Fuzzy Adaptive Particle Swarm Optimization Research Articles

Fuzzy Adaptive PSO-ELM Algorithm Applied to Vehicle Sound Quality Prediction

When dealing with specific tasks, the hidden layer output matrix of an extreme learning machine (ELM) may change, largely due to the random assigned weight matrix of the input layer and the threshold matrix of the hidden layer, which sequentially leads to the corresponding change to output weights. The unstable fluctuations of the output weights increase the structural risk and the empirical risk of ELM. This paper proposed a fuzzy adaptive particle swarm optimization (PSO) algorithm to solve this problem, which could nonlinearly control the inertia factor during the iteration by fuzzy control. Based on the fuzzy adaptive PSO-ELM algorithm, a sound quality prediction model was developed. The prediction results of this model were compared with the other three sound quality prediction models. The results showed that the fuzzy adaptive PSO-ELM model was more precise. In addition, in comparison with two other adaptive inertia factor algorithms, the fuzzy adaptive PSO-ELM model was the fastest model to reach goal accuracy.

IC Package Warpage Reduction Based on Fuzzy Adaptive Particle Swarm Optimization Algorithm and Neural Network

IC Package Warpage Reduction Based on Fuzzy Adaptive Particle Swarm Optimization Algorithm and Neural Network

Collaborative beamforming in wireless sensor networks using a novel particle swarm optimization algorithm variant

Collaborative Beamforming (CBF) is an essential tool towards increasing transmission range in Wireless Sensor Networks (WSNs). Owing to the random and complex nature of WSNs, development and use of improved metaheuristic algorithms in CBF is of essence. Particle Swarm Optimization (PSO) algorithm is a good candidate for use in CBF owing to its simplicity and low computation complexity. However, the basic PSO algorithm suffers from premature convergence particularly in highly multimodal functions (typical of CBF). This paper delves into the development and application of an improved Particle Swarm Optimization (PSO) algorithm in CBF. A new fuzzy-logic based confidence and inertia weight parameters adaptation scheme has been developed with an aim of enhancing exploration and exploitation capabilities of the PSO algorithm. Normalized particle quality and iteration count have been used as the inputs to the designed fuzzy-logic inference system. The fuzzy logic based parameters adaptation scheme has been implemented in the form of a lookup table to minimize “on-line” computation complexity. Furthermore, a particle culling/ re-initialization procedure is utilized at half the number of maximum iterations to enhance overall swarm diversity. The modified PSO algorithm has been christened Culled Fuzzy Adaptive Particle Swarm Optimization (CFAPSO) algorithm. The developed CFAPSO algorithm is noted to outperform other metaheuristic algorithms in a statistical performance analysis procedure (on the basis of a set of standard unimodal and multimodal functions). Upon application to CBF, the CFAPSO algorithm is found to generate a beamsteering outcome statistically identical to that of conventional beamsteering.

Effective Power Congestion Management Technique Using Hybrid Nelder–Mead – Grey Wolf Optimizer (HNMGWO) in Deregulated Power System

The aim of this article is to apply Hybrid Nelder–Mead – Grey Wolf Optimizer (HNMGWO) in congestion management problem with optimal congestion cost by rescheduling generators in the power system. When the transmission power lines are overloaded in the power system, the following strategies are followed: generator rescheduling and installation of FACTS devices on the lines and load curtailment. But, load curtailment is not performed as the deregulated system encourages customer satisfaction. Thus, generator rescheduling is selected for problem solution as it does not involve the creation of any new infrastructure. Grey Wolf Optimizer (GWO) is one of the recent optimization techniques which work based on the leadership hierarchy and the hunting technique of grey wolves. The effective local search is performed by the Nelder–Mead (NM) method and the output is used to initialize the population for GWO, which searches global best value. In this paper, the HNMGWO is attempted based on the positive outcome of both NM and GWO. This proposed algorithm has been applied and results have been discussed related to the tasks of Independent System Operator. The proposed HNMGWO is applied in a standard IEEE 30 bus and IEEE 118 bus systems and thereby results are compared with standard GWO, Particle Swarm Optimization (PSO), fuzzy adaptive PSO, genetic algorithm, and bacterial foraging algorithms. The result shows that the proposed work is more effective by consuming minimum congestion cost in reduced rescheduled power and power loss.

