What is the PJM Interconnect? How does it work? And why you should care? ... 1-Basics

Last update:  Wednesday 9:32pm 10/15/25

This note, Part 1 in a three part series, will provide an introduction to the PJM Interconnect that directs the transmission of electric power across thirteen states and the District of Columbia. Part 2 will highlight features of the PJM that provide persistent advantages — lower electricity bills — for households and enterprises in some states, while imposing persistent penalties — higher electricity bills — on households and enterprises in other states. Part 3 will analyze the persistent penalties, i.e., the negative externalities as they are being reported by the media with increasing frequency and stridency. The media often assert that negative externalities have been caused by AI-related, hyper-scale, cloud-based data centers. They also recommend that federal regulators require data centers to provide their own power. Unfortunately, their findings and recommendations exaggerate the impact of data centers and are legally dubious. 

• Hyper-scale data centers might aggravate these externalities, but as will be shown in Part 2, persistent negative externalities are the inevitable consequences of the PJM’s historic decision to admit states that did not deregulate their electric utilities, i.e., states wherein electric utilities were still regulated.

• Federal regulators might not have the authority to compel data centers in regulated states to build their own power generators anymore than they can compel users in regulated states to purchase enough solar panels and batteries to provide their own electric power. The feds only have constitutional jurisdiction over interstate transmissions of electric power; they do not have constitutional jurisdiction over intrastate transmissions.

The neoliberal/progressive Clinton administration in the 1990's pressed hard for the deregulation of the nation's electric utilities under the mistaken assumption that interconnects like the PJM would provide deregulated electric utilities with substantial competitive advantages. Ironically, Part 2 of our notes will argue that the PJM actually provided substantial long-term competitive advantages to the regulated utilities.

Click HERE to view full report

Up until a few weeks ago, the editor of this blog only had a vague notion of what the PJM was. Then he engaged Gemini, Google's chatbot, in a series of extensive tutorial sessions.

Interviews with Claude, Anthropic's chatbot ...

Each of the three notes in this series will have an interview format. Each note will record the responses of the Claude chatbot to a series of questions that were inspired by the understanding of the PJM that the editor had gained from his sessions with Gemini. The editor is switching chatbots because Claude is a much better writer than Gemini, so Claude will get the final wording. However, some of the editor’s questions will include hints that are based on memorable insights provided by Gemini.

Question 1. An organization called “PJM Interconnect” directs the transmission of electric power across thirteen states and DC. What do the initials PJM stand for?

Answer 1. PJM stands for Pennsylvania, New Jersey, and Maryland.

 Question 2. When was PJM founded and why?

Answer 2. The organization started in 1927 as a power pool between utilities in Pennsylvania and New Jersey. 

Question 3.  When PJM was founded, all electric utilities were regulated. So how do regulated utilities operate and how they are regulated?
 

Answer 3.  Regulated utilities are vertically integrated monopolies: 

• One utility in a given service territory owns EVERYTHING:
  -- Power plants (generation)
  -- High-voltage transmission lines
  -- Lower-voltage distribution lines (the “last mile” to your home)
  -- The billing relationship with customers
  
  
• Geographic monopoly:
  -- Typically one utility per service territory (could be city, county, or region)
  -- Some states might have multiple utilities serving different parts of the state
  -- But within each territory, only ONE utility - no competition
  
  
• Obligations to serve:
  -- Regulated utilities are required to serve all customers within their territories
  -- Provide reliable continuous power to all customers
  -- Maintain infrastructure to meet all demand
  -- Build capacity as needed to serve growing load
  
  
• Regulated by state commissions:
  -- Utilities can not raise rates without the permission of state regulators
  -- Have to justify costs to regulators
  -- Obtain approval of rates that provide guaranteed “fair” returns on investments
  
  
• No brokers, no choice, no shopping around:
  -- Customers within a utility’s district can only buy electric power from that utility; they can not buy directly from a power plant or from another utility.
  
  
• The PJM connection:
  -- Before deregulation, utilities in PA/NJ/MD formed and expanded PJM (1927-1956) to coordinate and share resources

Question 4. Gemini told me that PJM’s transformation into what it is today was triggered by deregulation. But that raised a prior question: what triggered the deregulation of so many electric utilities?

Answer 4.  

The Northeast Blackout on November 9, 1965.   

• Affected 30 million people across the Northeast (New York, parts of 7 states, Ontario) 

• 13 hours - New York City in darkness 

• Started with a single relay failure in Ontario that cascaded 

• Exposed how fragile and interconnected the grid was 

• Showed that utilities operating independently couldn’t prevent cascade failures. 

Federal/state regulators set rates through slow administrative processes 

• Utilities negotiated bilateral contracts - “I’ll sell you 100 MW for the next year at $X” 

• When unexpected demand hit or a plant failed, utilities scrambled with phone calls to arrange emergency power 

• No dynamic price signals - just rigid contracts and regulatory mandates 

• Committees met quarterly/annually - way too slow for real-time grid management 

Devastating cascades like the Northeast Blackout could only be prevented by a market mechanism that matched power generators’ current capacities with customers’ current needs in real time. So that’s what PJM became: an economic market mechanism. 

