Search for: All records

Research on driving energy consumption (DEC) has become more popular due to the high adoption of electric vehicles (EVs). This research utilizes a comprehensive dataset from realworld driving data for one month in Mobile, Alabama. CAN bus data loggers were installed in the vehicle to collect dynamic data such as speed, acceleration, latitude, longitude, and altitude. The dataset contains approximately five thousand kilometers of driving distance and around one thousand individual trips. After calculating the driving energy, the time series data is presented and analyzed. Statistical techniques such as the Augmented Dickey-Fuller (ADF) test, Autocorrelation, Partial Autocorrelation and time series decomposition were implemented to evaluate the stationarity, correlation analysis and seasonality properties of the time series. The results showing the data stationarity with seasonality provide insights for predictive algorithms that can reshape vehicle-to-grid research. 

This study examines barriers and motivators for adopting electric vehicles (EVs) in South Alabama by extending the Diffusion of Innovation (DOI) framework. While the transition to EVs is a growing national trend, skepticism and limited exposure continue to slow diffusion in the region, and consumers view EVs as incompatible with their daily routines. EV adoption across South Alabama has lagged despite coordinated efforts by government agencies to develop EV infrastructure and the efforts of EV manufacturers to promote adoption. Results of a PLS-SEM analysis reveal that the Relative Advantages that EVs provide over traditional vehicles significantly predict Purchase Intentions, with Price Value serving as an antecedent, suggesting consumers see a long-term financial appeal despite higher upfront costs. However, environmental beliefs in the form of Biospheric Values did not translate into increased purchase intentions, as Environmental Relative Advantage failed to demonstrate a mediating effect. Among DOI attributes, Complexity acted as a barrier, while Trialability and Compatibility were motivators for adoption, particularly with the availability of test drives and adequate charging infrastructure. Social norms also shaped perceptions of Compatibility, showing peer influence can act as either a barrier or motivator to EV adoption. Findings underscore the need for targeted infrastructure investment as well as opportunities for hands-on experience to address consumer hesitancy. This study contributes to the understanding of EV market penetration and provides actionable insights for policymakers and stakeholders aiming to address geographic disparities in EV adoption. Future research should expand the study by including samples from similar regions. 

The increased use of renewable energy (RE) in residential settings is driving the demand for smart energy management systems (EMS) to optimally coordinate the purchasing and selling of power to the grid. Given the uncertain and volatile nature of RE and electricity consumers’ changing load behavior, the EMSs require accurate net load forecasting, which has become a tough challenge. Unlike prior approaches that might employ a single, fixed Long Short-Term Memory (LSTM) architecture for all data components regardless of their underlying complexities, the model proposed in this paper introduces a specifically designed advanced hybrid machine-learning algorithm for highly accurate net load forecasting in residential areas equipped with solar panels. This involves applying more complex architectures to high-frequency data components and simpler architectures for lower-frequency components. This tailored approach is crucial for optimizing network complexity and computational burden while maintaining or enhancing forecasting performance, leading to comparable accuracy with significantly shorter training times compared to fixed architectures. This paper provides brief descriptions of powerful forecasting tools to accurately predict different variables in power systems, and presents a case study of these models in different combinations. This paper further compares them across three different time resolutions of data, and discusses their characteristics and different evaluation metrics. Compared to other methods that have similar computational efficiency, the proposed model demonstrates superior accuracy as the time resolution of the input data increases in order to accommodate more intricate details in the RE generation and consumers’ load behavior.