The previous blog discussed the physical aspects of a ruggedized chassis, including short depth and serviceability. The overarching theme being that of creating a durable server, in a form factor that can be deployed in a wide range of Telecom and Edge compute environments.

This blog will focus on the inside of the server, specifically design aspects that cover efficient and long-term, reliable server operations. This blog covers the following topics:

• Optimal Thermal Performance
• Power Efficiency
• Contaminant Protections and Smart Bezel Design

Optimal thermal performanceFigure 1. Serial Heat Rise Example from Front to Back

Certainly, one of the greatest challenges of Edge Server Design is architecture and layout. It is extremely challenging to optimize airflow such that heat is efficiently dissipated over the entire operational temperature and humidity range.   

In an Edge Server, there are still the same compute, storage, memory, and networking demands required for a traditional data center server. However, the designers are dealing with 30 percent less real estate to work with—and even less space when dealing with some of the sledded server architectures, such as with Dell’s new PowerEdge XR4000 Server.

These design restrictions typically result in components being placed much closer together on the motherboard and a concentration of heat creation in a smaller area.  Smart component placement, which mitigates pre-heated air from passing over other sensitive components and advanced heat sinks specifying high-performance fans and the use of air channels to internally direct air through the server, is critical to creating server designs that can tolerate temperature extremes without creating excessive hotspots in the server.

These designs are repeatedly simulated and optimized using a Computational Fluid Dynamics (CFD) application.  Hot spots are identified and mitigated until a design is created that maintains all active components within their specified operating temperatures, over the entire operational range of the overall server. For example, for NEBS Level 3 this would range from -5C to +55C, as discussed in the third blog of this series. 

Bringing together these server performance requirements, thermal dissipation challenges, component selection, and effective airflow simulations, while involving considerable engineering and applied science is very much an art form.  A well-designed server is remarkable not only in its performance but the efficiency and elegance of its layout.  Perhaps that’s a little overboard, but I can’t help but admire an efficient server layout and consider all the design iterations, time, engineering efforts and simulations that went into its creation.

Figure 2. Example 80PLUS Platinum Efficiency CorePower efficiency

Having high-efficiency Power Supply Units (PSUs) options, that support multiple voltages (both AC and DC) and multiple PSU capacities will allow for the optimal conversion of input power (110VAC, 220VAC, -48VDC) server consumable voltages (12VDC, 5VDC). 

Power Supplies operate most efficiently in a utilization range.  PSUs are generally rated with a voluntary certification, called 80PLUS, which is a rating of power conversion efficiency. The minimum efficiency is 80 percent for power conversion rating. The flip side of an 80 percent efficiency rating, is that 20 percent of the input power is wasted as heat. Maximum PSU efficiency rating is currently around 96 percent. Of course, the higher the efficiency the higher the price of the PSU.  The increasing costs of electricity globally is dimensioning the PSU, resulting in significant TCO savings.

Ensuring that a server vendor has multiple PSU options that provide optimal PSU efficiencies, over the performance range of the server can save hundreds to thousands of dollars in inefficient power conversion over the lifetime of the server.  If you also consider that the power conversion loss represents generated heat, the potential savings in cooling costs are even greater. 

Contaminant protection and Smart Bezel design

GR-63-Core specifies three types of airborne contaminants that need to be addressed:  particulate, organic vapors, and reactive gases. Organic vapors and reactive gases can lead to rapid corrosion, especially where copper or silver components are exposed in the server.  With the density of server components on a motherboard increasing from generation to generation and the size of the components decreasing, corrosion becomes an increasingly complex issue to resolve.

Particulate contaminants, which include particulates—such as salt crystals on the fine side and common dust and metallic particles like zinc whiskers on the coarse side—can cause corrosion but can also result in leakage, eventual electrical arcing, and sudden failures. Common dust build-up within a server can reduce the efficiency of heat dissipation and dust can absorb humidity that can cause shorts and resulting failures.

Hybrid outdoor cabinet solutions may become more common as operators look toward reducing energy costs.  These would involve combination of Air Ventilation (AV), Active Cooling (AC), and Heat Exchangers (HEX). Depending on the region AV+AC (warmer) or AV+HEX (cooler) can be used to efficiently evacuate heat from an enclosure, only falling back on AC and HEX when AV cannot sufficiently cool the cabinet. However, exposure to outside air brings in a whole new set of design challenges, which increases the risk of corrosion.

One method of protection employed is a Conformal Covering is a protection method that combats corrosive contaminates in hostile environments.  This is a thin layer of a non-conductive material that is applied to the electronics in a server and acts as a barrier to corrosive elements. This layer and the material used (typically some acrylic) is thin enough that its application does not impede heat conduction. Conformal Coverings can also assist against dust build-up.  This is not a common practice in servers due to the complexity of applying the coating to the multiple modules (motherboard, DIMMs, PCIe Cards, and more) that compose a modern server and is not without cost.  However, the tradeoff of coating a server compared to the savings of using AV may make this practice more common in the future.

Using a filtered bezel is a common option for dust. These filters block dust from entering the server but not keep dust out of the filter. Eventually, the dust accumulated in the filter reduces airflow through the server which can cause components to run hotter or cause the fans to spin at a higher rate consuming more electricity.

Periodically replacing filters is critical—but how often and when? The use of Smart Filter Bezels can be an effective solution to this question. These bezels notify operations when a filter needs to be swapped and may save time with unnecessary periodic checks or rapidly reacting when over-temperature alarms are suddenly received from the server.

Conclusion

The last two blogs in this series covered a few of the design aspects that should be considered when designing a compute solution for the edge that is powerful, compact, ruggedized, environmentally tolerant and power efficient. These designs need to be flexible, deployable into existing environments, often short-depth, and operate reliably with a minimum of physical maintenance for multiple years.