Smart Scheduling Algorithm Research Articles

Prediction of EV Charging Behavior using BOA-based Deep Residual Attention Network

In smart city applications, electric vehicles (EVs) are rapidly gaining popularity due to their ability to help cut down on carbon emissions. Numerous environmental conditions, including terrain, traffic, driving style, temperature, and so on, affect the amount of energy an EV needs to operate. However, the burden on power grid infrastructure from widespread EV deployment is one of the biggest obstacles. Smart scheduling algorithms can be used to handle the rising public charging demand. Scheduling algorithms can be improved using data-driven tools and procedures to study EV charging behaviour. Predictions of behaviour, including temperature, departure time, and energy requirements, have been the focus of research on past charging data. Weather, traffic, and surrounding events are all factors that have been mostly ignored but which could improve representations and predictions. The DRA-Net, or Deep Residual Attention Network, was developed by the researchers and is used to recognize EV charging patterns. To minimize data loss, the Res-Attention component utilized tighter connections and smaller convolutional kernels (3 x 3). In addition, an Artificial Butterfly Optimisation Algorithm (BOA) model is used to fine-tune the DRA-Net's hyper-parameters. We highlight the significance of traffic and weather info for charging behaviour predictions, and the study's experimental forecasts show a considerable improvement over prior work on the same dataset. The future of electric vehicle (EV) research has been mapped out thanks to in-depth study, and as a result, EVs will soon significantly impact the auto industry.

A smart management system of electric vehicles charging plans on the highway charging stations

Electric vehicles (EVs) are seen as one of the principal pillars of smart transportation to relieve the airborne pollution induced by fossil CO2 emissions. However, the battery limit, especially where the journey is with a long-distance road remains the most formidable obstacle to the large-scale use of EVs. To overcome the issue of prolonged waiting charging time due to the large number of EVs may have a charging plan at the same charging station (CS) along the highway, we propose a communication system to manage the EVs charging demands. The architecture system contains a smart scheduling algorithm to minimize trip time including waiting time, previous reservations and energyare needed to reach the destination. Moreover, an automatic mechanism for updating reservation is integrated to adjust the EVs charging plans. The results of the evaluation under the Moroccan highway scenario connecting Rabat and Agadir show the effectiveness of our proposal system.<br /><div> </div>

Prediction of EV Charging Behavior Using Machine Learning

As a key pillar of smart transportation in smart city applications, electric vehicles (EVs) are becoming increasingly popular for their contribution in reducing greenhouse gas emissions. One of the key challenges, however, is the strain on power grid infrastructure that comes with large-scale EV deployment. The solution to this lies in utilization of smart scheduling algorithms to manage the growing public charging demand. Using data-driven tools and machine learning algorithms to learn the EV charging behavior can improve scheduling algorithms. Researchers have focused on using historical charging data for predictions of behavior such as departure time and energy needs. However, variables such as weather, traffic, and nearby events, which have been neglected to a large extent, can perhaps add meaningful representations, and provide better predictions. Therefore, in this paper we propose the usage of historical charging data in conjunction with weather, traffic, and events data to predict EV session duration and energy consumption using popular machine learning algorithms including random forest, SVM, XGBoost and deep neural networks. The best predictive performance is achieved by an ensemble learning model, with SMAPE scores of 9.9% and 11.6% for session duration and energy consumptions, respectively, which improves upon the existing works in the literature. In both predictions, we demonstrate a significant improvement compared to previous work on the same dataset and we highlight the importance of traffic and weather information for charging behavior predictions.

An Efficient Formal Modeling Framework for Hybrid Cloud-Fog Systems

Advanced communication technologies (e.g., 5G) probably elicit a complete change of network and its applications. For example, a growing number of services begin shifting from central clouds to vast mobile devices, as the hybrid use of cloud and fog computing technologies can provide enhanced quality of service and efficient utilization of resources. However, to design such complex hybrid cloud-fog (HCF) systems, it remains a challenge to implement time-consuming modeling and inefficient evaluation in its early design stage based on the conventional simulation or practical experimentation. Therefore, how to reduce design cost and improve development efficiency becomes a crucial issue in the process of designing large-scale HCF systems. To address the issue, this paper proposes a novel modeling framework for large-scale HCF systems based on a high-level formal language, i.e. performance evaluation process algebra (PEPA). Toward the key components of an HCF system, the proposed framework includes three crucial model prototypes: compositional architecture model, abstract communication model and scheduling model. Moreover, the scheduling model is designed with a novel smart scheduling scheme that integrates two atomic scheduling algorithms and a decision module to make an efficient algorithm selection. The smart scheduling algorithm can well adapt the HCF systems by yielding stable and fast response to end-users, particularly under dynamical system conditions. Finally, the framework is the first research achieving the full potential of formal methods to implement industry-level modeling and evaluation.

