Author Archives: Versa

Because Power over Ethernet (PoE) Powered Devices (PD) show up in user-facing smart-building deployments, they are ideal for collecting data. Moreover, the points where they are positioned and the kinds of data they collect make them extremely useful in the Machine-Learning (ML) space. In fact, you could say ML and PoE technologies have a symbiotic relationship. That data specific to the people occupying a room, building, or city provides the right insight to help managers, developers and other machines simplify the smart management process.

Smart buildings and smart devices are getting smarter by applying these data-driven insights. This process streamlines the functionality of homes, workspaces, and learning environments, making things like lighting more personalized. As a result, ML brings a whole new level of sophistication, personalization, and functionality to the world of low powered devices.

This blog will look at how ML works with PoE and the value it’s bringing to the table.

Machine Learning Defined

Machine learning applies artificial intelligence (AI) systems, including algorithms and programs, to automatically learn and improve experiences without human intervention. It develops computer programs that process data to “self” learn and improve existing systems.

There is a distinct difference between AI and ML. In AI, machines think like humans independently. In ML, continuous data mining harvests insights.

With ML, the efficient running of a building is the chief goal. Humans are still required. ML automates the process while anticipating and evolving. Change is seen over time, or you could say learning occurs.

ML implements in two phases. First, developers train neural network models using massive datasets. Without the help of machines, these data sets are too large for humans to interpret.

Once trained models are verified, they move into the inference engine phase. Inference is the predictive part of the application set. From a dictionary perspective, inference is the process of deriving strict logical consequences from assumed premises. The ML apps use the trained model to class external data and queries. Parallelization distributed between multiple training nodes sorts through enormous amounts of data to improve the model accuracy.

With ML, the importance of the rapid return of the results means that hyperscale computing needs to be deployed and always with a view to keeping costs down. As a result, the competition between cloud service providers is steep.

Machine learning growing adoption in business across industries reflects how effective its algorithms, frameworks and techniques are at solving complex problems quickly. The global machine learning market was valued at $1.58B in 2017 and is expected to reach $20.83B in 2024, growing at a CAGR of 44.06% between 2017 and 2024.

Louis Columbus, Roundup of Machine Learning Forecasts and Market Estimates 2020
Forbes.com

Device as ML Data Collector

The smart home, office and city employ a diverse set of connected technologies that are not only simplifying management processes, they’re making bank. Up to 83% of IT leaders say AI & ML is transforming customer engagement, and 69% say it is transforming their business. [Enterprise Technology Trends, Salesforce Research.] Customer experience is a Midas touch the hospitality industry has capitalized on in recent years. That principle has definitely wicked its way into the approach for better smart space product development.

Additionally, the data capture process is amping up with 5G. Because 5G is also an enabler of IIoT, it provides the speed needed for IIoT applications. As the data from the IIoT amasses, ML and AI will increasingly gain insights.

Why ML Data Collection, Analysis and Interpretation In PoE Is Important

In the 2020 state of enterprise machine learning, the authors cite three main uses of ML.

• The reduction in company costs (38%)
• The generation of customer insights and intelligence (37%)
• The improvement of customer experiences (34%)

Customer insights drawn from ML are enhancing business process effectiveness in verticals like security, billing and supply chain management helps service providers to identify anomalies and alert customers. Smart billing helps service providers improve customer satisfaction by enabling smart billing to optimize rate plans automatically.

In smart settings, ML optimizes satisfaction is through predictive maintenance scheduling and automated order processes for replacement parts. Connected devices leveraging the last mile Ethernet ecosystem to bring broad-based solutions that are interoperable and cost-effective.

Places Where Machine Learning and PoE Intersect

The best way to understand how ML will begin showing improvement for the end-users is to discuss how it is used within different technologies—autonomous cars and smart buildings.

How Autonomous Vehicles Use ML

Autonomous vehicles are, by definition, driverless. They have neural networks that synthesize to help vehicles learn how to react in real-time. These features use apps based on algorithms that take sensor data to predict driver responses. The sensors rely on speech and facial recognition and make these “perceptions” and plug them into the car driving system. An autonomous driving algorithm can also learn multiple routes between home and work and choose the roads with the least amount of traffic based on traffic alerts.