 Question 5. How big is PJM today?

Answer 5. As can be seen on the adjacent map, PJM covers 13 states plus DC; but the name kept the initials of the three founding states. Here’s the complete membership: Delaware, District of Columbia, Illinois (partly), Indiana (partly), Kentucky (partly), Maryland, Michigan (partly), New Jersey, North Carolina (partly), Ohio (partly), Pennsylvania, Tennessee (partly), Virginia, West Virginia (partly)

Question 6. I’m back with more questions about the big blackout in New York. If power was out for 13 hours and came back on, then there was nothing wrong with the transmission lines. There was nothing wrong with the generators. What is a “cascade” that can start in Ontario and spread. Where did the power go? Why did it stop flowing to the areas that needed it?

Answer 6. Excellent questions - this gets at a fundamental misunderstanding most people have about the electrical grid. The power didn’t “go” anywhere - the grid SHUT ITSELF DOWN as a safety mechanism. Here’s what happens in a cascade failure:

1. The initial trigger of the 1965 blackout: 

 

• A relay in Ontario malfunctioned

• This tripped a circuit breaker, disconnecting one transmission line

• Power that was flowing towards that line suddenly had to find another path 

 2. The cascade effect:

• Electricity instantly rerouted to other lines

• Those lines became overloaded (too much current)

• Their protective relays said “DANGER - shut down before we melt/catch fire”

• They disconnected automatically

• This forced even MORE power onto remaining lines

• More overloads → more automatic shutdowns

• Domino effect across the interconnected grid 

 

3. Why generators shut down:

• When transmission lines disconnect, generators suddenly have nowhere to send their power

• Generators must stay synchronized at exactly 60 Hz

• Sudden load loss → frequency spikes → generators automatically trip offline to protect themselves from damage

• Grid frequency became unstable → MORE generators tripped offline

 4. The result -- within minutes massive cascading failure

• Generators offline (protecting themselves)

• Transmission lines offline (protecting themselves)

• Nothing physically broken - just everything in “safety shutdown mode”

5. The 13-hour restart:

• One can’t just flip switches back on

• Generators must be restarted one by one in careful sequence

• Grid frequency and synchronization must be gradually rebuilt

• “Black start” procedure are extremely slow and careful

Question 7. Does this mean that PJM really serves two purposes? 

Answer 7.  Yes.  

• The first is economic. The PJM provides a market mechanism that enables users needs to be matched to power generators capabilities in real time.     

• The second is physical. The PJM monitors the flow of electricity in real time. If a power plant or transmission line shuts down, PJM tells some generators in some areas to reduce output (or shut down) and tells other generators in other areas to generate more. This rebalances the flow of electricity and prevents more transmission lines from becoming overloaded and shutting down. Monitoring to limit the number of self-protective shutdowns is based on physics:  electricity always has to flow somewhere.  

Question 8. How does PJM provide a market mechanism that matches customers demands with the power generators supplies? Gemini said that PJM conducts different kinds of surveys, some in real time, to determine "bids" and "loads", which I interpreted to mean "supply" and "demand".

Answer 8. Yes, you’re right that “bids” relate to supply and “loads” relate to demand, but let me clarify how PJM’s market mechanism actually works: 

•  The Real-Time Energy Market:   
  PJM operates multiple interconnected markets, but the core is the real-time energy market that runs 24/7/365:
  
  -- Every 5 minutes, PJM runs an auction that determines which power plants will generate electricity and at what price
  
  -- Generators submit offers (not bids - they’re selling): “I can provide X megawatts at $Y per megawatt-hour”
  
  -- PJM knows the load (demand) from real-time monitoring of actual electricity consumption across the grid
  
  -- PJM’s computer systems stack all the generator offers from cheapest to most expensive (this is called the “supply curve” or “merit order”)
  
  -- PJM accepts offers starting with the cheapest until there’s enough supply to meet the current demand. For example, suppose the load (demand) = 150MW. If natural gas offers 50MW, coal offers 80MW,  and oil-fired offers 20MW, then the demand is satisfied.
  
  -- The most expensive generator needed to meet demand sets the price that ALL generators get paid for that 5-minute interval (this is called “locational marginal pricing” or LMP)
  
  
• Why this structure?
  
  -- Cheapest first: Natural gas might cost $30/MWh, coal $40/MWh, oil-fired peaker plants $150/MWh. PJM uses the cheapest available sources first.
  
  -- Everyone gets the clearing price: If demand is high enough that PJM needs that $150/MWh peaker plant, then even the $30/MWh natural gas plant gets paid $150/MWh for that interval. This rewards efficient plants and ensures expensive plants are willing to be on standby.
  
