Long-Term Carbon-Efficient Planning for Geographically Shiftable Resources: A Monte Carlo Tree Search Approach

The global climate challenge is demanding urgent actions for decarbonization, while electric power systems take the major roles in the clean energy transition. Due to the existence of spatially and temporally dispersed renewable energy resources and the uneven distribution of carbon emission intensity throughout the grid, it is worth investigating future load planning and demand management to offset those generations with higher carbon emission rates. Such techniques include inter-region utilization of geographically shiftable resources and stochastic renewable energy. For instance, data centers are perceived as major carbon emission producers in the future due to increasing information load, while they hold untapped capability of geographical load balancing. In this paper, we focus on locating and operating geographically shiftable resources, and propose a novel planning and operation model minimizing the system-level carbon emissions. This model decides the optimal locations for shiftable resource expansion along with the power dispatch schedule. To accommodate future system operation patterns and a wide range of operating conditions, we incorporate 20-year fine-grained load and renewables scenarios for grid simulations of realistic sizes (e.g., up to 1888 buses). To tackle the computational challenges coming from the combinatorial nature of such large-scale planning problems, we develop a customized Monte Carlo Tree Search (MCTS) method, which can find reasonable solutions satisfying solution time limits. Besides, MCTS enables flexible time window settings and offline solution adjustments. Extensive simulations validate that our planning model can reduce more than 10% carbon emission across all setups. Compared to off-the-shelf optimization solvers such as Gurobi, our method achieves up to 8.1X acceleration, while the solution gaps are less than 1.5% in large-scale cases. Moreover, our method can find reasonable solutions within different time windows, unlike other benchmarked solvers that require considerable time or fail to produce feasible solutions.