Imperialist Competitive Algorithm Research Articles

Research on Power System Day-Ahead Generation Scheduling Method Considering Combined Operation of Wind Power and Pumped Storage Power Station

In the proposed wind-storage combined operation technology, the storage side is foreseen to play a significant role in power system day-ahead generation scheduling. Based on the operational characteristics of pumped storage power stations, the day-ahead dispatching method of a power system with wind farms and pumped storage power stations is studied. The dispatching mode that aims at the lowest operating cost is proposed, taking into consideration the coordination relationship between the scheduling benefit of pumped storage power stations and the total peak-shaving economy of the system and the fluctuation of new energy output. First, taking the constraint of reservoir capacity, the output power, and the daily pumping power of the pumped storage power station into account, a day-ahead generation scheduling model is constructed, with the objective of minimizing costs. Then, the imperial competition algorithm is applied to the proposed model. Finally, the algorithm is compared with the standard particle swarm optimization algorithm. The simulation results based on standard 4-unit and 10-unit systems indicate that the proposed method is effective and robust for a power system with wind power and pumped storage power stations.

A novel energy consumption prediction method for chillers based on an improved support vector machine

The energy consumption prediction of the chiller is an important means to reduce the energy consumption of buildings. Therefore, a novel energy consumption prediction model for chillers based on an improved support vector machine (ICA-DE-SVM) is proposed. The imperialist competitive algorithm (ICA) is used to optimize the penalty coefficient and kernel function width of SVM, greatly improving the generalization ability and prediction accuracy of the SVM model. The assimilation process is very important in ICA. Colonies of empires move randomly toward imperialists during the assimilation process in ICA, which decreases population diversity and can lead to premature convergence. Therefore, to create more new locations for colonies and increase population diversity, the idea of differential mutation proposed by differential evolution (DE) was applied to ICA. The established model was experimentally verified in an actual multi-chiller system in a building, and the results showed that the ICA-DE-SVM model could obtain good prediction results. Finally, the proposed model was compared with SVM model, PSO-SVM model, GA-SVM model, WOA-SVM model, and ICA-SVM model. With an MAPE of 0.6%, an MSE of 2.3, and an R2 of 0.9998, the findings demonstrate that the ICA-DE-SVM model has a greater prediction accuracy than the other models.

Estimation of properties of ultra great workability concrete by optimized ANFIS models

The mechanical properties of the ultra-great workability concrete (UGWC) are deeply related to the weights of components, curing period and condition, and occasionally property of admixtures. This study aimed to appraise the usefulness of the adaptive neuro-fuzzy inference system (ANFIS) technique for forecasting the compressive strength of UGWC and enhancing the accuracy of the literature. To outline the forecasting process, two improved ANFIS were suggested, in which determinative variables of them were determined by metaheuristic algorithms named imperialist competitive algorithm (ICA) and multi-verse optimizer (MVO) algorithms. For this purpose, 170 data samples were collected from published literature separated accidentally for the train and test phase. The calculated performance criteria for proposed ANFIS models demonstrate that both ICA-ANFIS and MVO-ANFIS models can result in justifiable workability for fc of the UGWC prediction procedure. The MVO-ANFIS model could outperform ICA-ANFIS regarding all criteria. For instance, the value of R2 and VAF for the ICA-ANFIS model are roughly smaller than the MVO-ANFIS model, at 0.9012 and 90% in the training dataset and 0.8973 and 89% in the testing stage, respectively. While the best values of criteria have belonged to the MVO-ANFIS model, with R2 at 0.937 and 0.944 for the train and test phases, respectively. Overall, the hybrid MVO-ANFIS model can obtain higher workability than ICA-ANFIS and literature (R2 at 0.801), where causes are recognized as the proposed model.

Optimal energy management of CHP‐based microgrid examining different types of district heating networks

AbstractHeat recovery by combined heat and power (CHP) systems to provide heat load reduces the cost of microgrid (MG) energy management. However, heat transfer from CHP systems to consumers is limited due to the heat loss of pipelines. The amount of heat loss varies depending on pipeline material and environmental characteristics. Here, a day‐ahead energy management of CHP‐based microgrid, including various types of CHP systems to supply electrical and thermal loads, is performed. In this regard, the accurate model of heat transfer losses (HTL) through pipelines in the energy management problem is considered. Moreover, the optimal scheduling of different types of MGs in terms of HTL specifications is compared with each other. Evaluating the simulation results, it is inferred that accurate modeling of HTL in the energy management problem has a significant impact on the optimal scheduling and operation cost of MG. To solve the optimization problem, a new enhanced imperialist competitive algorithm (E‐ICA) is examined and validated. The E‐ICA method improves the efficiency of the classical ICA method to prevent getting stuck in local optimums by enhancing exploration and exploitation. The results of the energy management problem show E‐ICA superiority compared to other evolutionary algorithms.

