Figure 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Optimal placement of Charging stations (CSs) and infrastructure planning are one of the most critical challenges that face the Electric Vehicles (EV) industry nowadays. A variety of approaches have been proposed to address the problem of demand uncertainty versus the optimal number of CSs required to build the EV infrastructure. In this paper, a Ma...
Citations
... Metaheuristics in this area promote applicable solutions to increase the percentage of sustainable vehicles used in transportation and logistics. Since energy costs are lower, specific algorithms such as Grey Wolf Optimization, using stochastic modeling, have improved the net gain of companies by optimizing charging station allocation problems in electric vehicle networks [67]. This positively impacts waiting times and energy consumption in transportation, with cases reporting a 69.9% reduction in waiting times and a 48.03% decrease in fuel consumption [68]. ...
... In turn, economic sustainability gains strength through the use of algorithms using sustainable transport, such as electric vehicles. The Grey Wolf Optimization (GWO) algorithm is used to select the best charging station locations with the aim of maximizing net gain in both budget and routing constraints [67]. This gives strength to the arguments that the advance of metaheuristics implies maximization of benefits and increasing search for sustainability. ...
Importance: This bibliometric analysis of the application of metaheuristics in transportation and logistics examines over two decades of research (1999–present), aiming to uncover global trends, anticipate future directions, and highlight how interconnections between key factors facilitate the development of practical and sustainable solutions for the industry. Methodology: A quantitative approach is employed to analyze the evolution of the discipline by reviewing an extensive database of relevant research and key authors and utilizing advanced data processing tools. This analysis enables the assessment of advances in the optimization of metaheuristic models, with an impact on time and cost savings from an economically sustainable perspective. Results: The use of metaheuristics optimizes the efficiency and competitiveness of the transportation sector while promoting a positive economic impact on companies. The main areas of application are optimization and metaheuristic methods, cost and operational efficiency, planning and scheduling, logistics and transportation, supply chain and logistics networks, energy and sustainability, and demand and users. Additionally, genetic algorithms stand out as particularly important. Conclusions: This research provides a comprehensive and detailed view of the impact of metaheuristics on the transportation sector, highlighting their current and future trends (such as artificial intelligence) and their economic relevance.
... These approaches are typically validated using simulation models or alternative algorithms. Shabbar et al. (2021) proposed a profit-maximizing model using Grey Wolf Optimization (GWO) and a Markov-chain model to simulate demand. Later, Jordán et al. (2022) developed an optimized charging infrastructure based on GA, validated through agentbased simulation. ...
In urban India air pollution is a critical environmental issue with the transportation sector being a major contributor. Transitioning to electric vehicles is one essential policy decision that can reduce emissions, thus, necessitating a robust network of public charging stations. This study proposes a facility-based Multi-Criteria Decision-Making (MCDM) analysis integrated with Geographical Information System (GIS) to address site selection issues for EV charging stations. The methodology involves three steps to determine the optimal locations for EVCs: (i) defining 12 sub-criteria and weighting them using both CRiteria Importance Through Intercriteria Correlation (CRITIC) and ENTROPY, (ii) generating a suitability map for potential EVCSLs via GIS, and (iii) ranking the performance levels of EVCSLs based on the suitability map using Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and Weighted Aggregated Sum Product Assessment (WASPAS) methods. The comprehensive model is illustrated in Fig. 1. A case study in Telangana, India, with existing charging stations, validates the proposed approach. Sensitivity and comparative analyses demonstrate that criteria weight changes significantly impact the solution, underscoring the importance of proper criteria identification and accurate weight assignment. Among the methods compared (TOPSIS-CRITIC, TOPSIS-Entropy, WASPAS-CRITIC, WASPAS-Entropy), TOPSIS-CRITIC outperforms others in 10 out of 13 scenarios, offering larger service areas for a given number of charging stations for the given case study. The results indicate that the proposed MCDM framework is stable, reliable, and effective for EVCS location selection incorporating a holistic criteria-based framework, supporting India's goal of full EV adoption by 2030 as per its Paris Agreement commitments.
... In the above-mentioned studies significance of the road network has been undervalued. In [6], [7], road and distribution network both are considered in order to optimally allocate the charging stations by maximizing the profit of the service provider. In [8], EVCSs are strategically placed in a superimposed distribution and road network by optimizing the power loss of the distribution network. ...