Design and Evaluation of Fuzzy Adaptive Particle Swarm Optimization Based Maximum Power Point Tracking on Photovoltaic System Under Partial Shading Conditions

Artificial intelligence methods such as fuzzy logic and particle swarm optimization (PSO) have been applied to maximum power point tracking (MPPT) for solar panels. The P-V curve of a solar panel exhibits multiple peaks under partial shading condition (PSC) when all modules of a solar panel do not receive the same solar irradiation. Although conventional PSO has been shown to perform well under uniform insolation, it is often unable to find the global maximum power point under PSC. Fuzzy adaptive PSO controllers have been proposed for MPPT. However, the controller became computation-intensive in order to adjust the PSO parameters for each particle. In this paper, fuzzy adaptive PSO-based and conventional PSO-based MPPT are compared and evaluated in the aspect of design and performance. A simple fuzzy adaptive PSO controller for MPPT was designed to reach the global optimal point under PSC and uniform irradiation. The controller combines the advantages of both PSO and fuzzy control. The fuzzy controller dynamically adjusts the PSO parameter to improve the convergence speed and global search capability. Since tuning of the PSO parameter is designed to be common for all particles, it reduced the computation complexity. The fuzzy controller’s rule base is designed to obtain a fast transient response and stable steady state response. Design of the fuzzy adaptive PSO-based MPPT is verified with simulation results using a boost converter. The results are evaluated in comparison to the results using a conventional PSO controller under PSC. Simulation shows the fuzzy adaptive PSO-based MPPT is able to improve the global search process and increase the convergency speed. The comparison indicates the settling time using the fuzzy adaptive PSO-based MPPT is 14% faster under PSC on average and 30% faster under uniform irradiation than the settling time using the conventional PSO. Both the fuzzy adaptive and conventional PSO controllers have similar output power tracking accuracy.

Deployment of On-Orbit Service Vehicles Using a Fuzzy Adaptive Particle Swarm Optimization Algorithm

On the basis that satellites given fixed count and orbit elements can be served in bounded time when an on-orbit serving mission order is set at any uncertain time in a given time interval, the deployment of on-orbit service vehicle (OSV) serving satellites becomes a complex multiple nested optimization problem, and the essence of deployment is to determine the count and orbit elements of OSVs. In consideration of the characteristics of this deployment problem, we propose a fuzzy adaptive particle swarm optimization (FAPSO) algorithm to solve this problem. First, on the basis of double pulse rendezvous hypothesis, a transfer optimization model of a single OSV serving multiple satellites is established based on genetic algorithm (GA), and this is used to compute the indexes of the subsequent two optimization models. Second, an assignment optimization model of OSVs is established based on the discrete particle swarm optimization (DPSO) algorithm, laying the foundation of the next optimization model. Finally, the FAPSO algorithm, which improves the performance of PSO algorithm by adjusting the inertia weight, is proposed to solve the deployment problem of multiple OSVs. The simulation results demonstrate that all optimization models in this study are feasible, and the FAPSO algorithm, which has a better convergence result than that obtained using the other optimization algorithms, can effectively solve the deployment problem of OSVs.

Collaborative Beamforming in Wireless Sensor Networks Using a Novel Particle Swarm Optimization Algorithm Variant

Wireless Sensor Network (WSN) nodes inherently feature limited transmission range. A recent solution to the long range transmission problem is Collaborative Beamforming (CBF). The outcome of an ideal CBF process ought to be a radiation pattern whose main beam is oriented towards the intended transmission destination (WSN sink), inherently increasing the transmission range. Owing to the random and complex nature of WSNs, development and use of improved metaheuristic algorithms in CBF is of essence. This paper delves into the development and application of an improved Particle Swarm Optimization (PSO) algorithm in CBF from the perspective of a 3 dimension WSN configuration (wherein the sink is elevated from the nodes’ plane). The modifications done on the PSO algorithm entail use of fuzzy-adaptive confidence and inertia weight parameters alongside a particle culling procedure. The modified PSO algorithm has been christened Culled Fuzzy Adaptive Particle Swarm Optimization (CFAPSO) algorithm. Comparisons against use of a linearly-adaptive PSO algorithm variant, basic PSO algorithm and the Genetic Algorithm (GA) in CBF have established the superiority of the proposed CFAPSO algorithm. The CFAPSO algorithm is found to generate a beamsteering outcome statistically identical to that of conventional beamsteering. It is noteworthy that conventional beamsteering is inapplicable to beam-pattern optimization with respect to processes such as sidelobe minimization, nulling among others. The developed CFAPSO algorithm befits utilization in a plethora of CBF schemes.

