An Artificial Intelligence (AI) based approach towards efficient City Management
The world is undergoing an unprecedented pace of urbanization, and if present trends continue, the world urban population will rise by about 72% in the next 4 decades. While the reasons for this rapid urban expansion are many, it is primarily driven by two entities with complementary needs: cities, on one end, to attract the best-skilled people and enterprises; and people, on the other end, by their preference to migrate to cities that provide a better quality of life.
This rapid scale of urbanization will need smarter, sustainable cities that are able to effectively and efﬁciently manage city utilities and services for its citizens. Electric grids, water distribution systems, transportation systems, communication infrastructure, waste treatment plants, commercial buildings, hospitals, homes, and education centers are existing vital facilities that shape the livability standard of a city.
There is a general consensus that an efﬁcient and effective management of these existing and possibly new city systems requires integration via a platform based approach needed for transforming a traditional city into a digital city. However, value creation through integration can only be achieved when data generated by tens of thousands of sensors installed in the city across vehicle parking lots, on public street lighting poles, security surveillance cameras, in water, power, gas and irrigation transmission lines are analyzed using an algorithmic approach to provide actionable cross vertical insights to the city administration about new use cases for managing the city infrastructure in a much more efficient and cost effective manner.
The real time and near real time data sets such as vehicle speeds, travel times, turning movement, counts by bike, vehicle class and street classification will complement the historical open data available from the city as well as other third party data sources. For example, for the evaluation of proposed transportation improvement projects, such analytics will result in more accurate performance metrics such as vehicle mile traveled, annual congestion cost, average commute trip time, vehicle-hours delay and emergency response time. Other examples of actionable insight obtained from cross vertical analytics performed on sensor data are by drawing correlations between:
1. Public street lighting with CCTV surveillance and people movement to reduce crime
2. The rate of movement of noxious/poisonous gas emissions due to industrial accidents and wind speed/direction thereby allowing for effective and timely implementation of citizen emergency evacuation plans
3. The traffic density on main arterial roads and dynamic management of traffic signs as well as implementing automated road closures / one way with display of information to motorists via variable message signs
4. Volume of water supply and demand to detect water leaks/theft based on historical/seasonal water consumption data
5. Movement and density of people in a shopping/tourist district and augmentation of public transportation services as well as dynamic crowd management to prevent stampedes and other such disasters
To conclude, urban analytics is an evolving field and will play a major role in helping cities develop more cost-effective and data driven policy decisions to help tackle urban challenges in real time or near real time. The result will be a more efficient and sustainable city.