Client: Decentralized Administration of Crete

Decentralized Administration of Crete is one of the seven decentralized administrations of Greece, solely consisting of the region of Crete. Its seat is in Heraklion.

It has under management and operation the Stalida tunnel which is a two direction tunnel with 2 lanes and has length  417 m, the maximum width is 11.5 m,  and the working height is 5.0 m.
The tunnel is equipped with the following electromechanical equipment:

• Electric lighting installation of tunnel and outdoor section
  
• Automatic vehicle height control system, visibility & air quality monitoring (CO, NO).
• Automatic fire detection system and fire extinguishing installation.
• Emergency telephone installation inside the tunnel.
• Electricity supply substation and standby generator pair (H/Z) 250KVa.
• Electricity supply substation and standby generator pair (H/Z) 250KVa.
• Electricity supply substation and standby generator pair (H/Z) 250KVa.
  ‍

The need

The Goritsa Tunnel was constructed in 2003 and all the automation system were obsolete and no properly functional with lot of issues in maintenability. The upgrade of the system  was a major need and Extrabit was selected and awarded the upgrade of the TMS.

Where

IntelliLight was put on full scale development as part of a project by Olympia Odos Concession Company SA (https://www.olympiaodos.gr).
The project was implemented on the Elefsis – Patras more than 190km of highway controlling the street lighting which consist of 30 intersections and more than 8000 lighting fixtures.

Key Technical Features

Assets Under Management (AuM): 8000 lighting fixtures
Machine Learning Algorithms: Utilizes advanced algorithms to predict and adapt to traffic patterns.
Predictive Analytics: Anticipates vehicular flow, enabling proactive adjustments to lighting conditions.
Real-time Monitoring: Provides continuous data streams for instant insights aboutthe road traffic condition.
Energy-efficient Controls: Dynamically adjusts lighting levels for optimal energy consumption.
Explore Technical Insights: Delve into the technical intricacies of IntelliLight, from machine learning algorithmsto real-time data analytics. Uncover how predictive analytics redefine street lightingthe era of smart cities.

Using machine learning algorithms, inputs are processed, and an accurate dimming decision is directed to the dimming controllers.

Final deliverables

• Retrieve and process traffic volume data originating from the inductive loop detectors.
• Predict the traffic volume in intervals of 15 minutes for the following four days.
  Receive traffic related incidents from a video incident detection system installed on the I/C.
• Receive meteorological alarms such as heavy rain and low visibility though a newly installed meteorological station
• Classify the predicted traffic volume to predefined dimming levels and send the output to the dimming controllers
• React to external events and raise the dimming in cases of incidents or bad weather conditions

The results exceeded the original expectations, with a prediction accuracy of more than 96% in a four day period and more than 90% for predictions in a 30 minute window. Moreover, the system was able to consistently recognize external events and respond by raising the dimming levels.
‍

The figure presents the overall architecture of the system that was implemented as part of the pilot phase. Blue rectangles depict the processes that were developed whereas the yellow rectangles represent existing infrastructure. The glue logic was implemented by building custom RESTful APIs that organized and presented in a meaningful way the data to the required components.

The modularity of the system allowed us to cover additional requirements from the highway operator such as dimming in predefined levels instead of linear dimming. Specifically, dimming decisions were made on Annual Average Daily Traffic (AADT) limits. As a result, three plus one dimming levels were used:

• Contractual class which is the maximum possible brightness used on incident detection and bad weather conditions
• Nominal class (Initial dimming level)
• 1st Dimming class (lower traffic volume)
  
• 2nd Dimming class (minimum traffic volume)

Finally, in the event of low accuracy (less than 85% in a four day period) the machine learning algorithm enters a re-train mode that utilizes recent traffic data to adjusts its decision weights.

For the obligatory screenshots of the IntelliLight user interface, figure 3 depicts the predictions of the ML algorithm with red (30 minutes ahead) and green (1 hour ahead) lines aligned to the actual traffic with a blue line in a period of one day. The data are for the Ancient Corinth I/C. As it is evident, the predictions even for the pilot phase were quite accurate with the 1 hour being much closer to the real-time traffic than the 30 minute prediction.

The figure shows raffic prediction compared to actual traffic. The accuracy of the four day
prediction is also visible in the right gauge.

Figure 4 presents the final dimming decision for an uneventful night. The output is enabled after a specified time in the afternoon and is disabled in early morning. As it is evident from the diagram, traffic was predicted to rapidly decrease after 23:00 and hence the dimming was lowered to the minimum allowed class (2nd dimming class) at approximately 23:30. On the contrary, traffic was predicted to rapidly increase at 6:00 in the morning and as a result IntelliLight proactively increased the dimming to the Nominal class at 5:30.