This paper reviews the evolution of four generations of concepts of the “smart grid,” the role of computational intelligence in meeting their needs, and key examples of relevant research and tools. The first generation focused on traditional concepts like building more wires, automated meters, workforce development, and reducing blackouts, but it already had many uses for computational intelligence. The second generation, promulgated by Massoud Amin at EPRI, entailed greater use of global control systems and stability concepts, and coincided with new issues of market design and time of day pricing. New third generation and fourth generation concepts aim for a truly intelligent power grid, addressing new requirements for a sustainable global energy system, making full use of new methods for optimization across time, pluggable electric vehicles, renewable energy, storage, distributed intelligence and new neural networks for handling complexity and stochastic challenges. Important opportunities for society and new fundamental research challenges exist throughout.