Efficient allocation of electric vehicle charging stations (EVCSs) is crucial to promote widespread adoption of electric vehicles, to support sustainable transportation, and to reduce range anxiety. Thus, it enhances energy security and mitigates environmental impact. In this work, EVCSs are optimally distributed across a superimposed road and distribution network with a focus on electric vehicle (EV) user's convenience to reach charging station. The allocation problem has primarily been solved by taking into account nodal cost and vehicular uncertainty. The process also considered minimizing fundamental energy and harmonic losses in the distribution network. The quantity of charging ports is a crucial consideration that is frequently overlooked during the allocation process. Optimal port allocation not only helps in determining the waiting time of each EV user reaching that charging station but also reduces the burden on the distribution network of excessive port in a charging station. In this instance, the cost of installing the charging port is taken into account and optimized. An additional fee to the charging station has been imposed as an additional expenditure for the distribution losses caused by the inclusion of the charging station in the network. The suggested method has been implemented on MATLAB platform and tested on a practical distribution network with 40 buses. Outcomes are encouraging and the methodology may be applied to solve similar problems for practical systems
... For example, ref. [33] found that transport hubs, parking spaces, and urban points of interest were important aspects to station selection through the use of a spatial model function and stakeholder interviews. Other studies regarding this topic even took an optimization approach, such as [34]. Here, a gray wolf optimization algorithm based off a Markov chain network model was proposed with the objective to maximize net profit in order to determine charging station locations. ...
With the proliferation of vehicular mobility traces because of inexpensive on-board sensors and smartphones, utilizing them to further understand road movements have become easily accessible. These huge numbers of vehicular traces can be utilized to determine where to enhance road infrastructures such as the deployment of electric vehicle (EV) charging stations. As more EVs are plying today’s roads, the driving anxiety is minimized with the presence of sufficient charging stations. By correctly extracting the various transportation parameters from a given dataset, one can design an adequate and adaptive EV charging network that can provide comfort and convenience for the movement of people and goods from one point to another. In this study, we determined the possible EV charging station locations based on an urban city’s vehicular capacity distribution obtained from taxi and ride-hailing mobility GPS traces. To achieve this, we first transformed the dynamic vehicular environment based on vehicular capacity into its equivalent urban single snapshot. We then obtained the various traffic zone distributions by initially utilizing k-means clustering to allow flexibility in the total number of wanted traffic zones in each dataset. In each traffic zone, iterative clustering techniques employing Density-based Spatial Clustering of Applications with Noise (DBSCAN) or clustering by fast search and find of density peaks (CFS) revealed various area separation where EV chargers were needed. Finally, to find the exact location of the EV charging station, we last ran k-means to locate centroids, depending on the constraint on how many EV chargers were needed. Extensive simulations revealed the strengths and weaknesses of the clustering methods when applied to our datasets. We utilized the silhouette and Calinski–Harabasz indices to measure the validity of cluster formations. We also measured the inter-station distances to understand the closeness of the locations of EV chargers. Our study shows how CFS + k-means clustering techniques are able to pinpoint EV charger locations. However, when utilizing DBSCAN initially, the results did not present any notable outcome.
... But, the DN parameters are overlooked in [7,8]. Recognizing the importance of integrating both road and distribution network, researchers in [9,10] have incorporated parameters from both RN and DN to optimize CS allocation. Still, focusing solely on RN and DN parameters does not ensure optimal CS allocation without considering uncertainties. ...
The increase in electric vehicle sales has necessitated more charging stations. However, the converters in these stations impact the power quality of the network by generating harmonics, which must be maintained within specified limits according to IEEE 519 standard. Hence, this paper focuses on optimal allocation of electric vehicle charging stations (EVCSs) while ensuring the satisfaction of power quality and other constraints of the network. The power filters are also placed optimally, keeping their installation costs reasonable, when optimal allocation of EVCSs alone does not resolve the power quality issues. The problem is formulated as a multi-objective problem. The effectiveness of the proposed mathematical model is validated on a practical 40-bus superimposed road and distribution network. To perform the power quality analysis, harmonic spectrum data of a practical EVCS is captured with the help of a power quality analyzer. The optimization is conducted using the marine predator algorithm (MPA) in MATLAB. The best non-dominated solution is identified using the interactive fuzzy satisfying (IFS) method. The outcomes show that the proposed approach is effective and is capable of evaluating the location of charging stations for any practical distribution network, keeping power quality constraints within limit.
