extreme learning machine (ELM) optimized by bald eagle search (BES) algorithm is proposed in this paper. In the prediction model, the input weights and bias values of the ELM network were optimized using the BES algorithm, and the performance of the model was evaluated with parameters such as mean square error (MSE), coefficient of determination (R^2). Also, the correlations of parameters such as soil temperature, moisture content, pH, and water potential in the soil conductivity prediction model were determined using the exploratory data analysis (EDA) and HeatMap heat map tools. Finally, the proposed model was compared with back propagation neural network (BP), radial basis function networks (RBF), support vector machine (SVM), gated recurrent neural network (GRNN), long short-term memory (LSTM), particle swarm algorithm (PSO) optimization ELM, genetic algorithm (GA) optimized ELM prediction model. The experimental results showed that MSE, R^2 of the proposed model are 4.09 and 0.941, which are better than the other models. Also the results verified the effectiveness of the proposed method, which is a feasible prediction method to guide the irrigation and fertilization management in fine agriculture, because of its good prediction effect on soil conductivity.

Cloud Computing Task Scheduling Model Based on Improved Whale Optimization Algorithm

The efficiency of task scheduling under cloud computing is related to the effectiveness of users. Aiming at the problems of long scheduling time, high cost consumption, and large virtual machine load in cloud computing task scheduling, an improved scheduling efficiency algorithm (called the improved whale optimization algorithm, referred to as IWC) is proposed. Firstly, a cloud computing task scheduling and distribution model with time, cost, and virtual machines as the main factors is constructed. Secondly, a feasible plan for each whale individual corresponding to cloud computing task scheduling is to find the best whale individual, which is the best feasible plan; in order to better find the optimal individual, we use the inertial weight strategy for the whale optimization algorithm to improve the local search ability and effectively prevent the algorithm from reaching premature convergence; we use the add operator and delete operator to screen individuals after each iteration which is completed and updated to improve the quality of understanding. In the simulation experiment, IWC was compared with the ant colony algorithm, particle swarm algorithm, and whale optimization algorithm under a different number of tasks. The results showed that the IWC algorithm has good results in terms of task scheduling time, scheduling cost, and virtual machine. The application is in cloud computing task scheduling.

A Novel Sparrow Particle Swarm Algorithm (SPSA) for Unmanned Aerial Vehicle Path Planning

Unmanned aerial vehicle (UAV) has been widely used in various fields, and meeting practical high-quality flight paths is one of the crucial functions of UAV. Many algorithms have the problem of too fast convergence and premature in UAV path planning. This study proposed a sparrow particle swarm algorithm for UAV path planning, the SPSA. The algorithm selects a suitable model for path initialization, changes the discoverer position update, and reinforces the influence of start-end line on path search, which can significantly reduce blind search. The number of target points reached is increased by adaptive variable speed escapes in areas of deadlock. In this case, the planned trajectory will fluctuate, and adaptive oscillation optimization can effectively reduce the fluctuation of the path. Finally, the optimal path is simplified, and the path nodes are interpolated with cubic splines to improve the smoothness of the path, which improves the smoothness of the UAV flight trajectory and makes it more suitable for use as the UAV real flight trajectory. By comparison, it can be concluded that the improved SPSA has good convergence speed and better search results and can avoid local optimality.

A Multiobjective Particle Swarm Optimization Algorithm Based on Grid Technique and Multistrategy

When faced with complex optimization problems with multiple objectives and multiple variables, many multiobjective particle swarm algorithms are prone to premature convergence. To enhance the convergence and diversity of the multiobjective particle swarm algorithm, a multiobjective particle swarm optimization algorithm based on the grid technique and multistrategy (GTMSMOPSO) is proposed. The algorithm randomly uses one of two different evaluation index strategies (convergence evaluation index and distribution evaluation index) combined with the grid technique to enhance the diversity and convergence of the population and improve the probability of particles flying to the real Pareto front. A combination of grid technology and a mixed evaluation index strategy is used to maintain the external archive to avoid removing particles with better convergence based only on particle density, which leads to population degradation and affects the particle exploitation ability. At the same time, a variation operation is proposed to avoid rapid degradation of the population, which enhances the particle search capability. The simulation results show that the proposed algorithm has better convergence and distribution than CMOPSO, NSGAII, MOEAD, MOPSOCD, and NMPSO.