Banner01
We are a Digital Airport Company and we transform Airports and its related experiences through Digital Interventions with a strong service culture.

How data can augment the airport throughput


Author: Jasmeet Bhatia

Date: May 1, 2024

How data can augment the airport throughput

Introduction

An airport is a complicated system where disparate contributors (Airport Operators, Airlines, Govt Authorities, Security Agencies, Staff, and Passengers) actively participate in moving/transporting people and goods across the globe.

Today, airports are addressing increasingly complex operational challenges with exciting business and technological innovations. Smart digital investments demonstrate an attractive business case for airports, offering the potential to increase revenue and lower costs, at the same time, offer a great travel experience.

Airports are undergoing pivotal transformation, and digital tools are enabling new thinking, be it personalized advertising, enhanced passenger loyalty, or mobility for passengers.

Digital transformation at airports leverages multiple technology solutions, such as indoor geolocation, identity management, passenger flow management, data mining, artificial intelligence (AI), and automation & real-time monitoring of machines via the internet of things, to not just improve safety and security but also streamline their operations and enhance revenues.

Airports have achieved impressive efficiency gains by implementing digital technologies. Saving minutes of time per passenger processing time from terminal check-in to the security hold area by leveraging facial recognition technology, reducing minimum connecting times by accelerating baggage handling for selected priority bags, and reducing infrastructure costs by up to 10% through energy efficiency systems are just a few of the more prominent examples.

To make more out of available data, airports need to consolidate data, break the data silos, and form an open, interoperable, and collaborative system across participants and procedures. Harnessing the power of data, it is in the best interest of the airports to deploy full-fledged Digital Twins, not just for Airport Operations, but to also address sustainability needs through solutions for Infrastructure, Energy, and Water Management.

Deploying the digital twin breaks down information silos and helps access the right information at the right time, enabling situational awareness. Inspection data, work history, and extremely large datasets can be used in the context of a digital twin. Using extensive graphics and dashboards and real-time and reliable information helps to reduce the total cost of assets; better manage, make changes, and obtain accurate returns; and ensure better asset performance and return on investment (ROI).

To accomplish this, all the shortlisted airport-related data streams – from all participants together are required to bring in a single central data lake that is simultaneously accessible to airport stakeholders. This will create a single source of truth to refer to for airport operations. Actionable, real-time information on everything going on in the airport will be provided in dashboard views to everyone who needs to know so that well-informed and quick decisions can be made in a crisis.

The digital twin also carries the necessary tools for advanced prediction and simulation of future developments to which airport operators can then respond proactively. In other words, the twin delivers effective decision-support tools for everything from short-term scenarios to infrastructure expansion decisions.

Additionally, since data is already located in one virtual space, new use cases, and applications can be developed on the fly by all interested parties. Potentially, the digital twin of an airport could even be visualized in a 3D model that would be accessible via virtual or augmented reality.

The digital twin of an airport is a high-value use case that unlocks the full potential of data for airports – and aligns with the vision of smart airports of the future.

Data-driven technologies that airports use to improve performance and master current challenges

In line with Airport 4.0, there are several data-driven technologies that airports are using to improve performance and address current challenges. Some examples include:

  • Predictive maintenance: Airports leverage data analytics and machine learning to predict maintenance needs, enabling proactive addressing of potential issues before they arise. This reduces downtime and enhances overall operational efficiency.
  • Baggage tracking: Many airports employ RFID tags and other tracking technologies to enhance the accuracy and efficiency of baggage handling. This minimizes the occurrence of lost bags and enhances the overall customer experience.
  • Real-time surveillance and monitoring: Airports utilize various sensors and cameras for real-time surveillance and monitoring of the airport environment. This enhances safety and security and facilitates efficient management of airport operations.
  • Predictive analytics: Airports utilize data analytics to forecast demand for various airport services, such as parking and food and beverage. This optimization of resource allocation improves overall airport efficiency.
  • Customer experience optimization: Airports employ data analytics to enhance the customer experience by offering personalized recommendations for shopping and dining, real-time flight information, and tailored loyalty programs. This fosters increased customer satisfaction and loyalty.
  • Environmental sustainability: Airports utilize data analytics to optimize energy usage, reduce emissions, and implement sustainable practices, aiding in meeting sustainability goals and minimizing environmental impact.

Where are we at with the use of data to enhance airport ecosystems

The use of data to enhance airport ecosystems has made significant strides in recent years, with many airports adopting data-driven technologies to improve efficiency, safety, and customer experience. However, there is still room for growth and development in this area.

