A Study on Power Grid Project Portfolio Based on Multiscale Feature Integration

Abstract

Power grid companies have established a feasibility study reserve phase to optimize the rolling schedule of annual investments, in which projects undergo preliminary feasibility studies, are incorporated into a project reserve pool, and subsequently proceed through release, implementation, and monitoring. However, the lack of synergy among projects in this process makes it difficult to maximize investment returns. To address this issue, this paper proposes a multiscale feature integration approach to power grid project portfolio management to optimize project management and investment efficiency. The proposed method constructs a multidimensional project association network integrating strategic, geographic, and semantic factors, and it extracts and fuses multiscale features to support project portfolio decision-making. Experimental results demonstrate that the proposed method effectively optimizes power grid project portfolios and is better suited to power grid projects than existing project optimization methods.