Gravitational Search Particle Swarm Optimization Research Articles

New Approach for Sediment Yield Forecasting with a Two-Phase Feedforward Neuron Network-Particle Swarm Optimization Model Integrated with the Gravitational Search Algorithm

Predicting sediment yield is an important task for decision-makers in environmental monitoring and water management since the benefits of applying non-linear, artificial intelligence (AI) models for optimal prediction can be far reaching in real-life decision support systems. AI-based models are considered to be favorable predictive tools since the nonlinear nature of suspended sediment data series warrants the utilization of nonlinear predictive methods for feature extraction, and for accurate simulation of suspended sediment load. In this study, Artificial Neural Network (ANN) approaches are employed to estimate the monthly sediment load where the two-phase Feed-forward Neuron Network Particle Swarm Optimization Gravitational Search Algorithm (FNN-PSOGSA) is developed, and then evaluated in respect to 3 distinct algorithms: the Adaptive Neuro-Fuzzy Inference System (ANFIS), Feed-forward Neuron Network (FNN) and the single-phase Feed-forward Neuron Network Particle Swarm Optimization (FNN-PSO). The study is carried out using the monthly rainfall, runoff and sediment data spanning a 10 year period (2000–2009) where about 75% of data are used in model training phase, 25% in testing phase. Three statistical performance criteria namely: the mean absolute error (MAE), Nash-Sutcliffe coefficient (NSE) and the Willmott’s Index (WI) and diagnostic plots visualizing the tested results are used to evaluate the performance of four AI-based models. The results reveal that the objective model (the two-phase FNN-PSOGSA model) and the single-phase FNN-PSO model yielded more precise results compared to the other forecast models. This result accorded to an NSE value of 0.612 (for the FNN-PSOGSA model) vs. an NS value of 0.500, 0.331 and 0.244 for the FNN-PSO, FNN and ANFIS models, and WI = 0.832 vs. 0.771, 0.692 and 0.726, respectively The study also demonstrated that the FNN model generated slightly better results than the ANFIS model for the estimation of sediment load data but overall, the two-phase FNN-PSOGSA model outperformed all comparison models. In light of the superior performance, this research advocates that the fully-optimized two-phase FNN-PSOGSA model can be explored as a decision-support tool for monthly sediment load forecasting using the rainfall and runoff values as the predictor datasets.

Testing evolutionary algorithms for optimization of water distribution networks

Water distribution networks (WDNs) are one of the most important elements of urban infrastructure and require large investment for construction. Design of WDNs is classified as a large combinatorial discrete nonlinear optimization problem. The main concerns associated with the optimization of such networks are the nonlinearity of the discharge-head loss relationships for pipes and the discrete nature of pipe sizes. Due to these issues, this problem is widely considered to be a benchmark problem for testing and evaluating the performance of nonlinear and heuristic optimization algorithms. This paper compares different techniques, all based on evolutionary algorithms (EAs), which yield optimal solutions for least-cost design of WDNs. All of these algorithms search for the global optimum starting from populations of solutions, rather than from a single solution, as in Newton-based search methods. They use different operators to improve the performance of many solutions over repeated iterations. Ten EAs, four of them for the first time, are applied to the design of three networks and their performance in terms of the least cost, under different stopping criteria, are evaluated. Statistical information for 20 executions of the ten algorithms is summarized, and Friedman tests are conducted. Results show that, for the two-loop benchmark network, the particle swarm optimization gravitational search and biology and bioinformatics global optimization algorithms efficiently converge to the global optimum, but perform poorly for large networks. In contrast, given a sufficient number of function evaluations, the covariance matrix adaptation evolution strategy and soccer league competition algorithm consistently converge to the global optimum, for large networks.