  -- Location matters: Prices can vary by location based on transmission constraints (hence “locational” marginal pricing)
  
  
• The Day-Ahead Market:
  
  -- PJM also runs a day-ahead market where generators and load-serving entities (utilities, brokers) can lock in prices for the next day:
  
  -- Runs once per day for each hour of the following day
  
  -- Generators submit offers, buyers submit bids
  
  -- About 97% of PJM’s energy is committed in this market
  
  -- Provides price certainty and helps generators plan which units to start up
  
  
• Capacity Markets:
  Separately, PJM runs capacity auctions 3 years in advance to ensure enough generation will be available when needed. This guarantees generators get paid just for being available, even if they’re not called upon to generate.  

Question 9. How does the PJM monitor and manage the flow of electricity in the system so that it minimizes the self-protective shutdowns that otherwise would lead to massive “blackouts”?

Answer 9. PJM operates a control center in Audubon, Pennsylvania that monitors the grid 24/7, receiving data every 2-4 seconds from thousands of sensors across the entire system. These sensors measure voltage levels, current flowing through transmission lines, grid frequency (which must stay at exactly 60 Hz), and the temperature of transmission lines.

Preventing Cascades - The Core Strategy:

When PJM sees a transmission line approaching its thermal limit (the maximum current it can safely carry without overheating and triggering an automatic shutdown), it takes immediate action to redirect power flows:

• Economic dispatch adjustments: PJM tells generators in congested areas to reduce output and tells generators in other areas to increase output. Since electricity flows according to physics based on where it's being generated, this changes the path power takes through the grid, redirecting it away from overloaded lines.

• Contingency analysis: Every few minutes, PJM's computers run thousands of "what if" scenarios - "What if this major transmission line fails right now?" or "What if this large power plant suddenly goes offline?" If any scenario would trigger a cascade, PJM takes preventive action immediately, before anything actually fails. 

• Frequency management: PJM keeps certain generators on Automatic Generation Control that automatically ramp up or down every few seconds to keep the grid frequency stable at 60 Hz. If generation and demand get out of balance, frequency shifts, and that can trigger protective shutdowns across the system.

The Critical Constraint: 

PJM can't directly control where electricity flows - physics determines that based on the path of least resistance. But PJM can influence those flows indirectly by changing where generation happens. This is why the economic market and physical grid management must work together in real time.

Question 10. Recently the media has been full of stories about "Data Center Alley". Where is it? About what percent of the U.S. data centers of all kinds are in this area? What percent of U.S. hyper-scale AI cloud-based centers are located there? What percent of the world's hyper-scale AI cloud-based centers are in this "alley"? And where are the largest two other U.S. hyper-scale AI cloud-based data centers located?

Answer 10. Data Center Alley is located in Northern Virginia, primarily in Loudoun County, centered around the town of Ashburn, also known as the Dulles Technology Corridor due to its proximity to Dulles International Airport. It spans across Loudoun, Fairfax, and Prince William counties, with data centers clustered in Ashburn, Sterling, Herndon, Reston, Chantilly, and Manassas. (LightyearUPSTACK)

Map coourtesy of Panethos ... Click to enlarge, more readable.

About what percent of U.S. data centers are in this area?
Almost 50% of the data centers in the United States are in Virginia, with 90% of Virginia's data centers located in Northern Virginia. (Six Reasons Why Data Centers in Virginia Are Right For You ) So roughly 45% of all U.S. data centers are in the Northern Virginia area.

What percent of U.S. hyperscale AI cloud-based centers are located there?

About 25% of U.S. hyperscale dAI ata centers are located in Virginia. (The Dawn of Data | Virginia Economic Development Partnership)

What percent of the world's hyperscale AI cloud-based centers are in this "alley"?
Virginia is home to approximately 35% of all known hyperscale data centers worldwide, with about 150 hyperscale facilities. (Virginia Economic Development PartnershipCardinal News )

An estimated 70% of the world's internet traffic travels through Data Center Alley each day. (How Ashburn, VA became the Colocation Mecca known as Data Center Alley)

Where are the largest two other U.S. hyperscale AI cloud-based data centers located?
Based on the search results, after Northern Virginia, the next largest U.S. hyperscale data center locations are:

1. Dallas/Fort Worth, Texas - which has over 150 data centers and experienced a 173.1% increase in inventory during the second half of 2023, with more than 1,125 megawatts of multi-tenant commissioned power (The AI JournalDgtl Infra)
   
   
2. Phoenix, Arizona (Maricopa County) - which has become one of the top counties nationally for data center capacity, with 3,436.1 MW operating and under construction, plus 5,966 MW in planning phases (The AI JournalArizto)

Other major markets include Silicon Valley/Northern California, Chicago, and Oregon (particularly around Portland), but Dallas and Phoenix represent the second and third largest concentrations after Northern Virginia.

  Map courtesy of Visual Capitalist ... Click to enlarge, more readable..

____________________________________

Links to related notes on this blog:  

•