  • One challenge faced by airports is the integration and management of multiple data sources. Ensuring that data is accurate, up-to-date, and secure can be a complex and time-consuming task. Additionally, airports must consider privacy and regulatory issues when using data, aligning with region-specific data protection laws.
  • The need for skilled personnel continues to be a challenge to fully realize the benefits of a data-centric strategy. As the use of data expands within the airport ecosystem, there will be a growing demand for professionals with strong data analysis and management skills.
  • Another factor is the fear of losing control over data. Stakeholders may be hesitant to share data, fearing that it may lose value or be exploited for commercial purposes by other parties. Consequently, data sharing remains the exception rather than the norm.
  • Despite these challenges, the use of data to enhance airport ecosystems is expected to grow in the coming years. Advancements in data analytics and machine learning technologies will enable airports to leverage more powerful insights and predictions, enhancing operations and customer service. Moreover, with the emergence of low-code and no-code platforms, the scarcity of skills and talent may soon be addressed through the rise of citizen data scientists.

How data analytics can be used in the airport ecosystem

Decision-makers need to have clarity on the outcomes they seek. They must align their needs with an understanding of the power of data and how it can be harnessed in connected and complex environments. Data, especially in large sets, presents the opportunity to gain insights and take action in ways that would typically require extensive efforts to unlock. With the Internet of Things (IoT), this often involves gathering various types of data over time, such as temperature, humidity, vibration, and usage, and analyzing patterns. Statistical tools can then be used to better describe the data, compare different datasets, and discover correlations or causes of specific observations. Based on these insights, decision processes can be defined and automated through digital applications (software).

To illustrate, consider the example of a baggage handling system. By combining data collected through applications and IoT devices, a digital twin of the baggage handling system can be created. This digital twin can help optimize the operating process and identify bottlenecks, leading to improved efficiency and performance.

Typical Data Analytics Solution Architecture

Data analytics architecture refers to the framework and components that enable organizations to collect, store, process, and analyze large amounts of data. It typically involves several layers, including data acquisition, storage, processing, analysis, visualization, and reporting.

Here is an overview of the components that make up a typical data analytics architecture:

  1. Data sources: This includes the various sources of data that an organization collects, such as structured data from databases and applications, as well as unstructured data from social media, sensors, and other sources.
  2. Data acquisition: This involves collecting and ingesting data from various sources and preparing it for analysis. It may include processes like data cleansing, transformation, and enrichment.
  3. Data storage: This refers to the infrastructure used to store large amounts of data, including data warehouses, data lakes, and other storage systems.
  4. Data processing: This layer involves processing data to extract insights and value from it. It may include data mining, machine learning, and other techniques to identify patterns, predict trends, and make recommendations. Solutions such as Hadoop and Spark are commonly used for distributed computing and big data processing, while AI and ML tools like TensorFlow, Keras, and PyTorch are used for building and training neural networks.
  5. Data analysis: This involves analyzing data to gain insights and inform decision-making. It may involve the use of dashboards, reports, and other tools for visualizing and exploring data. Tools like Tableau and SAS are used for data visualization and business intelligence.
  6. Data visualization: This involves presenting data in a way that is easy to understand and interpret, using charts, graphs, and other visualizations. Programming languages like Python and R, as well as visualization libraries like D3.js, are commonly used for data visualization.
  7. Reporting: This involves generating reports and communicating findings to stakeholders. Solutions like Excel, Crystal Reports, SAP BI, and MicroStrategy are used for reporting and business intelligence purposes.

Overall, a well-designed data analytics architecture should empower organizations to effectively collect, store, process, and analyze large volumes of data. By leveraging this architecture, organizations can make informed, data-driven decisions and gain a competitive advantage in their respective industries.

Utilizing data’s full potential across interfaces on a unified, IoT platform

The Internet of Things (IoT) is permeating every aspect of our daily lives, from the vehicles we drive to the cities we live in, transforming how we shop and take care of ourselves. While the full potential of this innovation is yet to be explored, businesses and public offices can already harness its benefits by gathering vast amounts of data about customers and community residents.

The ability to collect and process insights in real-time holds immense power. However, this power also comes with a responsibility. Tech teams must approach data collection and management responsibly, prioritizing the design of reliable and secure application architectures.

In the realm of the Internet of Things, this often involves gathering various types of data over time, such as temperature, humidity, and vibration, and analyzing patterns. Statistical tools are then employed to better describe the data and compare different datasets using regression analysis to uncover correlations or causes of specific observations. With these insights in hand, decision processes can be defined and automated through digital applications (software).

To fully leverage the potential of data across interfaces within a unified Internet of Things (IoT) platform, several key considerations come into play:

  • Integration of data sources: An effective IoT platform should be capable of gathering and integrating data from diverse sources, including sensors, cameras, and other devices. This ensures a comprehensive and accurate understanding of the data being collected, facilitating informed decision-making.
  • Interoperability: Seamless communication and data exchange between the IoT platform and other systems and devices are essential. Interoperability enables integration with existing infrastructure and promotes a more cohesive and efficient ecosystem.
  • Security: Protecting data integrity and confidentiality is paramount in an IoT environment. Implementing robust security measures such as encryption, authentication, and access controls safeguards data from unauthorized access or manipulation, ensuring its trustworthiness and reliability.