An autonomous planning model for solving IoT service placement problem using the imperialist competitive algorithm

An autonomous planning model for solving IoT service placement problem using the imperialist competitive algorithm

Time-Domain Structural Damage Identification Using Ensemble Bagged Trees and Evolutionary Optimization Algorithms

This paper presents a two-step vibration-based strategy for damage identification of framed structures using ensemble bagged trees known as a well-known supervised machine learning (ML) paradigm in conjunction with evolutionary optimization algorithms. The proposed model incorporates the actual response, wavelet coefficients, and wavelet energy to extract damage-sensitive features from the time-domain of the measured and simulated signals. Unlike available studies in this scope, the key objective of this research is to identify damage with a localization precision down to a single structural member, rather than limiting the evaluation to the group of elements. In order to increase the training performance in contributing to extremely large datasets with numerous class labels, the proposed strategy involves the artificial generation of features. Additionally, a modified genetic algorithm is proposed for fast damage localization. It is deduced that the damage locations are confidently detected within a fast computational time. Subsequently, damage identification is followed by the application of evolutionary optimization algorithms. For comparison purpose, the employment of the water cycle optimization algorithm (WCA) is comparatively investigated with the other three state-of-the-art optimizers, i.e., particle swarm optimization (PSO), imperialist competitive algorithm (ICA), and differential evolution algorithm (DE). The numerical and experimental validation studies evidence satisfactorily reliable identification results with no false detection in dealing with multiple damage scenarios in large-scale and real-world applications. It is concluded that developing the most damage-sensitive features and using the proposed data fusion strategy lead to informative features with a reasonably small size and significantly improve the ML performance.

Multi-objective optimization of petroleum engineering problems using a hybrid workflow: Combination of particle swarm optimization, fuzzy logic, imperialist competitive algorithm and response surface methodology

Optimization techniques are used to find the strategies for chemically enhanced oil recovery in a sandstone reservoir. This research develops a multi-objective optimization methodology by combining experimental design methods and artificial intelligence techniques. The capability of this hybrid artificial intelligence methodology is evaluated in the optimal design of control variables to achieve the highest performance of a surfactant/polymer injection project into a sandstone reservoir. In the first step, a two-level full factorial design is used to screen initial control variables. Thereafter a response surface methodology (RSM) is employed to optimize the RF and NPV of a CEOR application. The neuro-simulation technique provides the required outputs for screening and RSM designs. The performance of network is improved using the imperialist competitive algorithm (ICA). Having precise fitness functions, multi-attribute optimization was performed using particle swarm optimization (PSO) and fuzzy logic (FL). This paper discusses the advantages of different perspectives over single-objective approaches. Using the RF-objective PSO algorithm, RF exceeded 64% of original oil in place (OOIP), while the profit of project slumped to $5.90 MM. On the other hand, NPV-attribute PSO increased NPV to $8.48 MM. Meanwhile, RF, as the technical success of the project, plunged to less than 53% OOIP. However, the proposed multi-objective algorithm increased RF to 57% OOIP with NPV of $8.11 MM, solving the trade-off between technical and economic terms. The results of this study indicate the efficacy of proposed hybrid workflow for multi-attribute decision-making of CEOR field implementation.

An advanced intelligent MPPT control strategy based on the imperialist competitive algorithm and artificial neural networks

An advanced intelligent MPPT control strategy based on the imperialist competitive algorithm and artificial neural networks

An efficient recurrent neural network for defensive Stackelberg game

This study presents a robust and efficient recurrent neural network (RNN) to solve the continuous defensive location problem (CDLP). CDLP is a bilevel mathematical model, where a planner locates various types of defense facilities for stopping a offender from reaching a critical vertex called core in the network. Due to the NP-hardness of the CDLP, RNN is implemented to find satisfactory solutions on four small-sized, two medium-sized and two larger-sized examples of problem. The numerical experiments show that RNN is able to produce promising results with good execution time and precision when compared with the best previous methods including tabu search (TS), imperialist competitive algorithm (ICA) and hybridization of TS with Levenberg–Marquardt algorithm (HTS) and hybridization of ICA with BFGS algorithm (HICA). The objective values of RNN show that this method stops the attacker at a further distance from the core in comparison with other methods. As well, to validate the efficiency of the proposed RNN, statistical criteria are considered and results are analyzed. For small-sized examples, the computational experiments show that the RNN can obtain solutions as the same as exact approaches but in a shorter runtime.