How Smart Buildings Use ML

In the smart building, ML is both supervised and unsupervised.

In the training session, algorithms in supervised ML sort through labeled training data. The supervised algorithm learns from previous examples by pairing inputs with the desired outputs. The algorithm searches through the data set for the input that corresponds to the desired output.

In unsupervised ML, the algorithm searches for previously unpredicted data sets with no pre-existing labels and a minimum of human supervision.

One of the ways this learning might show up is in a smart lighting platform, “knowing” a preset light level for a meeting or classroom. When the teacher starts a presentation, it not only lowers the light to predetermined levels to allow a presentation screen to show up, it might also lower blinds on the windows. Smart lighting algorithms might learn when to turn on motion sensors for lights for a cleaning crew and when they come on, have them turn on at 50 percent intensity.

As these smart space trends continue to develop, ML technology will continue to make the places we live and work more efficient, intuitive, and personalized.

Follow Versa Technology on YouTube.

Gartner Top 10 Strategic Technology Trends for 2020
https://youtu.be/6HzdOkPPPRU

In this blog Versa Technology is circling back on a previous post, Adjustable LED Lighting: Revolutionizing Workspace Design, to share insight on several developments taking place in the research of light and its effects on health and productivity. Light frequencies can be harnessed to mirror those found in nature. Researchers are finding that the right application of light can bring about benefits that not only make work more enjoyable; they can impact the bottom line also from the resulting increase in employee productivity. An investment in smart LED lighting systems is an investment in better working conditions that far outweigh the initial investment in smart Power over Ethernet (PoE) lighting systems.

The Natural Impact of Warm and Cool Light

Warm light is lower in frequency and occurs in nature at dawn and dusk, bookending the daylight cycle. This light is lower in frequency and provides a relaxing effect on the brain. That’s why adjustable lighting can work with and not against the flow of a natural feeling atmosphere in a room. Warmer light also promotes a feeling of wellbeing. It is appropriate for spaces in an office where workers go to relax.

Cool light is higher in frequency and occurs when the sun reaches its highest point in the sky. Light that is higher in frequency can promote focus and productivity and is perfect for areas within a campus where workers do the bulk of their work. It’s also good for spaces where collaboration takes place.

Model of Brain Response to Light Therapy
Image Courtesy of TheScientist

How Light Interacts with the Brain

Light travels in frequencies. Different wavelengths are proving to have a profound effect, at least within controlled environments. For example, bathing patients in flashing light and pulsing sounds [pink noise] both tuned to a frequency of 40Hz is showing promise in reversing signs of Alzheimer’s in the brain. Li-Huei Tsai, a Massachusetts Institute of Technology (MIT) neuroscientist, conducted a study back in March 2015, with two groups of mice programmed to produce the same plaque (Amyloid) that concentrates in the brains of Alzheimer’s patients. The mice that received one hour per day of flickering strobe light had a 50 percent reduction in the levels of plaque than others that spent the same hour in the dark.

This lightwave therapy also called gamma wave therapy or brainwave entrainment, synchronizes brain waves naturally with the rhythm of the light frequencies. Click here to see and hear a simulation of light and sound therapy used for Alzheimer’s treatment.

Prolonged exposure to daylight is also reducing sleeplessness in elderly patients with both Alzheimer’s and dementia patients. Getting patients out into the sunlight on a regular and prolonged basis promotes longer sleep cycles, and enough sleep slows the progression of either disease.

The implications of this study are profound. If light is helping people with acute health conditions, what can an introduction of exposure to light frequencies that more closely mirrors that found in nature do for those with milder challenges?

The Impact of Outdated Lighting Solutions on Workers

Decision-makers can increase worker well-being and productivity by making better lighting quality a priority. To drive home this point, let’s examine some of the effects of poor lighting quality.

1. Mental Fog Due to Sleep Deprivation

Fluorescent lighting, a cooler light with higher frequency, can disrupt the inner clock in the human brain. The scientific term for these inner cycles is circadian rhythms. They tell your body when to wake up and when to go to sleep. Keeping the internal clock aligned with natural light frequencies throughout the day helps support mental sharpness. Increasingly sophisticated Power Over Ethernet lighting solutions can be programmed to mimic the light frequencies that are happening outside, contributing to the mental focus of workers. Because the flow of light flows with natural brain tendencies, workers will experience deeper and longer sleep cycles, which promote productive functioning throughout the day.