... Metaheuristic algorithms are designed to generate high-quality solutions from a random population. The generation takes inspiration from natural system behaviours and continues until a specific termination condition is fulfilled 76 . GWO is based on three key steps i.e., surrounding prey, hunting, and sand attacking prey. ...
This research suggests a robust integration of artificial neural networks (ANN) for predicting swell pressure and the unconfined compression strength of expansive soils (PsUCS-ES). Four novel ANN-based models, namely ANN-PSO (i.e., particle swarm optimization), ANN-GWO (i.e., grey wolf optimization), ANN-SMA (i.e., slime mould algorithm) alongside ANN-MPA (i.e., marine predators’ algorithm) were deployed to assess the PsUCS-ES. The models were trained using the nine most influential parameters affecting PsUCS-ES, collected from a broader range of 145 published papers. The observed results were compared with the predictions made by the ANN-based metaheuristics models. The efficacy of all these formulated models was evaluated by utilizing mean absolute error (MAE), Nash–Sutcliffe (NS) efficiency, performance index ρ, regression coefficient (R²), root mean square error (RMSE), ratio of RMSE to standard deviation of actual observations (RSR), variance account for (VAF), Willmott’s index of agreement (WI), and weighted mean absolute percentage error (WMAPE). All the developed models for Ps-ES had an R significantly > 0.8 for the overall dataset. However, ANN-MPA excelled in yielding high R values for training dataset (TrD), testing dataset (TsD), and validation dataset (VdD). This model also exhibited the lowest MAE of 5.63%, 5.68%, and 5.48% for TrD, TsD, and VdD, respectively. The results of the UCS model’s performance revealed that R exceeded 0.9 in the TrD. However, R decreased for TsD and VdD. Also, the ANN-MPA model yielded higher R values (0.89, 0.93, and 0.94) and comparatively low MAE values (5.11%, 5.67, and 3.61%) in the case of PSO, GWO, and SMA, respectively. The UCS models witnessed an overfitting problem because the aforementioned R values of the metaheuristics were 0.62, 0.56, and 0.58 (TsD), respectively. On the contrary, no significant observation was recorded in the VdD of UCS models. All the ANN-base models were also tested using the a-20 index. For all the formulated models, maximum points were recorded to lie within ± 20% error. The results of sensitivity as well as monotonicity analyses depicted trending results that corroborate the existing literature. Therefore, it can be inferred that the recently built swarm-based ANN models, particularly ANN-MPA, can solve the complexities of tuning the hyperparameters of the ANN-predicted PsUCS-ES that can be replicated in practical scenarios of geoenvironmental engineering.
... This collaborative exploration helps them to overcome the disadvantages of single-solution approaches. Some of the popular PBMA algorithms are Genetic Algorithm (GA) [86], [87], [88], [89], [90], [91], Differential Evolutionary Algorithm (DE) [92], Harmony search [93], [94], Ant Colony Optimization (ACO) [95], [96], Artificial Bee Colony Algorithm (ABC) [97], Particle Swarm Optimization (PSO) [98], [99], [100], [101], [102], Grey Wolf Optimizer (GWO) [103], [104], Firefly Algorithm [105][105], Cuckoo Optimization Algorithm (COA) [106], Gravitational Search Algorithm (GSA) [107], Artificial Hummingbird Algorithm (AHA) [108], , Whale Optimization Algorithm (WOA) [109], Grasshopper Optimization Algorithm (GOA) [110], Artificial Fish Swarm Algorithm (AFS) [111], Chicken Swarm Optimization (CSO) [112], Teaching Learning-Based ...
