[Paper Review] Data-Driven Distributionally Robust Scheduling of Community Integrated Energy Systems with Uncertain Renewable Generations Considering Integrated Demand Response

Yang Li, Meng Han+3 more|arXiv (Cornell University)|Jan 21, 2023

Smart Grid Energy Management15 citations

TL;DR

This paper proposes a data-driven two-stage distributionally robust optimization framework for scheduling a community integrated energy system under renewable generation uncertainty, integrating demand response and building thermal comfort considerations. It uses a GAN-based scenario generator and a mixed uncertainty set to improve economy and robustness.

ABSTRACT

A community integrated energy system (CIES) is an important carrier of the energy internet and smart city in geographical and functional terms. Its emergence provides a new solution to the problems of energy utilization and environmental pollution. To coordinate the integrated demand response and uncertainty of renewable energy generation (RGs), a data-driven two-stage distributionally robust optimization (DRO) model is constructed. A comprehensive norm consisting of the 1-norm and infinity-norm is used as the uncertainty probability distribution information set, thereby avoiding complex probability density information. To address multiple uncertainties of RGs, a generative adversarial network based on the Wasserstein distance with gradient penalty is proposed to generate RG scenarios, which has wide applicability. To further tap the potential of the demand response, we take into account the ambiguity of human thermal comfort and the thermal inertia of buildings. Thus, an integrated demand response mechanism is developed that effectively promotes the consumption of renewable energy. The proposed method is simulated in an actual CIES in North China. In comparison with traditional stochastic programming and robust optimization, it is verified that the proposed DRO model properly balances the relationship between economical operation and robustness while exhibiting stronger adaptability. Furthermore, our approach outperforms other commonly used DRO methods with better operational economy, lower renewable power curtailment rate, and higher computational efficiency.

Motivation & Objective

• Motivate robust scheduling of Community Integrated Energy Systems (CIES) under uncertain renewable generation.
• Develop a data-driven two-stage distributionally robust optimization (DRO) model.
• Incorporate integrated demand response accounting for thermal comfort and building thermal inertia.
• Employ a GAN-based scenario generator to capture renewable generation uncertainty.
• Demonstrate the method on a real CIES in North China and compare with traditional methods.

Proposed method

• Formulate a two-stage distributionally robust optimization model with an uncertainty information set composed of a 1-norm and infinity-norm mix.
• Develop a generative adversarial network (GAN) based on the Wasserstein distance with gradient penalty to generate renewable generation scenarios.
• Incorporate an integrated demand response mechanism that accounts for human thermal comfort ambiguity and building thermal inertia.
• Solve the DRO model to balance economic operation and robustness.
• Compare with stochastic programming and robust optimization to evaluate performance and efficiency.

Experimental results

Research questions

• RQ1 How can DRO be used to robustly schedule CIES under uncertain renewables while leveraging demand response?
• RQ2 What is the impact of using a mixed norm uncertainty set on solution robustness and economy?
• RQ3 Can GAN-generated scenarios improve the representation of renewable uncertainty for DRO?
• RQ4 How does integrated demand response considering thermal comfort and inertia affect renewable utilization and costs?
• RQ5 How does the proposed approach perform relative to traditional stochastic programming and robust optimization?

Key findings

• The DRO model balances economic operation and robustness under renewable uncertainty.
• GAN-generated scenarios based on Wasserstein distance improve scenario generation for DRO.
• Integrated demand response with thermal comfort and inertia enhances renewable energy consumption and reduces curtailment.
• The proposed method shows better operational economy, lower curtailment, and higher computational efficiency than other DRO approaches.
• Simulation on a real North China CIES demonstrates practical applicability and robustness improvements over traditional methods.