An Enhanced MPR OLSR Protocol for Efficient Node Selection Process in Cognitive Radio Based VANET

A VANET is an excellent instance of a wireless sensor network. The mobile vehicles are the nodes and communication happens between the vehicular nodes. This facility of communicating with the vehicular nodes finds varied applications ranging from entertainment to emergency services. When combined with cognitive radio techniques, VANETs are equipped with the facility of sensing the spectrum opportunistically. When the spectrum is sensed efficiently, the channel and the bandwidth can be utilized effectively. To achieve this, we have coordinated the enhanced Optimal Link State Routing Protocol (MMPR-OLSR) with the GSA-PSO (Gravitational Search-Particle Swarm Optimization) scheme in combination with the cognitive radio technique. This technique can be applied to the Vehicular Sensor Networks. MMPR-OLSR with GSA-PSO optimization facilitates the MMPR-OLSR protocol to select the suitable member nodes using an optimal searching technique. The GSA-PSO optimization not only helps in choosing the appropriate MMPR nodes, but also helps in reducing the unnecessary overheads due to the propagation of the control packets. By selecting the appropriate MMPR nodes. It is also possible to minimize the number of relay selector nodes used in transmission. The optimization technique also focuses on assigning the channels among all the network users. This is controlled by our proposed approach. A group of nodes are selected before the start of the actual transmission. These vehicular nodes within the communication range are used as relays in the transmission. These nodes are categorized as Multi Point Relays. Cognitive radio plays an active role by identifying the idle channels, thus enabling the usage of the unused channels. Our proposed approach works efficiently in achieving the objective of effective channel utilization combined with efficient transmission. Our proposed approach is simulated using the NS2 platform and is evaluated based on important network metrics. Our proposed method shows a sharp decrease in delay and a high packet delivery ratio in addition to a high channel utilization. The proposed GSA-PSO approach decreases the delay associated with packet transmission and delivery in VANETs and also ensures a good PDR due to the effective channel utilization.

A hybrid structure of an extreme learning machine combined with feature selection, signal decomposition and parameter optimization for short-term wind speed forecasting

Influenced by various environmental and meteorological factors, wind speed presents stochastic and unstable characteristics, which makes it difficult to forecast. To enhance the forecasting accuracy, this study contributes to short-term multi-step hybrid wind speed forecasting (WSF) models using wavelet packet decomposition (WPD), feature selection (FS) and an extreme learning machine (ELM) with parameter optimization. In the model, the WPD technique is applied to decompose the empirical wind speed data into different, relatively stable components to reduce the influence of the unstable characteristics of wind speed. A hybrid particle swarm optimization gravitational search algorithm (HPSOGSA) combining conventional PSOGSA with binary PSOGSA (BPSOGSA) is utilized to realize the FS and parameter optimization simultaneously. The PSOGSA is employed to tune the parameter combination of input weights and biases in ELM, while BPSOGSA is exploited to select the most suitable features from the candidate input variables determined by a partial autocorrelation function for reconstruction of the input matrix for ELM. The proposed forecasting strategy carries out multi-step short-term WSF using mean half-hour historical wind speed data collected from a wind farm situated in Anhui, China. To investigate the forecasting results of the hybrid model, a lot of comparisons and analyses are executed. Simulation results illustrate that the proposed WPD-ELM model with FS and parameter optimization can effectively catch the non-linear characteristics hidden in wind speed data and provide satisfactory WSF performance.

Use of modified hybrid PSOGSA for optimum design of RC frame

ABSTRACTA realistic and optimum design of reinforced concrete structural frame, by hybridizing enhanced versions of standard particle swarm optimization (PSO) and standard gravitational search algorithm (GSA) is presented in this paper. PSO has been democratized by considering all good and bad experiences of the particles, whereas GSA has been made self-adaptive by considering a specific range for certain parameters like ‘gravitational constant’ and ‘set of agents with best fitness value.’ Optimal size and reinforcement of the members have been found by employing the technique in a computer-aided environment. Use of self-adaptive GSA together with democratic PSO technique has been found to provide two distinct advantages over standard PSO and GSA, namely better capability to escape from local optima and faster convergence rate. The entire formulation for optimal cost design of frame includes the cost of beams and columns. In this approach, variables of each element of structural frame have been considered as continuous functions and rounded off appropriately to imbibe practical relevance to the study. An example has been considered to emphasize the validity of this optimum design procedure and results have been compared with earlier studies.

Stochastic optimal reactive power planning and active power dispatch with large penetration of wind generation

In this paper, an optimal probabilistic reactive power planning and active power dispatch method considering uncertain loads and intermittent wind generation is proposed. Four types of wind generator models, viz, simple PQ model of an induction generator and pitch regulated fixed speed, semi-variable speed, and doubly fed induction generator models, have been considered in this work. The objective of the planning strategy adopted is to maximize the annual profit of the utility. To maximize the profit, a modified particle swarm optimization gravitational search algorithm based optimization technique has been developed. The performance of this developed technique has been compared with those obtained from genetic algorithm, gravitational search algorithm, and modified particle swarm optimization gravitational search algorithm optimization methods. Extensive simulation studies on IEEE-30, IEEE-57, and IEEE-118 bus systems show that the performance of the modified algorithm technique is superior to that of other methods in terms of the value of both the objective function and the reproducibility of results.

