Modern video surveillance systems increasingly make use of extended camera counts, typically streaming higher resolution video. As VMS-based solutions become more prevalent, so the restrictions of more limited technologies are eroded, and the user has greater freedom regarding the amount of data being collected by a video surveillance solution, along with the ways in which the data is used.
In many systems, the main purpose of video data collection and processing will be for security, affording ever higher levels of protection for people, premises and assets. However, with the continued growth in business intelligence-driven analytics, business and organisations are now able to leverage added-value benefits that deliver operational efficiencies.
This increased demand for video data places a greater emphasis on the resilience of the supporting infrastructure. As a result, much of the ‘heavy lifting’ in terms of video processing and analytics algorithm management is best performed at the edge of the network, rather than transmitting huge amounts of data to a central server for all management tasks.
As the video data plays a greater role in site and process management for businesses and organisations, it becomes vital than continuity is ensured. Any failure or weakness in the infrastructure can result in performance issues, which in turn will impact on the total cost of ownership and return on investment.
Maintaining infrastructure to ensure optimum performance can be an on-going task, and as such requires regular checks to monitor the IT environment. As systems grow is scale and complexity, this becomes an increasingly difficult task to perform. The amount of resources that must be dedicated to such an approach impacts negatively on many businesses and organisations.
The increased use of artificial intelligence (AI) in video-based solutions offers an answer to this problem. AI technology can be used to ‘learn’ system performance parameters, identifying issues and either recommending or automating solutions. This ensures the infrastructure performance remains at its optimum, even when demands on the system change.
One tool that offers this level of support is HPE InfoSight. It is an AI-powered application that both predicts and prevents issues on a solution’s infrastructure. Making use of a ‘recommendation engine’, the platform is able to predict problems and resolve them automatically. By collecting information from multiple sensor points and analysing the data, HPE InfoSight can accurately and repeatedly measure performance of any system and its accompanying infrastructure. This data is then used to allow the platform to ‘learn’ about system parameters. In turn, this enhances the platform’s predictive analytics and recommendation engine.
Research and field data show that HPE InfoSight delivers significant performance benefits. For example, 86 per cent of issues are automatically predicted and resolved. The system, and infrastructure enjoy a guaranteed 99.9999 per cent availability. Other benefits include 85 per cent less time spent on managing storage issues. This is vital in security-centric applications where the credibility of data storage remains a critical issue for end users.
HPE InfoSight can also automate actions, ensuring the system always offers optimum performance. This is achieved via the recommendation engine, enabling the platform to predict issues and dynamically make recommendations and implement actions that improve and optimise the core system. Because the decisions are based upon AI analysis of system performance, they are application-aware, ensuring any actions are not detrimental to the core functionality of the solution. This is critical in security applications, where the continuity of protection must be preserved.
HPE InfoSight can proactively improve performance and optimise the use of system resources, utilising the experience-based learning to ensure effective and efficient operations. For modern security solutions, including those that make use of business intelligence technologies to add value, this is a pivotal part of system credibility.