Government-mandated closures aren’t the only thing cutting into power demand in New York this summer.
Once the epicenter of the COVID-19 outbreak in the U.S., New York maintained strict closures and travel restrictions throughout April and May. Its shutdowns were swift compared with the rest of the country. As early as March 24, my team uncovered the first hints of COVID-19-related power load demand destruction.
Figure 1 above shows Enverus’ first phase of measuring demand destruction in NYISO. As I wrote in March, my team detected demand destruction between 10-15% compared with what our machine-learning models predicted using historical weather and demand data.
Bringing more thorough predictability using AI
We were eager to give this analysis more thorough predictability as the AI began to learn the intricacies of COVID-19 demand destruction. The patterns were unlike anything we’d ever measured before and had no historical precedent for guidance.
My team soon introduced weather-normalized analysis to our load models. By late May, with greater hindsight and two months’ worth of data, the accuracy of Enverus’ short-term demand destruction views continued to improve. At that time, temperatures were warming in NYISO, on-peak demand destruction continued to steadily grow with the seven-day moving average reaching nearly 18% in late May.
Just after I posted this blog at the end of May, demand rebounded in NYISO, as shown in Figure 2 above in the black and red lines. The recovery was short-lived, however, as protests and civil unrest spread in New York City and across the U.S. Just as soon as demand started to recover, it dropped. As protest activity subsided slightly in June and more businesses reopened around the state, demand destruction once again eroded. As of June 10, the seven-day moving average on-peak demand destruction stood at 15%. However, as protests have subsided and as New York continues to reopen, we have measured the demand destruction recovery growing.
What lies ahead for NYISO and power load demand destruction?
Now, my team is forecasting load demand destruction even further into the future. When thinking about what lies ahead for July and August, we predict that demand destruction will fall between 5-10% on-peak.
How did we arrive at that conclusion? We considered a few unknowns that could impact this forecast:
- Economic activity per region.
- Current protest activity and social unrest.
- Return of growing COVID-19 cases/recent demand destruction increases.
- New quarantine regulations.
This forecast is based on demand destruction reversals due to increased economic activity and summer-like temperatures we have measured. It is based on the pre-COVID-19, post-COVID-19, and weather normalized demand destruction numbers.
NOTE: If demand destruction numbers do not begin to recover even more within the next two weeks, those numbers will be increased. In fact, many of these regions were recovering and have now increased again.
For more power demand destruction content, sign up for a free trial of our twice-daily e-ISOForecast reports.