We are back on one of our pet topics today which is the reasonableness around some of the assumptions around the future cost of renewable power. We reference, work done by the US Department of Energy in the Exhibit below, and see two potential pitfalls with the assumptions around continuous improvement in solar, wind, and hydrogen costs, although there is a slight twist for hydrogen. The first is around the dynamics of learning curves. As the exhibit shows, in the early stages of any product development, there are huge leaps in cost improvements, driven by scale, better know-how, more efficient manufacturing, and in the case of solar power, both better processes for installation and some technology improvements. However, as you drive costs lower, the cost of raw materials becomes a much larger component of overall costs, and your ability to lower costs further can be overwhelmed by moves in material costs. Any inability to pass on the costs will result in economics that do not justify additional capital and you find yourselves in a commodity cycle. This is something that we have seen in basic polymers for decades, and no buyer of polyethylene today can claim that they are benefiting from a learning curve improvement. Closer to home for solar, we are seeing the same issue today in semiconductors – not enough margin to invest as everyone has been trying to push costs lower. The expectation in the DOE study and highlighted in the CNBC take on the study below is that annual solar installations in the US need to rise by 3-4X to meet some of the renewable power goals the Biden Administration is looking for by 2030, while similar growth is expected in other markets – the solar panel and other component makers have to be making good money to achieve this.
