Review and Research Development of Optimization Algorithms Based on Wolf Intelligence

Uniform magnetic fields are widely used in atomic magnetometers, MRI and other fields. The traditional method of solving closed-form equations is usually used to design highly uniform magnetic field coils. In this paper, a new intelligent algorithm, wolf pack algorithm (WPA), is proposed to design the coil structure of a highly uniform magnetic field. This method can replace the traditional method to obtain the coil parameters. We additionally use a discrete optimization method to solve the rounding error. According to the investigation, compared with particle swarm optimization (PSO) algorithm, WPA has stronger global optimization ability, faster convergence speed and multiple optimization strategies. We set appropriate coil constraints (structural and process constraints) and simplify the multi-dimensional solutions to one-dimensional solutions to reduce the difficulty of operation. The distribution of magnetic field intensity of three axes of coils is analyzed by the finite element analysis method, and the 1%, 0.1%, and 0.01% uniform regions are studied. Under the same conditions, the uniform magnetic field regions of the coils designed by the PSO and WPA, as well as a single pair of axial and radial coils are compared. The performance results of multiple pairs of coils are superior to those of a single pair of coils. In general, the uniformity of the axial and radial magnetic field coils designed by the WPA is better than that designed by the PSO. Finally, the experimental value of the magnetic field uniformity is nearly consistent with the theoretical value.

A wavelet neural network (WNN) prediction model based on improved wolf pack algorithm(WPA) is proposed to meet the demand of Shanxi's spot market, which requires power sales companies to "quote quantity but not offer price". Customers are classified by considering the differences in electricity consumption characteristics of different industries. The bidirectional comparison method is used to preprocess the original data, which can effectively reduce the errors in the process of data measurement and acquisition. Using WNN to forecast the customer's day-ahead electrical load. Meantime, the intelligent algorithm is used to optimize the network parameters and strengthen the prediction performance of the WNN. The wolf pack algorithm is used to optimize the system, and the walking mode of the wolf pack is improved, which further to improve the optimization ability of the system. An example shows that the model is more accurate in short-term load prediction. Compared with before the improvement, the prediction accuracy has been improved by nearly 2%, and the accuracy has reached 96.4%, which can provide a strong guarantee of the electricity sales company to master the customer load curve, participate in the spot market, and improve its competitiveness.

In this paper, we study an intelligent path planning problem on avoiding traffic obstacles in urban transportation networks. We apply three heuristic methods to solve the optimization model, including genetic algorithm, wolf pack algorithm, and a mixture method of genetic algorithm and wolf pack algorithm. In the numerical results, we compare the solutions and performance of these three intelligent algorithms. It shows that the optimal path lengths obtained by these three algorithms are very closed, whereas the convergence time of the genetic algorithm is the shortest among them. We also find that the mixture method is more efficient in updating the population, and its convergence speed is the fastest. Besides, it is found that the convergence time of the wolf pack algorithm is smaller than the others. By means of the analysis in our experiments, we evaluate the pros and cons of these algorithms when solving the studied optimization problem, which would be of great significance for the intelligent optimization of obstacle path planning in smart cities.

The parameters of hydraulic turbine governor directly affect the dynamic characteristics of the hydraulic unit, thus affecting the regulation capacity and the power quality of power grid. The governor of conventional hydropower unit is mainly PID governor with three adjustable parameters, which are difficult to set up. In order to optimize the hydraulic turbine governor, this paper proposes wolf pack algorithm (WPA) for intelligent tuning since the good global optimization capability of WPA. Compared with the traditional optimization method and PSO algorithm, the results show that the PID controller designed by WPA achieves a dynamic quality of hydraulic system and inhibits overshoot.

