Will Data Centers Ruin Your Neighborhood? | HackerNoon

Data centers have become an integral part of the digital age. Unfortunately, many communities realize they are loud, resource-intensive, and visually unappealing only after they’ve been built. Are these buildings neighborhood-ruiners, or are peoples’ concerns overblown?

Are Data Centers Already Ruining Neighborhoods?

The residents of the sleepy, tree-lined subdivision of Great Oak didn’t realize what was in store for them when construction began for an Amazon Web Services (AWS) data center. This small community in Prince William County, Virginia, soon became the epicenter of an ongoing quarrel between a multinational tech giant and a local homeowners association.

Dale Browne, the president of the Great Oak Homeowners Association, said the building’s “constant whir” was “obnoxious” and regularly exceeded 60 decibels (dB), according to measurements taken by some of the neighborhood’s residents. Community members went as far as to stage protests out front, holding signs condemning the noise.

Others didn’t object to the building’s construction or operation. While some saw it as an innovative move, others were apathetic because their once-rural oasis had already become a minimetropolis. After all, what’s one data center among highways, power lines, and supersized shopping centers?

Still, many residents were unhappy seeing these massive server warehouses pop up nearby. In the neighboring Loudoun County, companies have built them as close as 50 feet — a mere backyard away — from residential properties. Construction has picked up pace in the United States, prompting similar quarrels and concerns nationwide.

Why Are Data Centers Popping up Everywhere?

Data centers are proliferating despite pockets of concern. The artificial intelligence market — which experts expect will reach $407 billion by 2027 — is one of the main drivers of this trend. Cloud computing technology and the Internet of Things (IoT) are also pushing demand exponentially higher. Many modern technologies are power-hungry and water-thirsty. They need cutting-edge servers and a tremendous amount of storage to function.

Whether companies train a machine learning model or store 8K videos on cloud servers, they need data centers. While data center proliferation has been on the rise for years, it only became a well-known point of contention recently when AI’s popularity prompted firms to reinvest in server warehouses.

Why are data centers being built in Virginia? Decision-makers are quickly making this state the so-called “data center capital of the world” for good reason. While some counties are inviting tech companies in hopes of inspiring a second Silicon Valley, others are just in convenient locations — the land and labor are cheap in rural areas. Of course, the robust electric and telecommunications infrastructure helps.

How These Buildings Impact Nearby Neighborhoods

Why are people against data centers? One of the public’s biggest complaints is noise — many don’t realize how loud these buildings are until they live next to one. Other common concerns include resource usage, greenhouse gas emissions, traffic congestion, and potential pollution.

Water Drainage

Cooling a massive warehouse packed to the brim with servers, routers, storage systems, and processors takes a lot of water. Research shows one large data center can use up between 1 million and 5 million gallons of water daily — which is enough to supply a town of 10,000-50,000 people.

Noise Pollution

Many data centers have on-site generators. Their cooling systems — essential for keeping hardware operational — contain intake and exhaust fans, which are objectionably loud. They produce between 55 and 85 dB typically. The noise is even more noticeable in rural areas where massive, nondescript buildings replace spaces that used to be forests or farmland.

Are data centers noisy at night? Most are since they run around the clock. Even if their volume doesn’t increase after hours, their loudness is more noticeable when it gets quiet. People often describe the noise as a buzzing, tinny whining or low-pitched roar. Even 60 dB — the low end of the typical spectrum — sounds like overlapping conversations or background music.

Power Depletion

Do data centers use a lot of energy? They are among the most energy-intensive buildings in existence, consuming up to 50 times more power than standard offices. Although some have on-site power sources — diesel generators are a common choice — many rely on the local electrical infrastructure.

The Implications of Having a Data Center Nearby

Many people are concerned about having a structure that constantly produces 55-85 dB in their backyards — and for good reason. How loud is a data center? While 60 dB is equivalent to conversation, 70 dB seems as loud as a packed business, and 80 dB sounds as loud as a police siren or power tools. At 85 dB and above, hearing loss occurs.

There is also concern about intense resource usage. In Maryland, a proposed 70-mile power line that would cut across the state recently angered residents. While environmental advocates and homeowners have vehemently opposed the $424 million project on the grounds of ecosystem and property preservation, it could be up and running as early as 2027.

The health of local communities and ecosystems may also be at stake. If data centers use generators for on-site power, they could produce toxic pollutants like nitrogen oxide or diesel exhaust. The cooling system’s noise alone could drive local wildlife away, damaging environmentally sensitive areas.

Counties that initially welcomed large technology and cloud computing companies with open arms have wavered after realizing how loud and resource-intensive these structures are. Many may soon raise taxes on hardware, revise their noise ordinances, or enforce strict project review processes to make it worthwhile.

Are Communities’ Data Center Fears Justified?

The worst-case scenario is using 5 million gallons of water, outputting 85 dB, and producing toxic diesel exhaust daily. That said, most data centers will be noisy and resource-intensive. Air cooling is loud but standard, accounting for 99% of methods in use today. However, that doesn’t mean engineers and operators are unwilling to change to help their unhappy neighbors.

The Great Oak Homeowners Association is an excellent example of this fact. While Amazon initially denied the residents’ claims its building was outputting 60 dB — even going as far as to conduct a strategically engineered study to back its claim — it eventually took action.

One year after the spat between the AWS data centers and the Great Oak community made headlines, Amazon lengthened its exhaust tubes and directed airflow vertically. Measurements from it and the Homeowners Association revealed the noise leveldropped by 10 dB to about 50 dB, effectively cutting it in half.

Currently, it seems decision-makers aren’t considering the long-term repercussions of building near neighborhoods — they’re quickly seizing whatever land is cheap and available. To ease communities’ fears, they should consider their projects’ long-term viability, accounting for how construction and operation will affect nearby residents and local ecosystems.

When considering all of the negatives in a vacuum, data centers sound like one of the worst structures a company could ever build. However, they support essential services and help connect people around the world. Most of today’s problems are growing pains — now that engineers and operators know what not to do, they can build better or retrofit existing buildings.

For example, while air cooling generates significant noise, immersion cooling — which involves submerging hardware in a non-conductive liquid — apparently sounds considerably quieter in comparison. Engineers could also use on-site renewables to reduce their reliance on the city’s power and water supply, further easing residents’ concerns.

What Companies and Communities Can Do Going Forward

Gathering and implementing feedback is the only way to permanently ease communities’ concerns. This strategy may even pay off for technology companies because it streamlines site research and lets them know what interventions to prioritize. For example, if people worry about unsightly power lines but don’t care about noise, firms only need to build on-site power.