Adaptive Multi-Objective Bayesian Optimization for Capacity Planning of Hybrid Heat Sources in Electric-Heat Coupling Systems of Cold Regions

TL;DR

This paper presents an adaptive multi-objective Bayesian optimization method for capacity planning of hybrid heat sources in cold regions, improving flexibility, efficiency, and sustainability in electric-heat systems.

Contribution

It introduces a novel AMBO algorithm that eliminates subjective parameters and incorporates noise modeling for more accurate, diverse, and efficient capacity planning in cold-region heat systems.

Findings

AMBO outperforms traditional algorithms in Pareto front diversity.

The approach reduces planning subjectivity and improves sample efficiency.

Simulation results confirm better real-world applicability and sustainability.

Abstract

The traditional heat-load generation pattern of combined heat and power generators has become a problem leading to renewable energy source (RES) power curtailment in cold regions, motivating the proposal of a planning model for alternative heat sources. The model aims to identify non-dominant capacity allocation schemes for heat pumps, thermal energy storage, electric boilers, and combined storage heaters to construct a Pareto front, considering both economic and sustainable objectives. The integration of various heat sources from both generation and consumption sides enhances flexibility in utilization. The study introduces a novel optimization algorithm, the adaptive multi-objective Bayesian optimization (AMBO). Compared to other widely used multi-objective optimization algorithms, AMBO eliminates predefined parameters that may introduce subjectivity from planners. Beyond the algorithm, the proposed model incorporates a noise term to account for inevitable simulation deviations, enabling the identification of better-performing planning results that meet the unique requirements of cold regions. What's more, the characteristics of electric-thermal coupling scenarios are captured and reflected in the operation simulation model to make sure the simulation is close to reality. Numerical simulation verifies the superiority of the proposed approach in generating a more diverse and evenly distributed Pareto front in a sample-efficient manner, providing comprehensive and objective planning choices.