By addressing these factors, organizations can effectively harness the full potential of data across interfaces within an integrated IoT platform. This empowers them to make better-informed decisions, optimize operations, and drive innovation in various domains.

Possible systems to be connected to an open IoT platform

Moving toward the vision of the airport’s digital twin

A digital twin serves as a virtual representation of a physical system or process, often constructed using data from sensors and other sources. In the context of airports, a digital twin can play a crucial role in simulating and optimizing various operational aspects, including baggage handling, ground handling, aircraft turnaround, and maintenance. Utilizing the IoT operating system as its foundation, the digital twin forms an open and innovative airport ecosystem, facilitating end-to-end integration of processes and stakeholders.

Unlike a static virtual copy, the airport’s digital twin continuously receives real-time data about systems, processes, vehicles, and personnel, operating in parallel with the real world. This dynamic nature enables coordinated and collaborative actions across all ecosystem stakeholders and processes, focusing on monitoring, prediction, and use case development. It establishes a unified version of the truth, enabling continuous monitoring of ongoing activities and system statuses. Additionally, it empowers stakeholders to access customized dashboard information regarding system and process performance, facilitating joint decision-making processes with shared insights.

Furthermore, the digital twin serves as a predictive analysis tool, anticipating events that could disrupt airport operations and acting as an early-warning system. Through predictive analysis of potential outcomes, it can provide decision-support information on short notice, aiding in tasks such as the allocation of parking positions or gates for each plane.

The influence of the airport’s digital twin extends beyond short-term predictions, as it can also simulate trends, scenarios, and expected gains from infrastructure updates, impacting other turnarounds. This tool empowers stakeholders to optimize system performance and realize synergies, eliminating the need for duplicative data collection. With a collaborative approach, new service offerings can be developed by all ecosystem partners.

To progress towards the vision of the airport’s digital twin, several key steps can be taken:

  • Gather and Integrate Data: The initial step involves gathering and integrating data from various sources, including sensors, cameras, and other devices, to create a virtual model of the airport’s systems and processes.
  • Analyse and Visualize Data: Data analytics and visualization tools can then be employed to analyze and visualize data from the digital twin, providing insights and predictions to optimize operations.
  • Test and Optimize: The digital twin facilitates the simulation of different scenarios and testing of optimization strategies, enabling the identification of the most effective approaches for enhancing efficiency, safety, and customer experience.
  • Implement and Monitor: Once the most effective strategies are identified, they can be implemented in the physical airport. The digital twin continues to monitor the impact of these changes, allowing for further adjustments as needed.

By following these steps, airports can advance towards the realization of the airport’s digital twin, leveraging data and analytics to optimize operations and enhance customer service.

The most efficient approach to creating an airport’s digital twin, whether by integrating operational data or virtualizing the physical infrastructure, remains to be determined. However, beginning with a digitalized physical infrastructure, such as a 3D map of the airport buildings, provides a solid foundation. From there, the digital twin can be constructed by progressively integrating additional data streams into the platform.

These data streams may include information from various sources such as smoke alarms and ventilation systems from building automation, energy management data, baggage handling system data, input from passenger flow management systems, and performance data from aircraft and ground handling operations. As these data streams are harmonized and integrated, the digital twin gradually becomes a reality, providing a comprehensive virtual representation of the airport’s systems and processes.

The way forward: Where airports need to go from here

In this white paper, our focus has been on driving digitalization forward from a technological perspective. We emphasize the significance of an open Internet of Things (IoT) solution as the pivotal technology for enabling this transformation. Such a solution facilitates secure and selective data integration, creating a plug-and-play environment conducive to open innovation ecosystems. Airport operators need to seek out IoT solutions that are aligned with their technological needs and are prepared to collaborate with them on this journey. Additionally, they should cultivate a network of trusted partners within the airport ecosystem, including airlines, ground handlers, authorities, and other users, who are committed to investing in the data integration process.

While acknowledging the current status of digitalization in airports, we underscore that simply implementing technology is not sufficient. Airports must also foster a digital culture that empowers employees to drive change, ensures that all employees reap the benefits of digitalization, and bridges generational gaps that may exist within their workforce.

To propel this cultural shift, the appointment of a “Head of Digital” alone is insufficient. Instead, airports require a comprehensive digital change management process, dedicated digital teams to spearhead concrete projects, and user-friendly airport apps designed to streamline operations for employees.

Alongside this cultural evolution, there is a need to reassess and adapt project selection and investment decision processes. These processes should allow digital projects to undergo proof-of-concept and technology demonstrator phases within a stage-gate framework, postponing the business case discussion. This approach provides digital technologies with the opportunity to progress technologically while concurrently refining the business model.

Ultimately, the combination of an enabling solution, a digital mindset, and meticulous project selection will determine airports’ success in advancing on their digital journey and harnessing the power of real data.


wpChatIcon