2. Fatigue

Linked to mental fog is also mental and physical fatigue. It becomes harder to solve problems creatively and look at situations from different perspectives when you’re already struggling to apply yourself mentally.

Light within the range of daylight frequencies can boost mental clarity for workers who are trying to push through. Lowering light frequencies at end-of-day into evening, can help people begin to wind down and begin the relaxation period of the day and their brains prepare for sleep later on.

3. Eyestrain

The Mayo Clinic identifies light as being one of the primary causes of eyestrain. Too much or too little exposure to light can throw things out of whack. Extended amounts of blue light is one notorious cause. Straining to see in dim light is another.

Symptoms can include sore, watery eyes, tension in the neck and shoulders, difficulty concentrating, and the feeling of not being able to keep eyes open.

4. Migraine Headaches

Headaches of differing degrees can be triggered by the intensity of bright lighting in office spaces and is especially true for those who experience chronic episodes. By providing warmer lower-frequency lighting and the ability to dim lights within their workspace, employees can overcome this susceptibility.

Many lighting and facility platforms offer mobile that allow people individualized control over defined areas within a building. Workers struggling with these tendencies can enjoy relief through the use of lighting controls.

Power Over Ethernet Lighting to Create Natural Light Frequencies in the Workplace

Around the same time that Dr. Tsai was researching mice at MIT, Doctors Mohamed Boubekri, Ph.D., Ivy N. Cheung, B.A., and a distinguished group of researchers for the Journal of Clinical Sleep Medicine conducted a study examining the impact of daylight exposure on the health of office workers, specifically pertaining to sleep quality and patterns.

Participants in the study (2 groups), either worked in an environment with no or low window exposure versus those who had exposure to daylight while in an office setting. Workers in windowless workspaces lacked vitality, had physical problems, and exhibited the effects of poor sleep and sleep disturbances. The employees with windows and exposure to daylight were more active and had better sleep scores.

The conclusion of the findings of the MIT study?

We suggest that architectural design of office environments should place more emphasis on sufficient daylight exposure.

Easier said than done, as retrofitting windows into commercial buildings can come at a steep price point.