Design of highly uniform three-dimensional square magnetic field coils for external magnetic shielding of magnetometers

The original wolf pack algorithm has two distances to compare and determine whether ferocious wolf participates in the siege behavior. In order to improve the accuracy of optimization, a new distance is described as the approaching siege distance by expanding a certain range. An equation for calculating the approaching siege distance is given, and the distance between ferocious wolf and the head wolf is specified if ferocious wolf reach the approaching siege distance, which is able to participate in the siege behavior. Furthermore, on the basis of proposing the approaching siege distance, three step weights are introduced to make the step lengths of the three intelligent behaviors change in the iterative optimization and also improve convergence accuracy. Finally, through 5 standard test functions and a problem of optimal processing time in Job-shop Scheduling, the results are compared with the original wolf pack algorithm, and the effectiveness of the improved wolf pack algorithm is verified and the accuracy of optimization is increased by 1 to 3 orders in magnitude.

Aiming at the optimization of truss structure, a wolf pack algorithm based on chaos and improved search strategy was proposed. The mathematical model of truss optimization was constructed, and the classical truss structure was optimized. The results were compared with those of other optimization algorithms. When selecting and updating the initial position of wolves, chaos idea was used to distribute the initial value evenly in the solution space; phase factor was introduced to optimize the formula of wolf detection; information interaction between wolves is increased and the number of runs is reduced. The numerical results show that the improved wolf pack algorithm has the characteristics of fewer parameters, simple programming, easy implementation, fast convergence speed, and can quickly find the optimal solution. It is suitable for the optimization design of the section size of space truss structures.

In the upcoming era of 6G, the accelerated development of the Internet of Everything and high-speed communication is poised to provide people with an efficient and intelligent life experience. However, the exponential growth in data traffic is expected to pose substantial task processing challenges. Relying solely on the computational resources of individual devices may struggle to meet the demand for low latency. Additionally, the lack of trust between different devices poses a limitation to the development of 6G networks. In response to this issue, this study proposes a blockchain-based 6G task offloading and collaborative computational resource allocation (CERMTOB) algorithm. The proposed first designs a blockchain-based 6G cloud-network-edge collaborative task offloading model. It incorporates a blockchain network on the edge layer to improve trust between terminals and blockchain nodes. Subsequently, the optimization objective is established to minimize the total latency of offloading, computation, and blockchain consensus. The optimal offloading scheme is determined using the wolf fish collaborative search algorithm(WF-CSA) to minimize the total delay. Simulation results show that the WF-CSA algorithm significantly reduces the total delay by up to 42.58% compared to the fish swarm algorithm, wolf pack algorithm and binary particle swarm optimisation algorithm. Furthermore, the introduction of blockchain to the cloud-side-end offloading system improves the communication success rate by a maximum of 14.93% compared to the blockchain-free system.

In the process of LED chip coating, the steady flow at the spray gun in a unit time has a significant impact on the final luminous effect. Traditional PID control is difficult to control the flow accurately due to the nonlinearity of phosphor powder. In order to improve the luminous quality, a neural network PID control method based on wolf pack algorithm is proposed(WPA-BPNN-PID) in this paper. First, the weights and thresholds of BP neural network are optimized by using the wolf pack algorithm to improve the training speed and prediction accuracy. Second, the optimal PID control parameters are searched online by using the optimized BP neural network. Finally, the traditional PID control algorithm, neural network PID control algorithm and WPA-BPNN-PID algorithm are simulated by MATLAB simulation software. The experimental results show that the proposed WPA-BPNN-PID algorithm has better dynamic and static performance, anti-interference ability, and thus can further accurately control the colloid flow of phosphor powder in unit time.

The scattering effect of turbid media can lead to optical wavefront distortion. Focusing light through turbid media can be achieved using wavefront shaping techniques. Intelligent optimization algorithms and neural network algorithms are two powerful types of algorithms in the field of wavefront shaping but have their advantages and disadvantages. In this paper, we propose a new hybrid algorithm that combines the particle swarm optimization algorithm (PSO) and single-layer neural network (SLNN) to achieve the complementary advantages of both. A small number of training sets are used to train the SLNN to obtain preliminary focusing results, after which the PSO continues to optimize to the global optimum. The hybrid algorithm achieves faster convergence and higher enhancement than the PSO, while reducing the size of training samples required for SLNN training. SLNN trained with 1700 training sets can speed up the convergence of the PSO by about 50% and boost the final enhancement by about 24%. This hybrid algorithm will be of great significance in fields such as biomedicine and particle manipulation.

