Solving Network Load Management Issues at the Edge

Posted On 09 May 2019
Comment: Off

The traffic security CCTV camera operating on road detecting traffic

With traditional video surveillance systems, best practice was the placement of cameras at vulnerable locations, capturing images of people and vehicles at those locations. This approach allowed the minimal use of cameras, as well as reducing network load. The latter was achieved by using higher resolution cameras to cover entrances, ensuring identification and evidential-quality footage could be established when a suspect accessed a secure area. Lower resolutions cameras were then used for continuity purposes. The combination of high resolution and standard definition cameras allowed bandwidth needs to be managed.

Of course, such an approach only works if the sole purpose of the system is to deliver a basic level of security. Where a more advanced approach is required, or if the customer is seeking added value through the implementation of smart technology, the reality is that camera numbers are not only on the increase, but ever higher resolutions and real-time streams are demanded by end users.

Video is a great enabler, and with growth in security, IoT, intelligent buildings and smart cities, the potential for video deployments has never been greater. Whether used for identification of individuals, tracking of objects, triggering automated or peripheral systems, health and safety monitoring, counting, occupancy control, traffic management or simply to create reports based upon business intelligence algorithms, video delivers benefits to end users which enhance efficiencies and build an increased return on investment.

The increased use of GPUs and advanced algorithms allows a wider range of systems and applications to exploit metadata-rich video. By analysing the big data created by multiple video streams, ever smarter implementations can be created. However, because video is streamed in real-time, around the clock, from an ever-increasing number of devices, the sheer volume of data being captured, transmitted, processed and analysed is staggering. In terms of infrastructure, this places a significant demand on computational resources, storage and the network itself.

It is critical that system design and planning includes hardware which is appropriate for the use-case, and which can deliver the required capacities in terms of continuity and bandwidth management. The use of unsuitable hardware and infrastructure can lead to video packet loss, latency in video streams, slow or incomplete processing cycles, degraded image quality, or – in a worst-case scenario – failure of the entire system.

Video bit-rate will also impact on the storage requirements for a system, with a risk that prescribed retention periods may not be met.

Addressing the issues
One approach to managing the burgeoning data flow is to use edge-based processing and analysis. With a correctly designed infrastructure, this approach helps to reduce the overall network load by implementing data processing at the source of the video stream.

This can be achieved using HPE’s Edgeline hardware. The Edgeline video analytics portfolio is based on Edgeline Converged Edge Systems, powered by Intel Xeon processors, and backed by HPE’s security and video analysis partners. The systems’ GPUs allow fast and accurate analysis of events in real-time. As the processing happens at the edge, the need for data transfer is reduced, freeing up bandwidth and enhancing overall system efficiency. This approach not only reduces costs but also enhances cybersecurity as data is not moved around the network for centralised processing to take place.

Edge-based management also reduces the risk of data loss, and simplifies compliance with important data management policies, as usage is kept to a local level.
HPE Edgeline systems are specifically designed for edge implementation and are hardened to withstand hostile environmental conditions. The software is purpose-designed to meet the resilience required from security and intelligent video analytics systems.

Those delivering advanced analytics systems and smart solutions cannot allow bandwidth and data transfer issues to jeopardise the functionality and resilience of the system. With HPE’s Edgeline Converged Edge Systems, a purpose-built solution, based on a proven and credible hardware platform, can be implemented to meet the expectations of even the most demanding customers.