Navigating the New Energy Era: AI’s Impact on Hybrid Systems and Electric Vehicles
By Yuhui Gan
Artificial Intelligence (AI) technologies are revolutionizing the energy management landscape, enhancing efficiency and sustainability.
The accelerated growth of the hybrid and electric vehicle (EV) market is a multifaceted phenomenon, fueled by heightened environmental awareness, groundbreaking technological advancements, including battery technology innovations, supportive government incentives and regulations, increasing consumer demand, and significant cost reductions. This surge in interest, particularly from corporations seeking greener alternatives to petrol, positions EVs at the forefront of the eco-friendly movement. Unlike their petrol counterparts, EVs run on batteries, leading to zero emissions from exhaust — a pivotal factor, especially when considering the sources of electricity generation. This article explores the transformative role of Artificial Intelligence (AI) in this evolving landscape, emphasizing its synergy with advanced technologies like heuristic-based Hopfield neural networks, smart charging systems, and blockchain is revolutionizing the energy management landscape, enhancing efficiency and sustainability in this evolving sector.
AI in Hybrid Power Systems
Veerapandiyan Veerasamy (2022) brought up an innovative approach to optimizing hybrid power systems using AI is a design of a self-adaptive Proportional-Integral-Derivative (PID) controller, enhanced by a heuristic-based recurrent Hopfield neural network (HNN) which allows for more precise and efficient management of fluctuating power demands in hybrid systems than traditional PID controllers. This system is applied to Automatic Load Frequency Control (ALFC) in hybrid power systems, a crucial aspect for maintaining stability and efficiency in power grids. The approach tackles the control problem as an optimization task, aimed at minimizing the Lyapunov function. The HNN dynamically adapts to changes, such as varying load demands, making it highly effective for managing modern power networks that incorporate green energy technologies and electric vehicles.
A Hopfield Neural Network (HNN) is a form of recurrent artificial neural network that serves as an associative memory system with binary threshold nodes, commonly used for pattern recognition and storing and recalling information. In this case, it would adapt and learn from the system’s operational data efficiently and produce more accurate predictions and control actions.
Automatic Load Frequency Control (ALFC) is vital for balancing power supply and demand, ensuring a stable frequency in the power system. The AI-driven approach proposed in the paper allows for more dynamic and real-time adjustments to load variations, which is particularly challenging in hybrid systems consisting of diverse energy sources like wind, solar, and conventional fuels.
AI in Hybrid Electric Vehicles
AI-driven improvements in energy management system and vehicle performance play a key role in accelerating the adoption of hybrid electric vehicles (HEVs) and could be expanded to EVs. Harsh Jondhle (2023) provided an EMS strategy of advanced energy management system for HEVs based on a Convolutional Neural Network (CNN) whose weight was fine-tuned by a Predator Probability-Based Squirrel Search Optimization (PP-SSO) Algorithm. This tuning enhances the model’s accuracy in predicting the vehicle’s speed and driving behavior, thereby contributing to more effective and efficient energy management in HEVs. The CNN model is utilized to analyze various parameters like the state of charge, voltage, and current of the battery, ultracapacitor (UC), and fuel cell. This analysis includes the vehicle’s speed, acceleration, and driving behavior, helping optimize the energy distribution and efficiency of the HEV, ultimately enhancing battery life and overall vehicle performance. In addition, the strategy also contributes to a reduction in greenhouse gas emissions, aligning with environmental sustainability goals.
Blockchain Technology in Power Systems
Blockchain technology offers a promising solution for handling the complexities in electrical power grids, particularly with the integration of intermittent renewable energy sources, Distributed Energy Resources (DERs), and smart grid concepts, especially when it is incorporated with smart contract. Its potential in smart grids in decentralized Peer-to-Peer (P2P) systems, is notable, particularly when combined with AI and Machine Learning (ML) (Malla et al., 2022). They are capable of not only creating and executing contracts by conducting crucial analyses but also learning and evolving over time. This adaptability and learning capability make smart contracts highly effective in managing the complexities of modern power systems, addressing issues like scalability and security while ensuring efficient and reliable energy management.
However, making peer history records public in such systems raises significant privacy concerns, potentially deterring peer participation. An alternative is to use a centralized, trusted intermediary for transaction validation, but this introduces a risk of a single point of failure. Thus, balancing transparency, privacy, and security remains a key challenge in leveraging blockchain for power grid management.
While blockchain technology has not yet been implemented in energy systems, it holds the potential to create a secure framework for smart grid transactions. In the future, this technology, coupled with AI’s ability to predict and manage energy loads and distribution, could significantly enhance both the security and efficiency of smart grid operations.
In conclusion, AI’s predictive and analytical capabilities, combined with blockchain’s secure and transparent data management, pave the way for more efficient, reliable, and sustainable energy systems. The combination of these technologies heralds a new era in energy management. We are moving towards an ecosystem where energy systems are not only more efficient and reliable but also more user-centric and sustainable. This integration has the potential to revolutionize not just how we manage energy, but also how we interact with our environment, contributing to a greener and more sustainable future.
Author
Yuhui Gan is a member of the KTH AI Society and, a student in Information and Communication Technology at the KTH Royal Institute of Technology. You can reach her on LinkedIn or by email at yuhui@kthais.com.
Reference
Harsh Jondhle, Anil Nandgaonkar, Nalbalwar, S. L., & Sneha Jondhle. (2023). An artificial intelligence and improved optimization-based energy management system of battery-fuel cell-ultracapacitor in hybrid electric vehicles. Journal of Energy Storage, 74, 109079–109079. https://doi.org/10.1016/j.est.2023.109079
Malla, T. B., Bhattarai, A., Parajuli, A., Shrestha, A., Chhetri, B. B., & Chapagain, K. (2022). Status, Challenges and Future Directions of Blockchain Technology in Power System: A State of Art Review. Energies, 15(22), 8571. https://doi.org/10.3390/en15228571
Veerapandiyan Veerasamy, Wahab, A., Ramachandran, R., Mohammad Lutfi Othman, Hashim Hizam, Jeevitha Satheesh Kumar, & Xavier, A. (2022). Design of single- and multi-loop self-adaptive PID controller using heuristic based recurrent neural network for ALFC of hybrid power system. Expert Systems with Applications, 192, 116402–116402. https://doi.org/10.1016/j.eswa.2021.116402
