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

TL;DR

The study addresses wind curtailment in cold regions caused by CHP inflexibility by proposing a collaborative capacity planning framework for hybrid heat sources to broaden RES accommodation. It introduces Adaptive Multi-Objective Bayesian Optimization (AMBO), a noise-aware MOBO algorithm that yields a diverse and well-distributed Pareto front without relying on planner-specified parameters, and pairs it with a time-series scenario generator based on K-medoids. A noise model links simulated results to real-world performance, and the evaluation uses time-series operation simulations to compute two objectives: $C_{ann}$ and $P_{RES}$, under detailed thermal and electrical constraints. Case studies demonstrate AMBO’s superior efficiency, robustness to simulation noise, and scalability to large, high-dimensional planning problems, highlighting practical gains in flexible electricity–heat coupling and RES integration in cold regions.

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.

Figures (11)

• Figure 1: The motivation for planning of the hybrid heat sources.
• Figure 2: The influence of simulation deviation on the objective function.
• Figure 3: Relationship of the algorithms presented in the pseudocode
• Figure 4: The typical curves of electric load, heat load, wind power, and solar power.
• Figure 5: The average errors from different scenario selection methods.