Techno-economic analysis and optimal sizing of a battery-based and hydrogen-based standalone photovoltaic/wind hybrid system for rural electrification in Cameroon based on meta-heuristic techniques

In developing nations, particularly in African countries, where difficulties with rural electrification are highly severe, hybrid power systems appeared as a suitable method of distributing power to rural and off-grid locations. Cameroon, like other African countries, is facing a serious challenge of access to basic energy services for its population. The country's constraints present a global situation of less than 48% of the population having access to electrical energy. This situation is more frequent in rural areas. In this paper, a comparative assessment of meta-heuristics optimization techniques is conducted for optimal design of photovoltaic/wind/fuel cell and photovoltaic/wind/battery hybrid systems to constantly supply-three typical loads demand in Kousseri, Cameroun. For this purpose, four well-known meta-heuristics techniques namely artificial bee colony algorithm, cuckoo search algorithm, imperialist competitive algorithm and big bang-big crunch algorithm are implemented to solve the optimization problem, consisting of minimizing the net present cost while increasing the system reliability characterized by loss of power supply probability. Four others configurations namely photovoltaic/battery, wind/battery, photovoltaic/fuel cell and wind/fuel cell are also evaluated and the outcomes are compared with the results of the photovoltaic/wind/fuel cell and photovoltaic/wind/battery systems with regards to the life-cycle cost and cost of energy. To determine the most affordable configurations, simulations and optimizations studies are conducted. Our findings revealed that, the cuckoo search algorithm performs better than other algorithms. The results also show that, photovoltaic/wind/battery standalone hybrid system is the more reliable and cost-effective configuration for satisfying the three typical electrical loads demand encountered at Kousseri, Cameroon. The obtained optimal number of component and cost of energy of the photovoltaic/wind/battery hybrid systems are as follows: for heavy activity the optimal system integrates 27 PV panels, 1 wind turbine, 38 batteries banks, 1 inverter and the obtained cost of energy corresponds to 0.1959$/kWh; for medium activity, 13 PV panels, 1 wind turbine, 26 batteries banks and 1 inverter which resulted to a cost of energy of 0.2386$/kWh and for small activity, the best configuration includes 19 PV panels, 5 wind turbines, 18 batteries banks and 1 inverter with a cost of energy of 0.2641$/kWh.

Multi-objective optimization of IoT-based green building energy system using binary metaheuristic algorithms

Green building energy optimization systems (GBEOS) are of great interest to academics and industry professionals. One of the main challenges of GBEOS is optimizing energy consumption while maintaining people's comfort level. This paper proposes a metaheuristic-based GBEOS for optimizing energy consumption within a smart green building operating under a smart grid paradigm while considering the local environment and energy demand behaviors. In this regard, two complementary control procedures are developed: the supply-part optimizer (SPO) and the demand-part optimizer (DPO). By combining SPO and DPO, six binary multi-objective optimization algorithms, including Xtreme gradient boosting (XGBoost), multiverse optimizer (MVO), moth flame optimization (MFO), shuffled frog leaping algorithm (SFLA), moth flame optimization, imperialist competitive algorithm (ICA), and chimp optimization algorithm (ChOA) are developed to simultaneously minimizes costs and maximizes client comfort satisfaction (CS). First of all, considering the importance of convergence speed, seven unimodal, six multimodal, and twenty complex benchmark optimization functions are used to evaluate the proposed approach's convergence behavior. Afterward, an efficient weighting mechanism is used to handle the cost-comfort trade-off, allowing the user to discover a reasonable trade-off between monetary expense and comfort level. Then, in order to determine the influence of the pricing scheme's nature on the potential savings achieved through EMS, three individual models named real-time pricing (RTP), time-of-utilize pricing (TUP), and fixed-pricing plan (FPP) are proposed. The results show that ChOA presents the best result in terms of convergence, with 19 out of 33 test functions; also, XGBoost has the second-best performance. In addition, results show that suggested metaheuristic algorithms significantly increase PV energy penetration for self-consumption and lower power costs while keeping an optimal balance between CS and economical costs. Moreover, using dynamic pricing systems, i.e., RTP or TUP, results in great user price savings than FPP. To sum up, ChOA is found to be the best algorithm in this challenge, followed by XGBoost in second place.