Machine Learning Approaches for EV Charging Behavior: A Review

As the smart city applications are moving from conceptual models to development phase, smart transportation is one of smart cities applications and it is gaining ground nowadays. Electric Vehicles (EVs) are considered one of the major pillars of smart transportation applications. EVs are ever growing in popularity due to their potential contribution in reducing dependency on fossil fuels and greenhouse gas emissions. However, large-scale deployment of EV charging stations poses multiple challenges to the power grid and public infrastructure. To overcome the issue of prolonged charging time, the simple solution of deploying more charging stations to increase charging capacity does not work due to the strain on power grids and physical space limitations. Therefore, researchers have focused on developing smart scheduling algorithms to manage the demand for public charging using modeling and optimization. More recently, there has been a growing interest in data-driven approaches in modeling EV charging. Consequently, researchers are looking to identify consumer charging behavior pattern that can provide insights and predictive analytics capability. The purpose of this article is to provide a comprehensive review for the use of supervised and unsupervised Machine Learning as well as Deep Neural Networks for charging behavior analysis and prediction. Recommendations and future research directions are also discussed.

Virtual Budget: Integration of electricity load and price anticipation for load morphing in price-directed energy utilization

A methodology is presented for price-directed demand response steered by market signals and anticipation models. Electricity prices vary dynamically and with substantial volatility in a way that ceteris paribus (ceteris paribus is a Latin phrase meaning “with all other conditions remaining constant”) prices rise as the distance between available power and peak demand is reduced. Price can thus be a factor in overall load pattern morphing, that is, automated decision-making by energy management systems controlling devices consuming electricity. Load and price forecasting are key technologies for market participants to make optimal decisions regarding their demand response. To this end, this paper develops the Virtual Budget approach that couples price and load forecasting, and allows automated morphing of a user's electricity consumption. In particular, the Virtual Budget leverages price forecasts to modify the initial forecasted load demand via smart scheduling algorithms. The performance of the Virtual Budget is evaluated on a set of real historical data, and the reported results demonstrate that its use may lead to savings in electricity consumption costs.

Proposal for Standardization of Green Information Centric Networking Based Communication Utilizing Proactive Caching in Intelligent Transport System

Nowadays, Internet is mostly used to access content and users are also interested in content, instead of location. Information-Centric Networking (ICN) has drawn substantial consideration over past few years because its appearance introduced a new potential Internet architecture (deploying extensive cache structure to distribute and deliver information). Though ICN has undoubtedly become a promising Future Internet architecture to solve current host-centric Internet problems, conventional ICN design still has its own drawbacks. These include caching, routing, etc., particularly mobility issue and energy-efficiency problem due to additional energy consumption for Content Routers’ caching capability. In order to address the energy flaw and enhance the mobility performance of ICNArchitecture, in this article, we have designed, evaluated and proposed a wireless Information Centric Networking (ICN) based access model within the context of Intelligent Transport System (ITS) for ICN standardization procedure. We take into consideration the fact that number of mobile devices increases rapidly day by day as well as the public transportation (e.g. train, bus, etc) becomes more popular nowadays. Besides, mobile users may ask for different content interests via Internet during the period of time when they are on public transport vehicle. We then propose a wireless communication topology in ICN for the ITS by utilizing the smart scheduling algorithm with proactive-caching based strategy to deal with possible and practical situations of commuters (mobile content users). In our scheme, the dedicated content provider proactively sends appropriate segments of requested content (based on chunk-level structure of content) to expected proximity Aggregation content nodes located at neighbor stations (future attachment points) on the moving path of public transportation vehicle. This working scheme substantially enhances the mobile user’s quality of experience and network performance in ICN. Moreover, the proposed ICN based system adapts the network nodes to their optimized network utilization values according to content popularity by conducting cross-layer optimization. This mechanism provides mobile users more reliable and effective Green Information and Communication Systems (ICS) when they travel with public transportation. Therefore, the proposal integrates Green networking into ICN by combining the benefits of innovated rate-adaptivity and proactive-caching based schemes for achieving highly scalable, reliable and energy-efficient network performance in future transportation Information-centric communication system with data-awareness. In addition, we identify that there are currently various ICN-based models and emphasize the need of an official ICN international standard for wireless communication in general and transportation system in particular. Following, by evaluating the proposal, we show that the proposed cross-layer wireless content access model in ICN for ITS is a promising and feasible contribution for the standardization process of ICN.

Smartphone Traffic Engineering for Energy Efficient Communications: Design and Experimental Evaluation

Power management has increased its significance in mobile communications along with the growing population of mobile users and wireless connectivity. In this paper we propose a smart scheduling algorithm in Android network kernel to increase power efficiency. As periodically-updating applications start sync with a DNS query packet, we defer the packets in order to make these applications synchronize from smaller time difference to finally simultaneously. To implement the idea, we design the algorithm for two or more applications in this paper. This algorithm is composed of several mechanisms: approaching, aligning, and maintaining. By experiments we show the practicability and the comparison between the energy saving ratios in different scenarios.