Evolutionary Beamforming Optimization for Radio Frequency Charging in Wireless Rechargeable Sensor Networks.

This paper investigates how to efficiently charge sensor nodes in a wireless rechargeable sensor network (WRSN) with radio frequency (RF) chargers to make the network sustainable. An RF charger is assumed to be equipped with a uniform circular array (UCA) of 12 antennas with the radius λ, where λ is the RF wavelength. The UCA can steer most RF energy in a target direction to charge a specific WRSN node by the beamforming technology. Two evolutionary algorithms (EAs) using the evolution strategy (ES), namely the Evolutionary Beamforming Optimization (EBO) algorithm and the Evolutionary Beamforming Optimization Reseeding (EBO-R) algorithm, are proposed to nearly optimize the power ratio of the UCA beamforming peak side lobe (PSL) and the main lobe (ML) aimed at the given target direction. The proposed algorithms are simulated for performance evaluation and are compared with a related algorithm, called Particle Swarm Optimization Gravitational Search Algorithm-Explore (PSOGSA-Explore), to show their superiority.

Optimization of collision avoidance maneuver planning for cluster satellites in space debris explosion situation

In this study, the conjunction situation when a number of explosion fragments approach four cluster satellites was simulated, and an optimum avoidance maneuver plan that mitigates this risk was established. The orbits of four deputy satellites around a virtual chief satellite were defined using the Hill–Clohessy–Wiltshire equation, and NASA’s breakup model was applied to similar altitude rocket body to simulate explosions situation. The distribution of 230 explosion fragments after an explosion was simulated, and the size and direction of the Delta-V were applied to each fragment. In this situation, the collision avoidance maneuver planning strategy that uses heuristic algorithm was proposed to establish efficient avoidance maneuver plan for approaching fragments after the explosion. Avoidance maneuver plans using four heuristic algorithms were established to minimize the fuel consumption of the four cluster satellites within several constraints including conjunction risk, ground track and formation between cluster satellites. Eight simulations were performed with different combinations of the four heuristic algorithms and different generations and populations. As a result, all avoidance maneuver plan satisfied conjunction risk constraint as well as the other complex constraints. In particular, particle swarm optimization–gravitational search algorithm established the most efficient maneuver plan with the least fuel consumption and fastest convergence speed.

Machinability study of Carbon Fiber Reinforced Polymer in the longitudinal and transverse direction and optimization of process parameters using PSO–GSA

Carbon Fiber Reinforced Polymer (CFRP) composites are widely used in aerospace industry in lieu of its high strength to weight ratio. This study is an attempt to evaluate the machinability of Bi-Directional Carbon Fiber–Epoxy composite and optimize the process parameters of cutting speed, feed rate and drill tool material. Machining trials were carried using drill bits made of high speed steel, TiN and TiAlN at different cutting speeds and feed rates. Output parameters of thrust force and torque were monitored using Kistler multicomponent dynamometer 9257B and vibrations occurring during machining normal to the work surface were measured by a vibration sensor (Dytran 3055B). Linear regression analysis was carried out by using Response Surface Methodology (RSM), to correlate the input and output parameters in drilling of the composite in the longitudinal and transverse directions. The optimization of process parameters were attempted using Genetic Algorithm (GA) and Particle Swarm Optimization–Gravitational Search Algorithm (PSO–GSA) techniques.

Optimal Over-current Relay Coordination with Distributed Generation Using Hybrid Particle Swarm Optimization–Gravitational Search Algorithm

This article presents a hybrid optimization technique particle swarm optimization–gravitational search algorithm for optimal over-current relay coordination. The main contribution of this article is to find the optimized relay settings during variation in environmental factors that affect distributed generation performance. The detailed model of wind and photovoltaic source, modeled in a PSCAD/EMTDC platform is penetrated in a 13-bus distribution system. The optimal relay settings are found for different cases, including change in wind speed, change in penetration level, change in cell temperature, and insolation level of photovoltaic. A comparison of particle swarm optimization–gravitational search algorithm with particle swarm optimization and gravitational search algorithm technique is also done, and it is shown that the particle swarm optimization–gravitational search algorithm is a superior method that can be applied in relay coordination tasks.