... Regression analysis aims to predict the continuous value of a target variable based on the observed values of one or more independent variables. This involves [89] Charging capacity maximization, Power loss reduction [90] ▪Differential Evolution (DE) EV battery swapping station placement [92] →Nature Inspired ▪Artificial Bee Colony (ABC) Optimal power utilization [97] ▪Ant Colony Optimization (ACO) EV route optimization [95], [96] ▪Artificial Fish Swarm (AFS) Network loss minimization [111] Operational cost minimization [110] ▪Gravitational Search Algorithm (GSA) Power loss minimization [107] ▪Grey Wolf Optimizer (GWO) Operational cost minimization [103] EV charging station placement [104] ▪Harmony Search (HS) Unit Commitment [93] EV charging station planning [94] ▪Particle Swarm Optimization (PSO) ...
The transportation sector is one among the key sources of greenhouse emissions (GHGs) leading to climate change and global warming. Energy transition through electrified transportation is one of the solutions to tackle the issues. Electric vehicles (EVs) offer significant environmental and economic advantages against the conventional internal combustion engine (ICE) vehicles. EVs are called mobility loads and their connectivity to the utility grid for charging is unpredictable. The large penetration of such unpredictable loads into the utility grid will lead to undesirable impacts on the utility service. This paper highlights the importance of managing and optimizing the charging schedules. The optimization of EV charging has diverse aspects, and the perspectives of EV charging differ among consumers, aggregators, and utility services. Proper planning and management of EV charging is essential to achieve harmony amongst these stakeholders. A comprehensive review on the objectives of electric vehicle charging optimization from various perspectives is presented and discussed in this paper. EV charging optimization techniques including mathematical programming, meta heuristics algorithms and machine learning techniques are explored. The main objectives, constraints, strength, and limitations of different charging optimization techniques are analyzed in detail. A brief discussion on the communication strategies for data exchange in EV charging framework is presented and the need for a communication security constrained EV charging scheduling is also emphasized.
... There have been many studies in recent years, dedicated to the large-scale deployment of charging stations. Some of them were mainly focused on the best allocation of EV stations in the grid [7], [8], others on the best battery load shape to meet the sustainable energy supply or off-peak hours [9], [10]. In this paper the EV charging problem is discussed from both perspectives, considering the personal needs of an EV owner, as well as the requirements of the grid. ...
The extensive penetration of distributed energy resources (DERs), particularly electric vehicles (EVs),
creates a huge challenge for the distribution grids due to the limited capacity. An approach for smart
charging might alleviate this issue, but most of the optimization algorithms has been developed so far
under an assumption of knowing the future, or combining it with complicated forecasting models. In
this paper we propose to use reinforcement learning (RL) with replaying past experience to optimally
operate an EV charger. We also introduce explorative rewards for better adjusting to environment
changes. The reinforcement learning agent controls the charger’s power of consumption to optimize
expenses and prevent lines and transformers from being overloaded. The simulations were carried
out in the IEEE 13 bus test feeder with the load profile data coming from the residential area. To
simulate the real availability of data, an agent is trained with only the transformer current and the local
charger’s state, like state of the charge (SOC) and timestamp. Several algorithms, namely Q-learning,
SARSA, Dyna-Q and Dyna-Q+ are tested to select the best one to utilize in the stochastic environment
and low frequency of data streaming
... Therefore, it is necessary to optimize the allocation of CS so that the amounts to be paid by EV drivers are viable, as explained in Refs. [22,23]. In Ref. [22], an optimized combination of chargers is proposed to manage the charging level and, at the same time, minimize the installation costs of charging stations. ...
... Few of the research works carried out considering uncertainties are discussed below. Uncertainties are considered in [16] for optimal CS allocation using the Markov-Chain-based stochastic model in the road network considering traffic flow but without realizing the electrical network. The cost of CS infrastructure is minimized by considering uncertain driving patterns for placement of fast CS using Monte-Carlo simulation [17]. ...
... (14) here, is the estimated location, is the mean and is the standard deviation k th uncertain variable. is calculated by (15), (15) here, is the skewness of the k th uncertain variable and is calculated by (16), (16) here, is the expectation value [23] obtained using (17), is the individual value considered while forming the probability density function calculated by (18) and is probability density function [4,20,23] value of calculated using (19). (17) ...
... (14) here, is the estimated location, is the mean and is the standard deviation k th uncertain variable. is calculated by (15), (15) here, is the skewness of the k th uncertain variable and is calculated by (16), (16) here, is the expectation value [23] obtained using (17), is the individual value considered while forming the probability density function calculated by (18) and is probability density function [4,20,23] value of calculated using (19). (17) ...