The Benefits of Natural Light Anywhere

Power Over Ethernet lighting systems and platforms are a much more cost-effective solution than renovating to add windows. After contractors and materials, you can be looking at a sizable investment. Alternatively, adding LED lights and connecting them to a lighting platform can quickly give you a comprehensive solution to the full frequency of light and control, while stretching over an entire floor or even a building at a fraction of the cost. The improved health and well being of workers, though, is priceless and will reflect company productivity as they flourish on the job.
~~~
Find out more about Versa Technology’s PoE networking solutions (used to implement PoE Lighting Systems), follow this link.

Silicon Labs, an Austin based provider of silicon, software, and smart solutions, recently announced the release of a new line of integrated circuits (IC) that provide up to 90W per port of Power over Ethernet (PoE) to power devices (PDs), including 5G small cells. Victory lap for PoE. If you’re not familiar with Silicon Labs, don’t feel out of the loop. These technologies fall into the category of ingredient solutions, and so, even if you’re using them, you may be doing so unawares. They occur inside another manufacturer’s product.

Small Cell 5G Infrastructure Explained

What is small cell technology?

A small cell is basically a mini base station comprised of much smaller pieces, namely picocells, microcells, and femtocells. Small cell systems can be implemented either indoor or outdoor. They attach to a macrocell base station to increase the macro cell’s edge data capacity, speed, and overall network efficiency.

Small cells were added in 2008 to help densify networks and build out existing wireless infrastructure. They appear in urban areas in places lots of people use data at one time.

Outdoor Deployments

Most small cell deployments are outdoors.

Indoor Deployments

Indoor deployments can include unlicensed LTE bands, Wi-Fi or Licensed Assisted Access (LAA), based on the capabilities needed.

Small Cell 5G has been around for a decade, but sort of in the background. Now that the race is on and telcos are competing heavily to establish fully-functioning 5G networks, small cells are moving center stage. Small cells are closer to the end-user. This edge proximity allows the potential for faster speeds with less competition for bandwidth, as instead of more centralized wireless applications, which travel farther to get to and compete with countless other signals to get onto the network.

Small cell close proximity puts in place the structure needed for lower latency. And the benefits don’t end here. Small cells are also being deployed in the expansion of frequency ranges, making it even easier to get onto a network.

The lower frequencies used by existing mobile networks are already crowded and don’t have the ready bandwidth to support 5G. To counter this, new frequency bands are becoming available in many countries around the world. In addition to ‘mid-band’ frequencies, new bands in the so-called millimetre-wave (mmWave) spectrum, namely the 24 GHz, 28 GHz and 39 GHz bands are being allocated; with more likely to follow. Darrell Davies, Small Cells – Big in 5G, Nokia.com.

These speeds translate to better streaming and potential for better AR/VR experiences and even AI. Enhanced mobile broadband (eMBB) and ultra-low latency (URLLC), made available by 5G small cells, can also optimize industrial applications of wireless technology. Smart cars will also feel the benefit of 5G wireless signal intensification as they travel through increasingly dense signal frameworks.

PoE delivery of power and data is cost-efficient and the use of one-cable installations will likely bring down overhead, and will make rolling out the infrastructure to support 5G happen faster. The cost and complexity of adding 90W Power over Ethernet (PoE) to power-sourcing equipment (PSE) and powered devices (PDs) have decreased. One cable installations deployed locally are easier to install and easier to justify from a financial standpoint.

Why 90W PoE is such a big deal

The 90W PoE power capability expands the potential for feature-laden, sophisticated IEEE 802.3bt (Type 4) compliant devices. The 802.3bt standard delivers 60W to 90W, doubling PoE power from Type 2 (30W) and expanding the capabilities of wireless access points and IoT wireless gateways.

This higher power capability extends PoE delivery to 5G small cells and digital buildings.

These new Silicon Lab ICs bring power to IoT nodes with flexibility and a high degree of integration. Type 4 PoE 90W supports extensive integration and advanced features. These capabilities help developers simplify designs while meeting stringent power, size, and cost budgets, essential at this stage of the IoT ramp up.

The New Silicon Lab ICs

The March 2020 release includes three PSE and PD products.

The first IC is the Si3471 PSE controller is the industry’s first fully autonomous, 90W, single-port 802.3bt-compliant power-sourcing device. The Si3471 adds 90W to single-port midspans or “injectors” and automatically manages all nuances associated with the 802.3bt standard. One attractive feature is that it requires no external host MCUs, firmware downloads, or software programming, and may be configured using three digital I/O pins.

The next IC is the Si3474 quad Ethernet-port PSE controller. It powers up to four 90W, 802.3bt PoE ports or up to eight 30-W 802.3at/af PoE ports, and is suitable for Ethernet switches and security recording equipment use in industrial and commercial settings.

The third is the Si34071 single-chip PD device. It combines an 802.3bt interface with an integrated, high-efficiency dc-dc converter capable of achieving more than 90% efficiency. The Si34071 powers 5G small cells, wireless access points, and IoT gateways.

90W PoE Moves The 5G and Small Cell Rollout Forward

Small cells are considered labor-intensive, so having a one-cable solution for power and data eliminates work. The less it takes to install and power wireless technology, the better. And the better the optimization, the greater the return on investment for operators. Improving wireless network capacity means either adding more spectrum or increasing the nu

mber of cell sites. For small cells, increasing the number of sites is the key, and the 5G rollout is definitely a force driving this phenomenon. The small cell 5G network market revenue in the US is expected to grow from $0.5B USD in 2019 to $3.5B in 2025.

Mobile Data Traffic Speeds Higher

Increasing data traffic is giving rise to the demand for higher network bandwidth. One Gigabit per second (Gbps) per small cell is what is making 5G more attractive. According to Ericsson, the monthly data traffic per smartphone usage would increase by 10 times from 2017 to 2023. The increase in mobile data traffic leads to an increase in demand for small cell 5G networks. The FCC expects up to 80% of new cell site deployments will be small cells.

The three 90W ICs from Silicon Labs are just the beginning. It will be exciting to watch as other key products begin to emerge. Until then, congratulations are in order to Silicon Labs.

To stay up to date on our PoE technology discussions, follow Versa Technology on Twitter.