Transient simulation of gas pipeline networks using intelligent methods

Simulation of gas pipeline network has an important role in control and design of the natural gas transmission system. Transient simulation provides several advantages in energy consumption optimization where compressor stations variables are manipulated regarding to contract pressures. In this paper, a novel approach based on intelligent algorithms and three basic functions is proposed for dynamic simulation of gas pipeline networks. An optimization tool is used to find the inlet flow rates of the network. If the inlet flow rates are calculated correctly, all network variables can be computed using three basic functions. In each sample of time, the optimization tool called particle swarm optimization gravitational search algorithm (PSOGSA) offers some candidate solutions for inlet flow rates of the network. For each of these candidate solutions, the network is analyzed using three basic functions and then, outlet pressures are calculated. The differences between calculated outlet pressures and the reference values are considered as an error or fitness function of optimization tool. Finally, the optimization tool finds the optimum inlet flow rates at that sample of time which lead to minimum error. The proposed method is straight forward and easy to implement while its error percentage is near zero and converges faster than some well-known optimization algorithms. Numerical results confirm the accuracy and efficiency of the suggested algorithm.

Multi-response Optimization in Drilling of Carbon Fiber Reinforced Polymer Using Artificial Neural Network Correlated to Meta-heuristics Algorithm

This paper aims to optimize the drilling process parameters using artificial neural network (ANN) linked with the most popular meta-heuristics technique such as Hybrid Particle Swarm Optimization Gravitational Search Algorithm (PSOGSA) and Genetic Algorithm (GA). An aerospace grade T300 Carbon Fiber-Epoxy composite laminate of 8 mm thick was made of T300 Polyacrylonitrile (PAN) based Carbon Fiber and two part Epoxy resin was use for this study. The Carbon Fiber used is Bi-directional (BD) with a ply thickness of 0.25 mm and lay-up sequence of [60/90/0/90/90/60/0/60/60/60/60/45/90/90/0/45/60/90/60]. Drilling experiments were conducted on a composite laminate by varying the cutting speed (30, 40 and 50 m/min), feed rate (0.025, 0.05 and 0.1 mm/rev) and drill bit type (HSS, TiAlN and TiN). The experimental results in the form of thrust force, torque and surface roughness obtained are correlated with process parameters through artificial neural network (ANN) and optimized by PSOGSA and GA. The optimization results indicates that the proposed hybrid PSOGSA performances much better than the GA.

Optimal Power Flow Using a Hybrid Optimization Algorithm of Particle Swarm Optimization and Gravitational Search Algorithm

—This article presents a hybrid algorithm based on the particle swarm optimization and gravitational search algorithms for solving optimal power flow in power systems. The proposed optimization technique takes advantages of both particle swarm optimization and gravitational search algorithms by combining the ability for social thinking in particle swarm optimization with the local search capability of the gravitational search algorithm. Performance of this approach for the optimal power flow problem is studied and evaluated on standard IEEE 30-bus and IEEE 118-bus test systems with different objectives that reflect fuel cost minimization, voltage profile improvement, voltage stability enhancement, power loss reduction, and fuel cost minimization with consideration of the valve point effect of generation units. Simulation results show that the hybrid particle swarm optimization–gravitational search algorithm provides an effective and robust high-quality solution of the optimal power flow problem.

Optimal static state estimation using improved particle swarm optimization and gravitational search algorithm

In this paper, two novel evolutionary search techniques based on Improved Particle Swarm Optimization (IPSO) algorithm and Gravitational Search Algorithm (GSA), have been proposed to solve the static State Estimation (SE) problem as an optimization problem. The proposed methods are tested on five IEEE standard test systems along with two ill-conditioned test systems under different simulated conditions and the results are compared with the same of standard Weighted Least Square State Estimation (WLS-SE) technique, Particle Swarm Optimization (PSO) based SE and Hybrid Particle Swarm Optimization Gravitational Search Algorithm (PSOGSA) based SE technique. The optimization performance and the statistical error analysis show the superiority of the proposed GSA based SE technique over the other two techniques.