Fuzzy logic adaptive particle swarm optimisation based MPPT controller for photovoltaic systems

Maximum power point tracking (MPPT) controllers are a key element in photovoltaic (PV) conversion systems since they allow extracting the maximum power from PV generators. Metaheuristic algorithms such as the particle swarm optimisation (PSO) are nowadays widely adopted and have shown their superiority to many other techniques. However, conventional PSO (CPSO) algorithms still suffer from the problem of long convergence time when the range of the search area is large. To overcome this issue, this study proposes a fast fuzzy logic PSO (FL-PSO) based MPPT controller for PV systems. Unlike CPSO algorithm running with constant key parameters (inertia weight and acceleration coefficients), the proposed method includes a fuzzy inference system that dynamically adjusts these parameters. The effectiveness and rapidity of the proposed FL-PSO algorithm is validated trough numerical simulations and experimental tests. The obtained results show the superiority of the proposal as compared to CPSO, Jaya and hill climbing algorithms even under partial shading conditions and abrupt change of solar irradiation.

Personalized Learning Resource Recommendation Method Based on Dynamic Collaborative Filtering

This paper proposes a personalized learning resource recommendation method based on dynamic collaborative filtering algorithm. Pearson correlation coefficient is used to calculate the data similarity between learning users or project resources in the network, and the unscored value is obtained. In order to solve the problems of sparse data and poor scalability in collaborative filtering algorithm, dynamic k-nearest-neighbor and Slope One algorithm are used to optimize it, and the sparsity of learning resource data in the network is analyzed according to the result of neighbor selection. The bidirectional self-equalization of stage evolution is used to improve the personalized recommendation of resource push, and the fuzzy adaptive binary particle swarm optimization algorithm based on the evolution state judgment is used to solve the problem of the optimal sequence recommendation, so as to realize the personalized learning resource recommendation. The experimental results show that the proposed method has higher matching degree and faster recommendation speed.

Adaptive particularly tunable fuzzy particle swarm optimization algorithm

Particle Swarm Optimization (PSO) is a metaheuristic optimization algorithm that owes much of its allure to its simplicity and its high effectiveness in solving sophisticated optimization problems. However, since the performance of the standard PSO is prone to being trapped in local extrema, abundant variants of PSO have been proposed by far. For instance, Fuzzy Adaptive PSO (FAPSO) algorithms have been being studied extensively in recent years. In this study, a modified version of PSO algorithms is presented and is named as Adaptive Particularly Tunable Fuzzy Particle Swarm Optimization (APT-FPSO). In it, the global and personal learning coefficients of every single particle are tuned adaptively and particularly, at an individual extent, within each iteration with the aid of fuzzy logic concepts. Ample statistical evidence is provided indicating that the proposed algorithm further improves the potentialities and capabilities of the standard PSO.

Recognition of Complex Power Quality Disturbances Using S-Transform Based Ruled Decision Tree

Deteriorated quality of power leads to problems, such as equipment failure, automatic device resets, data errors, failure of circuit boards, loss of memory, power supply issues, uninterrupted power supply (UPS) systems generate alarm, corruption of software, and heating of wires in distribution network. These problems become more severe when complex (multiple) power quality (PQ) disturbances appear. Hence, this manuscript introduces an algorithm for identification of the complex nature PQ events in which it is supported by Stockwell’s transform (ST) and decision tree (DT) using rules. PQ events with complex nature are generated in view of IEEE-1159 standard. Eighteen different types of complex PQ issues are considered and studied which include second, third, and fourth order disturbances. These are obtained by combining the single stage PQ events such as sag & swell in voltage, momentary interruption (MI), spike, flicker, harmonics, notch, impulsive transient (IT), and oscillatory transient (OT). The ST supported frequency contour and proposed plots such as amplitude, summing absolute values, phase and frequency-amplitude obtained by multi-resolution analysis (MRA) of signals are used to identify the complex PQ events. The statistical features such as sum factor, Skewness, amplitude factor, and Kurtosis extracted from these plots are utilized to classify the complex PQ events using rule-based DT. This is established that proposed approach effectively identifies a number of complex nature PQ events with accuracy above 98%. Performance of the proposed method is tested successfully even with noise level of 20 dB signal to noise ratio (SNR). Effectiveness of the proposed algorithm is established by comparing it with the methods reported in literature such as fuzzy c-means clustering (FCM) & adaptive particle swarm optimization (APSO), Wavelet transform (WT) & neural network (NN), spline WT & ST, ST & NN, and ST & fuzzy expert system (FES). Results of simulations are validated by comparing them with real time results computed by Real Time Digital Simulator (RTDS). Different stages for design of complex PQ monitoring device using the proposed approach are also described. It is verified that the proposed approach can effectively be employed for design of the online complex PQ monitoring devices.

