Link Entities

Proposer: T2 (Slovenia)

Most smart city solutions focus on optimizing infrastructure, traffic, and energy, but what if we designed cities that actively improve the daily well-being of their residents in real time?

This challenge seeks AI-driven solutions that leverage real-time urban data (from IoT sensors, wearables, public services, and social dynamics) to dynamically adapt the urban environment and enhance quality of life.

Three possible focus areas:

1. Real-Time Personalized Urban Experience: AI systems that optimize individual commuting routes or public space recommendations based on environmental and personal well-being data (e.g., suggesting the least stressful walking route or adjusting street lighting dynamically for comfort and safety).
2. Adaptive Public Spaces: AI models that analyze real-time movement, crowd density, and air quality to dynamically reconfigure urban spaces (e.g., automatically adjusting flexible-use streets, pedestrian areas, green zones, etc.)
3. Urban Well-Being Index: AI-powered, privacy-preserving models that measure and predict well-being levels in city districts based on noise, pollution, weather, social activity, and mobility patterns—enabling cities to intervene proactively.

The end goal is to create AI-driven urban environments that actively respond to human needs in real time, making cities healthier, happier, and more adaptable to the well-being of their residents.

Proposer: Bosch (Hungary)

Overview:

Explore the feasibility and efficiency of synchronizing the internal temperature regulation of the Bosch Budapest Innovation Campus with external weather conditions. The primary objective is to enhance energy efficiency and improve employee comfort by dynamically adjusting the heating and cooling systems based on real-time and forecasted weather data.

Problem Statement:

Sudden changes in external weather conditions can significantly affect the internal temperature of the campus. Rapid increases or decreases in temperature can result in delays in the adjustment of internal heating or cooling systems, leading to employee discomfort and inefficient energy usage. This challenge aims to address these issues by integrating external weather data into the campus's temperature management system.

Objectives:

• Energy Efficiency: Assess whether synchronizing internal temperature regulation with external weather conditions can lead to significant energy savings.
• Employee Comfort: Enhance employee comfort by ensuring a stable and optimal internal temperature, irrespective of external weather fluctuations.
• Climate Forecast Integration: Utilize climate forecasts to anticipate and prepare for sudden changes in weather, ensuring a proactive approach to temperature management.

Weather Forecast Integration:

Utilize municipal weather forecasts, which provide predictions up to 48 hours in advance. This data will be crucial in preparing the campus's temperature management system for sudden changes in weather, such as extreme cold or heat.

AI and Energy Savings:

Implement artificial intelligence to analyze and correlate external weather data with internal temperature requirements. The AI system will optimize energy usage by dynamically adjusting heating and cooling settings based on real-time and forecasted weather conditions.

Interface and Software:

The challenge involves integrating the temperature regulation system with software from a German company, DMS AG, and Bosch Rexroth. The PWA (Progressive Web App) display software from Bosch will be used to visualize and control the system. Additionally, the system will include a shading controller to adjust blinds based on sunlight intensity.

Correlation Analysis:

Conduct a thorough analysis of the correlation between external temperature and internal campus space temperature. This will involve collecting and analyzing data to determine the most efficient ways to synchronize the two.

Primary Goal:

The goal of this challenge is to calculate potential energy savings by implementing the new temperature regulation system. This will involve detailed analysis and comparison of energy usage before and after the integration of external weather data.