Electric Vehicle User Behavior Analysis and Modelling and Infrastructure Planning
Agent-based Urban Simulation Model
Adoption and Impacts of Low-Carbon Technologies and Services
The development of smart cities contributes to inclusive growth, resilience, and global sustainability efforts, and thus plays a crucial role in advancing the Sustainable Development Goals (SDGs).
Prof. Chengxiang Zhuge, Assistant Professor from the Department of Land Surveying and Geo-informatics (LSGI) is leading the TIP research group focusing on Technology innovation, Infrastructure planning and Policy making in Smart Cities. They consider cities as complex systems and develop technologies and models to address urban issues based on artificial intelligence, simulation approaches and big data analytics. Recently, they are particularly interested in the TIP-related research topics in the mobility and residential sectors.
Topic 1: Electric Vehicle User Behavior Analysis and Modelling and Infrastructure Planning
Many cities are acting actively to electrify their transportation system towards a smart and sustainable mobility system. In 2024, electric vehicle (EV) sales in China surpassed 10 million units, accounting for 61% of global sales. The TIP group focuses on understanding EV user behavior and optimizing the layout and operation of charging infrastructure. From the behavioral perspective, they have developed an EV big data analytical framework based on large-scale real-world trajectory data from over 100,000 EV users. This framework can help to uncover the underlying mechanisms behind EV users’ travel, parking, and charging decisions.
To support short-term charging demand forecasting, the TIP group integrate deep learning techniques with the spatiotemporal patterns of charging demand. Their models enable accurate short-term predictions of charging needs at the station or regional level, thereby supporting more efficient infrastructure operations and management. For infrastructure deployment, the TIP group propose a series of microsimulation-based optimization models considering multiple energy sources, vehicle types, facility types, and stakeholder objectives. These models can help to search for tailored solutions that balance factors such as system cost, carbon emissions, and operational efficiency. The case studies span a range of cities, including Hong Kong, Beijing, Shenzhen, and New York.
Topic 2: Agent-based Urban Simulation Model
As a typical complex system, city is composed of multiple interrelated and interdependent subsystems, including transportation, land use, energy, environment, population, and economy. Urban micro-simulation models have been increasingly used as decision support systems to explore such complex dynamic systems, enabling urban planners and policymakers to systematically evaluate the impacts of various planning strategies and policy interventions, anticipate long-term urban development patterns under different scenarios, and provide scientific evidence to support urban planning, policy making, and technology investment.
The TIP group has been developing an open-source agent-based urban simulation model, SelfSim. Compared with existing urban micro-simulation models, SelfSim is focused on simulating the impacts of sustainable technologies, policies, and infrastructures. Its modular framework allows for the integration of various low-carbon technology diffusion models and the social network evolution model. Based on open-source data, the TIP group has applied SelfSim in five global cities: Beijing, Shenzhen, London, Berlin, and New York. These city-scale scenarios allow for the simulation-based appraisal of a wide range of planning and policy strategies, offering decision support for sustainable urban development.
Topic 3: Adoption and Impacts of Low-Carbon Technologies and Services
In 2019, the buildings and transport sectors each accounted for 29% of global end-use energy consumption and contributed 19% and 7%, respectively, to direct energy-related greenhouse gas (GHG) emissions. Studies indicate that by 2050, demand-side measures could reduce GHG emissions from buildings and land transport by 66% and 67%, respectively.
The TIP group focuses on the adoption behaviors of low-carbon technologies and services within the transportation and residential sectors. Using urban big data analytics and agent-based simulation methods, the group investigates the mechanisms behind the interlinked adoption of emerging technologies and services, particularly within development of smart cities. These include autonomous vehicles, shared mobility, and new energy vehicles in the transport sector, as well as smart home technologies, smart heating/cooling systems, and energy-efficient lighting systems in the residential sector. Based on the empirical analysis and simulation modeling of adoption behaviors, the TIP group has further developed an integrated framework to assess their impacts from infrastructural, energy, environmental, and social perspectives.