Fuzzy adaptive control particle swarm optimization based on T-S fuzzy model of maglev vehicle suspension system

At present, with the gradual promotion of Maglev vehicles, the stability of the suspension system has gradually become a hotspot. During the operation of Maglev vehicles, vibration may be caused by external disturbances such as track irregularity, non-directional wind load and load variation. When the vibration amplitude is within the controllable range of the current parameters, the restraint effect can be achieved and the stable convergence can be formed. However, when the vibration amplitude exceeds the current controllable range, the maglev vehicle may break the track or even lose stability. In order to solve the possible adverse effects of external disturbances on the stability of the system, a T-S fuzzy model considering both parameter uncertainties and external disturbances is constructed, and a relatively mature fuzzy adaptive control method is used for suspension control. However, considering the tracking performance of the system control parameters and the response speed of the parameter changes when the external disturbance changes, the particle swarm optimization (PSO) algorithm is used to optimize the system. The effectiveness of the optimized fuzzy adaptive control law in coordinating the closed-loop stability of the suspension system is proved in terms of response speed and convergence performance. Based on linear matrix inequality (LMI), the control response region satisfying the control performance after optimization is defined, and Lyapunov method is adopted to prove the stability of the optimized algorithm in controlling vehicle fluctuation operation. The simulation and experimental results show that the fuzzy adaptive control algorithm optimized by particle swarm optimization can further improve the speed of parameter optimization and the tracking performance of the system in the face of external disturbances and internal system parameter perturbations within a given range of control parameters. Compared with previous control strategies, the controller can greatly improve the response speed and the closed-loop information updating ability of the system in the face of disturbances, so that the system has stronger robustness and faster dynamic response.

Accurate Parameter Estimation of a Hydro-Turbine Regulation System Using Adaptive Fuzzy Particle Swarm Optimization

Parameter estimation is an important part in the modeling of a hydro-turbine regulation system (HTRS), and the results determine the final accuracy of a model. A hydro-turbine is normally a non-minimum phase system with strong nonlinearity and time-varying parameters. For the parameter estimation of such a nonlinear system, heuristic algorithms are more advantageous than traditional mathematical methods. However, most heuristics based algorithms and their improved versions are not adaptive, which means that the appropriate parameters of an algorithm need to be manually found to keep the algorithm performing optimally in solving similar problems. To solve this problem, an adaptive fuzzy particle swarm optimization (AFPSO) algorithm that dynamically tunes the parameters according to model error is proposed and applied to the parameter estimation of the HTRS. The simulation studies show that the proposed AFPSO contributes to lower model error and higher identification accuracy compared with some traditional heuristic algorithms. Importantly, it avoids a possible deterioration in the performance of an algorithm caused by inappropriate parameter selection.

GSA–FAPSO-Based Generators Active Power Rescheduling for Transmission Congestion Management

In the present electricity markets, an algorithm with fast convergence characteristics along with the production of accurate results is more needful in order to improve the profit margins of a utility. In this view, a hybrid algorithm comprising various techniques like gravitational search algorithm (GSA) and fuzzy adaptive particle swarm optimization (FAPSO) is proposed in the present work. The hybridization of the algorithms is done to have combined advantages like local search capability and global search capability of GSA and standard PSO (S-PSO) algorithms, respectively. Furthermore, fuzzy system based dynamic inertia weight is incorporated in the S-PSO algorithm in order to have exact nonlinear search space. The proposed hybrid algorithm is implemented to a complex nonlinear transmission congestion management problem in which the active powers of generators are rescheduled for achieving the congestion-free network lines of a bulk power system. The practical feasibility of the proposed approach is checked by evaluating the congestion cost on various IEEE standard networks. The adaptability of the algorithm is checked by considering various case studies involving congestion due to bilateral, multilateral transactions and line outages on respective test bus system.

Swarm intelligent-based congestion management using optimal rescheduling of generators

Congestion management (CM) refers to the controlling of transmission system such that the power transfer/flow limits are observed. In the restructured electrical system, the challenges of CM for the system operator (SO) is to maintain the desired level of system reliability and security in the short and long terms, while improving the market/system efficiency. In this paper, the CM problem is tackled by using the centralised optimisation, i.e., optimal rescheduling of generators, which in turn is solved by using the Swarm intelligent techniques. Here, the CM problem is solved by using the particle swarm optimisation (PSO), fitness distance ratio-PSO (FDR-PSO) and fuzzy adaptive-PSO (FA-PSO). First, the generators are selected based on sensitivity to the over-loaded transmission line, and then these generators are rescheduled to remove the congestion in the transmission line. The suitability and effectiveness of the proposed CM approach is examined on the standard IEEE 30 bus and practical Indian 75 bus systems.