Free to read on publisher's website Utilizing dynamic resource allocation for load balancing is considered as an important optimization process in cloud computing. In order to achieve maximum resource efficiency and scalability in a speedy manner this process is concerned with multiple objectives for an effective distribution of loads among virtual machines. In this realm,exploring new algorithms, as well as development of novel algorithms, is highly desired for technological advancement and continued progress in resource allocation application in cloud computing. Accordingly, this paper explores the application of two relatively new optimization algorithms and further proposes a hybrid algorithm for load balancing which can contribute well in maximizing the throughput of the cloud provider's network. The proposed algorithm is a hybrid of teaching-learning-based optimization algorithm (TLBO) and grey wolves optimization algorithm (GW). The hybrid algorithm performs more efficiently than utilizing every single one of these algorithms. Furthermore, it well balances the priorities and effectively considers load balancing based on time, cost, and avoidance of local optimum traps, which consequently leads to minimal amount of waiting time. To evaluate the effectiveness of the proposed algorithm, a comparison with the TLBO and GW algorithms is conducted and the experimental results are presented.

Multilevel Inverters are now increasingly used in most of the power electronics applications including medium and high voltage devices. SHE is useful for eliminating the switching losses particularly for high voltage applications. This paper presents selective harmonic elimination through Hybrid optimization algorithm for elimination of lower order odd harmonics and THD in the multilevel inverter output. This hybrid algorithm is a combination of Ant colony optimization and Newton-Raphson algorithm where ant Colony optimization algorithm is applied for first four cycles and then the output of this algorithm will be treated as a starting consideration for N- _R algorithm. The primary advantage of this algorithm is its simplicity of design, less computational efforts, faster convergence and elimination of need of initial guess compared to other conventional iterative methods. Results show that third, fifth and seventh harmonics along with THD are minimized greatly. MATLAB/Simulink software is used to simulate these results. Experimental results are also presented to prove the efficacy of proposed system.

The scale and complexity of search space are important factors deciding the solving difficulty of an optimization problem. The information of solution space may lead searching to optimal solutions. Based on this, an algorithm for combinatorial optimization is proposed. This algorithm makes use of the good solutions found by intelligent algorithms, contracts the search space and partitions it into one or several optimal regions by backbones of combinatorial optimization solutions. And optimization of small-scale problems is carried out in optimal regions. Statistical analysis is not necessary before or through the solving process in this algorithm, and solution information is used to estimate the landscape of search space, which enhances the speed of solving and solution quality. The algorithm breaks a new path for solving combinatorial optimization problems, and the results of experiments also testify its efficiency.

Antenna modeling based on meta-heuristic intelligent algorithms and neural networks

Optimizing resource allocation and routing to satisfy service needs is paramount in large-scale networks. Software-defined networking (SDN) is a new network paradigm that decouples forwarding and control, enabling dynamic management and configuration through programming, which provides the possibility for deploying intelligent control algorithms (such as deep reinforcement learning algorithms) to solve network routing optimization problems in the network. Although these intelligent-based network routing optimization schemes can capture network state characteristics, they are prone to falling into local optima, resulting in poor convergence performance. In order to address this issue, this paper proposes an African Vulture Routing Optimization (AVRO) algorithm for achieving SDN routing optimization. AVRO is based on the African Vulture Optimization Algorithm (AVOA), a population-based metaheuristic intelligent optimization algorithm with global optimization ability and fast convergence speed advantages. First, we improve the population initialization method of the AVOA algorithm according to the characteristics of the network routing problem to enhance the algorithm’s perception capability towards network topology. Subsequently, we add an optimization phase to strengthen the development of the AVOA algorithm and achieve stable convergence effects. Finally, we model the network environment, define the network optimization objective, and perform comparative experiments with the baseline algorithms. The experimental results demonstrate that the routing algorithm has better network awareness, with a performance improvement of 16.9% compared to deep reinforcement learning algorithms and 71.8% compared to traditional routing schemes.