Toward Carbon-Neutral Electric Power Systems in the New York State: a Novel Multi-Scale Bottom-Up Optimization Framework Coupled with Machine Learning for Capacity Planning at Hourly Resolution

Abstract

In this work, we propose a novel multi-scale bottom-up optimization framework for the carbon-neutral transition planning of the electric power sector, which incorporates hourly time scale and electricity storage to address the reliability and energy balance issues of the future deep-decarbonized power systems. In addition to the technology and capacity information for each facility, the proposed framework also accounts for facility ages, which are usually omitted in the literature, without significantly increasing the computational demand. To reduce the computational requirement of simultaneously optimizing capacity planning and hourly systems operations over the next few decades, a reduced model is developed based on representative days, using a novel approach that integrates multiple machine learning techniques. Based on the optimal transition pathways, hourly operational simulations are conducted for every year within the planning horizon to obtain detailed optimization results. To illustrate the applicability of the proposed framework, a case study for the New York State is presented through two cases, with and without electricity storage capacity expansion. The proposed approach using principal component analysis coupled with K-means outcompetes multiple conventional approaches of using clustering techniques directly. The transition planning results show that the total generation capacity for the case with electricity capacity expansion is 39% higher than the other case, while the latter case has 200% more generation capacity from non-intermittent sources. Detailed hourly operational simulation results indicate that offshore wind, hydro, and utility solar are the primary power sources by 2040 for the case with electricity storage capacity expansion, while hydro, offshore wind, and nuclear are the main electricity sources for the other case.

A Holistic Approach to Power Systems Using Innovative Machine Learning and System Dynamics

“…In their study [4], Dehghani et al recently demonstrated the importance of including the power plants' lifetime as a factor in the generation expansion planning problem, guided by a deep learning model to predict annual peak demand growth. Later, Zhao and You extended their work in [3] by introducing a novel robust optimization framework that integrated multiple machine learning techniques to provide more realistic transition pathways for New York [5]. Machine learning based on clustering techniques was used as a first step to reduce the model, making it less computationally demanding.…”

Optimal Transition Pathway of Power Systems for Guangdong-Hongkong-Macau Region in China

“…It is necessary to provides more details on energy transition with finer spatial resolution. Zhao and You [6] proposed a bottom-up optimization framework for low-carbon transition of New York's power system. Luo et al [7] analyzed transition pathways o energy systems towards deep decarbonization for Sichuan province, China.…”

Data-Driven Stochastic Robust Optimization for Industrial Energy System Considering Renewable Energy Penetration

“…The renewable energy supply is an efficient technology in reducing GHG emissions, and sources like solar, wind, and bioenergy have been broadly studied for system sustainable development. − Solar heat and wind energy have been the most popular renewable energies because of the source availability and technology maturity. − In the design and optimization of the integrated energy systems, superstructure-based methods have been widely applied, and the optimization problem can be formulated as a mixed-integer linear programming (MILP) problem or a mixed-integer nonlinear programming (MINLP) problem depending on whether the nonlinear terms were contained. Sánchez-Bautista et al presented a mathematical programming model for sustainable energy systems planning .…”