Artificial Intelligence-Based System for Integrated Optimization of Autonomous Electric Vehicle Fleets Across Transportation and Electricity Networks

Smart overview of the Invention

The patent describes a system utilizing artificial intelligence to optimize the allocation of autonomous electric vehicles (EVs) between transportation and electricity services. This system integrates real-time data such as energy forecasts, earth observations, and vehicle schedules to make informed decisions. Vehicle owners can input their availability, allowing the system to manage vehicle use efficiently through a hierarchical approach. This multi-objective optimization aims to balance revenue, energy costs, emissions, and battery health, thereby enhancing both transportation and grid stability.

Field and Background

This invention lies in urban mobility management, specifically focusing on AI-driven dynamic pricing, mapping, and scheduling of autonomous EVs. Current systems often overlook environmental impacts and multi-objective preferences, focusing mainly on distance and time. They lack advanced AI techniques like genetic algorithms that could optimize routes considering real-time conditions and emissions data. The growing use of EVs presents opportunities for integrating transportation with electricity grid management, yet existing systems operate in isolation, missing synergies.

Challenges and Needs

Existing vehicle fleet management systems do not fully exploit the dual role of EVs in transportation and electricity markets. They primarily optimize routes without considering grid services. Moreover, current demand response services are designed for stationary assets, ignoring the mobile nature of EVs. This fragmented management approach leads to missed optimization opportunities. An integrated system is needed to combine real-time emissions data, dynamic pricing, and multi-objective optimization for sustainable mobility and grid support.

System and Method

The system dynamically allocates EVs between transportation and grid services based on real-time data and owner schedules. It employs a hierarchical optimization approach using genetic algorithms to balance objectives like revenue, energy costs, and emissions. The system includes a computing device with programming instructions to acquire data, receive scheduling information, allocate vehicles, and manage financial transactions. It also provides alternative transportation options when vehicles are allocated to grid services.

Technical Implementation

The system's method involves acquiring data on transportation and electricity networks, receiving scheduling information, and implementing an optimization process across multiple time horizons. Objectives include revenue generation, energy cost minimization, and emissions reduction. The optimization process uses a genetic algorithm to satisfy vehicle and system constraints. Financial transactions are managed via a distributed ledger, and dynamic pricing is generated based on real-time emissions data. Machine learning models predict future conditions to enhance decision-making.