Simultaneous density and thermal conductivity depth profile reconstructions from noised thermal-wave amplitude and phase data using a combined integral-equation and imperialist competitive algorithm method

An efficient new thermal-wave inverse-problem approach based on an integral-equation boundary-value method coupled with an imperialist competitive algorithm was developed. The methodology was successfully applied to simultaneously reconstruct density and thermal conductivity depth profiles in a sintered powder metallurgy sample from an industrial automotive manufacturer with a surface layer of higher density than the bulk. The density and thermal conductivity depth profiles were validated independently using the manufacturer's data and in-house temperature and porosity measurements. The present non-destructive inverse problem approach represents a generalized formalism to thermal-wave reconstruction of dual depth profiles using frequency scan data measured from the interrogated surface. From a fundamental viewpoint, the method adds significant insights into the relationship between thermal conductivity and density distributions in inhomogeneous solids.

Optimal Design of Corona Ring for 132 kV Insulator at High Voltage Transmission Lines Based on Optimisation Techniques

The installation of a corona ring on an insulator string on a transmission line is one of the solutions to reduce the electric field stress surrounding the energised end of the insulator string. However, installing a corona ring with an optimum design to reduce the electric field magnitude on an insulator string is a challenging task. Therefore, in this work, a method to achieve the optimum design of a corona ring for 132 kV composite non-ceramic insulator string was proposed using two optimisation methods: the Imperialist Competitive Algorithm (ICA) and Grey Wolf Optimisation (GWO). A composite non-ceramic insulator string geometry with and without a corona ring was modelled in finite element analysis and used to obtain the electric field distribution in the model geometry. The electric field distribution was evaluated using a variation in the corona ring’s dimensions, i.e., the ring diameter, the ring tube diameter and the vertical position of the ring along the insulator string. From the results achieved, a comparison of the minimum electric field magnitude along the insulator string with a corona ring design shows that the minimum electric field magnitude is found to be lower using optimisation techniques compared to without using optimisation techniques by between 3.724% and 3.827%. Hence, this indicates the capability and effectiveness of the proposed methods in achieving the optimum design of a corona ring on an insulator string.

Minimizing Total Tardiness in a Two-Machine Flowshop Scheduling Problem with Availability Constraints

In this paper, we consider the problem of minimizing the total tardiness in a deterministic two-machine permutation flowshop scheduling problem subject to release dates of jobs and known unavailability periods of machines. The theoretical and practical importance of minimizing tardiness in flowshop scheduling environment has motivated us to investigate and solve this interested two-machine scheduling problem. Methods that solve this important optimality criterion in flowshop environment are mainly heuristics. In fact, despite the -hardness in the strong sense of the studied problem, to the best of our knowledge there are no approximate algorithms (constructive heuristics or metaheuristics) or an algorithm with worst case behavior bounds proposed to solve this problem. Thus, the design of new promising algorithms is desirable. We develop five metaheuristics for the problem under consideration. These metaheuristics are: the Particle Swarm Optimization (PSO), the Differential Evolution (DE), the Genetic Algorithm (GA), the Ant Colony Optimization (ACO) and the Imperialist Competitive Algorithm (ICA). All the proposed metaheuristics are population-based approaches. These metaheuristics have been improved by integrating different local search procedures in order to provide more satisfactory, especially in term of quality solutions. Computational experiments carried out on a large set of randomly generated instances provide evidence that the Imperialist Competitive Algorithm (ICA) records the best performances.

Optimal Allocation of STATCOM to Enhance Transient Stability Using Imperialist Competitive Algorithm

With the daily expansion of global energy consumption, developing the power grids is of uttermost importance. However, building a new transmission line is costly and time-consuming, so utilizing the same lines with possible higher transmission capacity is very cost-effective. In this regard, to increase the capacity of the transmission lines, the flexible alternating current transmission system (FACTS) has been widely used in power grids in recent years by industrialized countries. One of the essential topics in electrical power systems is the reactive power compensation, and the FACTS plays a significant role in controlling the reactive power current in the power grid and the system voltage oscillations and stability. When a static synchronous compensator (STATCOM) is embedded in a power system to increase the bus voltage, a supplementary damping controller can be designed to enhance the system oscillation damping. Given the expansion of the grids in the power system, the complexity of their optimization and the extraordinary ability of the imperialist competitive algorithm (ICA) for solving such problems, in this paper, the ICA has been used to determine the optimal position and size of the FACTS devices.

