By William Dupley
Big data analytics has been getting a lot of airtime over the last few years. It has promised to transform the way businesses identify opportunities for new wealth creation, and how to find the cause of problems. It also promises new tools to provide advanced analytics capabilities. All these promises are beginning to manifest in the manufacturing world and the e-commerce market.
Smart parking applications also have potential opportunities for big data analytics. This month’s blogs will examine big data and smart parking. Today we will start by discussing big data analytical tools and their overall capabilities. In further blogs, we will explore how big data analytics will transform how parking management, parking revenue, parking optimization, and parking integration can be changed to support an enterprise’s smart parking goals.
What is big data?
“Big data is extremely large data sets that may be analyzed computationally to reveal patterns, trends, and associations. Especially related to human behavior and interactions”
Big data consist of four attributes that differentiate from conventional data analytics. These attributes are value, variety, volume, velocity.
- Value includes the wisdom the data can provide if effectively mined. This wisdom can consist of predictive capabilities.
- Variety addresses the types of data that can be analyzed. This includes structured data such as conventional SQL datasets, and unstructured data such as media, documents, and written statements.
- Volume of data deals with the amount of data that is collected.
- Velocity defines the speed at which the data is collected.
These four attributes demand different data analytics tools to do real-time analytics. They also require new types of NoSQL databases such as Cassandra, Mongo, and Hbase.
The majority of data that is currently collected from smart parking applications is structured data. This type of data does not require a NoSQL database. However due to the volume, velocity, and value of the data I believe it still keeps smart parking data in the big data camp. As smart parking applications begin to capture unstructured data, such as customer complaints, or questions. NoSQL databases will need to be utilized in smart parking analytics applications. “According to Amadeus, 90 percent of US travelers with a smartphone share their experiences and photos in social media and reviews services. TripAdvisor has 390 million unique visitors and 435 million reviews. Every minute, about 280 traveler reviews are submitted to the site.” This kind of data is now profoundly affecting the travel industry and it will soon come to the parking industry.
Let’s examine a few case studies of big data analytics.
Big Data Analytics: Foreseeing the Future
Big data analytics enable an enterprise to make commitments to customers by being able to foresee parking spot occupancy. This capability will allow an enterprise to make commitments to customers and reserve parking spots ahead of time.
Valet Park of New England (VPNE) is an excellent example of a company that has exploited this capability. They once received a request from a customer who wanted to know if they could reserve 50 parking spots between 11 AM and 3:30 PM on Fridays. Because VPNE had big data analytic capabilities, they were able to examine their historical patterns and were able to determine the projected occupancy rates on those parking spots. Within 10 minutes they were able to make a commitment to the customer and reserve the spots they requested. This capability was enabled by their ability to analyze historical data and present that information in real time.
Here’s an example of the screens that they use to explain their nine parking lots occupancy rates:
The city of Aspen has a wide variation in parking spot occupancy depending on the season. They have high occupancy demand in the summer and winter and low occupancy at other times a year. During high occupancy periods, it is challenging to find parking in the downtown core which increases traffic and frustration among visitors. Using big data analytics, they were able to analyze the actual patterns of use down to the very day and types of vehicles. This helped them create a strategy for implementing variable pricing in the downtown core. The result of this analysis led to a shift in the utilization of parking spots downtown and created an increase in revenue. It also contributed to optimizing the parking spots in the peripheral areas of the city.
Here’s an example of the type of analysis report that the big data analytics were able to create:
Artificial intelligence is now being used extensively in the travel industry to recommend alternative travel arrangements based on weather conditions. These systems are now able to suggest alternative travel dates or routes. Although I have not found a smart parking application that has exploited the integration of structured and unstructured data, I believe it’s just a matter a matter of time before someone integrates historical data occupancy data with forecasted weather. The results of this marriage will be the possibility of dynamically adjusting the rates of the parking spots based on expected occupancy due to the weather.
The same type of integration could be used to integrate localized event data with parking spot management systems in order to adjust parking rates and exploit the increased demand for parking spots around the event. This would be a unique capability, made possible using big data analytics.
Big data analytics is an excellent future in the smart parking arena. In our next blog, we will examine additional case studies on how big data analytics helped to improve parking management.
About the Author:
Bill is the Digital Strategist for FoxNet Solutions. Formerly the Cloud Chief Technologist for Hewlett-Packard Enterprise Canada, Bill has provided Hybrid IT and IoT Strategic Planning advisory and planning services to over fifty Private and Public sector clients to help them migrate to a Hybrid IT Cloud Operating model. These transformation plans have helped both government and industry reduce the cost of IT, re-engineer their IT governance models, and reduce the overall complexity of IT. Bill is also a member of the Open Alliance for Cloud Adoption Team and has co-authored several documents on Cloud Maturity and Hybrid IT implementation.