Electricity Price Forecasting and Classification Through Wavelet–Dynamic Weighted PSO–FFNN Approach

In competitive electricity markets, accurate price forecasting is required to both power producers and consumers for planning their bidding strategies in order to maximize their own benefits. Price classification is an alternative approach to forecasting where the exact values of future prices are not mandatory. Presently, two efficient algorithms are proposed for both short term price forecasting (STPF) and classification (STPC) purposes. The algorithms include various methodologies like wavelet transform (WT), fuzzy adaptive particle swarm optimization (FA-PSO) and feed forward neural networks (FFNN). WT is utilized to convert the pathetic price series to an inviolable price series without losing the originality in the signal. Standard PSO (S-PSO) is implemented to tune the fixed architecture FFNN weights and biases. In the present nonlinear problem, linear variation of inertia weight does not resemble exact search process. Hence, dynamic inertia weight is accomplished by implementing the fuzzy systems in the S-PSO approach. The hybrid methodology is implemented on Spanish electricity markets for the year 2002. To validate, three types of price classes and historical price series that are utilized by many researches as input features, are considered. Various statistical indicators are evaluated to compare and validate the proposed approaches with the past approaches available in the literature survey.

PD Source Location Utilizing Acoustic TDOA Signals in Power Transformer by Fuzzy Adaptive Particle Swarm Optimization

PD Source Location Utilizing Acoustic TDOA Signals in Power Transformer by Fuzzy Adaptive Particle Swarm Optimization

Congestion Management Based on Optimal Rescheduling of Generators and Load Demands Using Swarm Intelligent Techniques

This paper presents the Congestion Management (CM) methodologies and how they get modified in the new competitive framework of electricity power markets. When the load on the system is increased or when some contingency occurs in the system, some of the lines may become overloaded. Thus, the loadability of the system should be increased by generating and dispatching the power optimally for the secure operation of power system. In this paper, the CM problem is solved by using the optimal rescheduling of generating units and load demands, and the Swarm intelligent techniques are used to handle this problem. Here, the CM problem is solved by using the Particle Swarm Optimization (PSO), Fitness Distance Ratio PSO (FDR-PSO) and Fuzzy Adaptive-PSO (FA-PSO). First, the generating units are selected based on sensitivity to the over-loaded transmission line, and then these generators are rescheduled to remove the congestion in the transmission line. This paper also utilizes the demand response offers to solve the CM problem. The effectiveness of the proposed CM methodology is examined on the IEEE 30 bus and Indian 75 bus test systems.

Optimal allocation of wind turbine generator in active distribution network

Nowadays, more and more wind turbine generators (WTGs) are being integrated into power systems. In this paper, an optimal WTG allocation model with the objective of minimizing the annual cost is proposed. The model can take into account the time‐sequential correlation between the wind speed and load demand, as well as four kinds of active management measures, i.e. regulating the on‐load tap changer of the transformer, curtailing the output power of WTG, regulating the power factor of WTG, and managing the demand side. The time‐sequential correlation is handled by the joint probability distribution method. A hybrid solving strategy combining the fuzzy adaptive particle swarm optimization algorithm and primal‐dual interior point method is developed to get the optimal solutions. Case studies carried out on the IEEE 33‐bus active distribution network verify the feasibility of the developed model and the high efficiency of the proposed solving strategy. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Study on day-ahead optimal economic operation of active distribution networks based on Kriging model assisted particle swarm optimization with constraint handling techniques

The distribution system is demanded to be more efficient, more flexible and more intelligent due to the continued growth of the electricity loads, the high efficiency of energy utilization and the environmental protection. The traditional distribution systems are facing the challenge of evolving from passive networks to the active distribution networks (ADN) with the integration of multiple controllable resources. This paper presents an optimal operation and schedule model of the ADN, considering a variety of controllable resources such as distributed generations, battery storages and interruptible loads. To solve the optimization problem, a modified fuzzy adaptive PSO assisted by Kriging model (KMA-MFAPSO) is developed in this paper. In KMA-MFPSO, a novel constraint handling technique (CHT) based on the PSO is proposed to handle the constraints effectively. In addition, under the premise of ensuring the accuracy of the calculation, the Kriging model is used in KMA-MFAPSO to calculate the power flow the ADN approximately, which greatly speeds up the solving process. Finally, the effectiveness of the proposed algorithm is tested on a modified IEEE-123 system. The optimal results obtained by the proposed method are compared with the results obtained by using other solving algorithms. The simulation results indicate that KMA-MFAPSO is very robust and fast to solve the optimization problem so that it can be used in practical systems.