Do we actually understand the impact of renewables on electricity prices? A causal inference approach

TL;DR

The paper targets causal inference in electricity markets with high renewable penetration by developing a local partially linear double machine learning framework with a boxcar kernel to estimate conditional average treatment effects (CATE) of wind and solar on prices, while also supplying mean smoothing and quantile modelling. It demonstrates a non-linear, time-evolving wind effect (a U-shaped response) and a robust solar merit-order effect that reduces prices across penetration levels, with both effects intensifying from 2018 to 2024, validated across UK APX prices and extended to NordPool and intraday markets. The methodology, including causal effect estimation via $CATE(x) = E[p | do(t+1), x] - E[p | do(t), x]$, avoids regression-based biases and provides a practical tool for policy design and market operation under rising renewables. These results have important implications for market design and energy policy as renewables scale, and the approach provides a generalizable toolkit for causal assessment of generation–price relationships in other markets.

Abstract

The energy transition is profoundly reshaping electricity market dynamics. It makes it essential to understand how renewable energy generation actually impacts electricity prices, among all other market drivers. These insights are critical to design policies and market interventions that ensure affordable, reliable, and sustainable energy systems. However, identifying causal effects from observational data is a major challenge, requiring innovative causal inference approaches that go beyond conventional regression analysis only. We build upon the state of the art by developing and applying a local partially linear double machine learning approach. Its application yields the first robust causal evidence on the distinct and non-linear effects of wind and solar power generation on UK wholesale electricity prices, revealing key insights that have eluded previous analyses. We find that, over 2018-2024, wind power generation has a U-shaped effect on prices: at low penetration levels, a 1 GWh increase in energy generation reduces prices by up to 7 GBP/MWh, but this effect gets close to none at mid-penetration levels (20-30%) before intensifying again. Solar power places substantial downward pressure on prices at very low penetration levels (up to 9 GBP/MWh per 1 GWh increase in energy generation), though its impact weakens quite rapidly. We also uncover a critical trend where the price-reducing effects of both wind and solar power have become more pronounced over time (from 2018 to 2024), highlighting their growing influence on electricity markets amid rising penetration. Our study provides both novel analysis approaches and actionable insights to guide policymakers in appraising the way renewables impact electricity markets.

Figures (9)

• Figure 1: Price variation across predicted renewable penetration levels. Bar plots show the mean APX prices for wind and solar penetration levels, over 2018-2024, with error bars representing associated 95% confidence intervals. The predicted wind power penetration intervals (a) are defined in 10% increments, while those for predicted solar power penetration (b) are defined in 1% increments, reflecting the lower installed solar power capacity in the UK.
• Figure 2: Regression analysis of predicted renewable penetration and APX wholesale prices. The top row shows the mean spot price modelled as a function of the hour of the day, as well as predicted (a) wind power penetration and (b) solar power penetration. The bottom row presents the results of quantile regression models, with the solid line representing the mean spot price, and the shaded region representing central 80%-coverage intervals, where the colour intensity indicates the data density (in terms of penetration data). These models capture the distributional effects of predicted (c) wind power penetration and (d) solar power penetration, on spot prices.
• Figure 3: Causal impact of predicted renewable power production on electricity prices. Comparison of observational mean and causal effects of wind (a) and solar (b) power production on wholesale electricity prices. The solid lines represent the non-linear CATE estimates derived using our local partially linear DML framework, capturing the price impact (in GBP/MWh) of a 1 GWh increase in renewable energy generation. The dashed lines show the observational mean trends as a function of renewable penetration levels, illustrating the differences between raw associations and the true causal effects. Shaded areas denote 80% confidence intervals.
• Figure 4: Temporal evolution of the causal impact of renewable power production on electricity prices. non-linear CATE estimates of (a) wind and (b) solar power production over time, obtained using a sliding window spanning two financial years, with each window containing approximately 35,000 observations. Shaded regions represent 80% confidence intervals.
• Figure S1: Results from the NordPool day-ahead market. Comparison of observational mean and causal effects of wind (a) and solar (b) power production on wholesale electricity prices. The solid lines represent the nonlinear CATE estimates derived using our locally partially linear DML framework, capturing the price impact [GBP/MWh] of a 1 GWh increase in renewable energy generation. The dashed lines show the observational mean trends as a function of renewable penetration levels, illustrating the differences between raw associations and the true causal effects. Shaded areas denote 80% confidence intervals obtained with bootstrap procedures.