Optimal Integration of PV-Based Distributed Generators and Shunt Capacitors for 69 Bus System using Imperialist Competitive Algorithm and ETAP Software

Optimal deployment of photovoltaic-based distributed generators (PVDG) and shunt capacitor units is a perilous task in modern power system planning. This work presents an effective Imperialist Competitive Algorithm (ICA) based on social political process for selecting the best locations and sizes for PVDGs and shunt capacitor units. Three different load patterns, i.e., nominal, decremented and incremented are taken into account while installing PVDG and shunt capacitor units in the typical radial distribution systems of 69-bus. The primary objective of this work is to reduce active power losses and to significantly improve the voltage pattern after positioning of PVDG and capacitor units. The results show that the losses are reduced significantly by integrating the PVDG and capacitor units simultaneously at the optimum position in the test system. Furthermore, results of simulating the 69 bus system (with the integrated PVDG and capacitors) prove to be promising and authentic.

A revised imperialist competition algorithm for cellular manufacturing optimization based on product line design

<p style='text-indent:20px;'>Due to the fierce market competition, enterprises try to satisfy customers' requirements for personalized products in order to maximize profit or market share of their products. This not only needs to determine the product variants through product line design, but also needs to pay attention to resource allocation in the manufacturing process. This paper proposes a cellular manufacturing optimization model that considers the market and production. If the company excessively pursues the satisfaction of customers' personalized needs, the manufacturing time and cost may increase accordingly. Of course, with the restriction of production capacity in manufacturing cells and the expectation of reducing cost, managers cannot design attributes' levels of a product line casually, which may result in its unstable marketing share and profit. Therefore, the product demand influenced by customers' preferences could be a key factor to link market and production. The objective of propose model is to maximize product profit which consists of revenue and miscellaneous costs (material, processing, transportation, final assembly and fixed costs). A revised imperialist competitive algorithm (RICA) is developed to optimize the discrete problem. Extensive numerical experiments and t-test are carried out to verify the effect of this method. The results demonstrate the proficiency of RICA over another imperialist competitive algorithm based method and genetic algorithm in terms of solution quality.</p>

Diagnosis of Autism Spectrum Disorder by Imperialistic Competitive Algorithm and Logistic Regression Classifier

Diagnosis of Autism Spectrum Disorder by Imperialistic Competitive Algorithm and Logistic Regression Classifier

Investigation of Task Scheduling in Cloud Computing by using Imperialist Competitive and Crow Search Algorithms

Cloud Storage is a complex method that is a method of processing and data of a cloud built by duplication of thousands of related devices in a complex manner. The main function of the data processing server is to show how many users are being investigated and provide accurate, efficient and efficient information. Important Algorithm Editing Players in the Cloud Defines the virtual machine (VM) required for this purpose. The role of editing the algorithm reduces the effect of the schedule. Naturally affected algorithms have recently been used to quickly comply with the recent traditional algorithms. Given many consumers of many cloud computing services, many researchers may have a serious explanation that many researchers take and discuss the complex themes of NP. Some sites use imperialist algorithms (ICA) and birds. The purpose of the proposed project is to develop intelligent scientific algorithms that focus on the integration of ICA and CSA to obtain data. CSA is concentrated on the corner of food habits. The crow is looking for his friends to get enough food for today's food. This will help the CSA find suitable VMs for these machines and complete the equipment. Cloud Sim is used to calculate CSA output with minmin and ant algorithms. The simulation results show that the CSA is extra powerful than the MinMin and Ant procedures.

Designing a reliable aggregate production planning problem during the disaster period

The purpose of this research is to introduce a Bi-Objective (BO) model for dealing with Aggregate Production Planning (APP) for a multi-product and multi-period Supply Chain Network (SCN) that incorporates multiple suppliers, factories, and demand points. One of the goals of the model is to minimize the total cost of this network during the disaster period. The other goal is to account for probabilistic lead times to maximize the minimum level of producers' reliability during the COVID-19 pandemic. They are done to ameliorate the system's performance and improve the reliability of production plans. Finally, considering that the mentioned problem is NP-hard, a Multi-Objective Imperialist Competitive Algorithm (MOICA) based on Pareto is used to solve the proposed model, and a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) is also utilized to measure the performance of the mentioned algorithm. The generated experimental problems' results demonstrate the proposed algorithm's power in finding Pareto solutions. According to innovation, this is the first paper on these topics considering the conditions of the COVID-19 disaster.