Wenchuan Wu

Yuwei Chen, Qinglai Guo, Hongbin Sun et al.

Currently, most district heating networks are running in a heat-setting mode, limiting the adjustment of the electrical power of combined heat and power (CHP) units. By considering the electrical power system (EPS) and district heating system (DHS) together, the peak regulatory capability of CHP units can be improved and renewable energy accommodation can be promoted. In this paper, a tractable integrated heat and electricity dispatch (IHED) model is described that addresses the thermal dynamic characteristics of pipelines and buildings to increase flexibility. To deal with the complexity of the optimization model, a water mass method (WMM) for pipeline thermal dynamics is proposed. Benefiting from the WMM, the proposed IHED model is an ordinary, non-linear model. An iterative algorithm based on the generalized Benders decomposition, and a sequential approach combined with the iterative algorithm and IPOPT, are proposed to solve the IHED model. Compared with a steady state model without thermal dynamics, considering the thermal dynamic characteristics in the DHS can further expand the peak regulatory capabilities of CHP units. The WMM is tested in the thermal dynamic simulations compared to an existing node method and a commercial simulation software. And the proposed solution strategy is verified in a small-scale system and a practical system. The simulation results of case studies are discussed to demonstrate the feasibility and economy of the dispatch model proposed here.

Zhuang Tian, Wenchuan Wu

Convex relaxation methods have been studied and used extensively to obtain an optimal solution to the optimal power flow (OPF) problem. Meanwhile, convex relaxed power flow equations are also prerequisites for efficiently solving a wide range of problems in power systems including mixed-integer nonlinear programming (MINLP) and distributed optimization. When the exactness of convex relaxations is not guaranteed, it is important to recover a feasible solution for the convex relaxation methods. This paper presents an alternative convex optimization (ACP) approach that can efficiently recover a feasible solution from the result of second-order cone programming (SOCP) relaxed OPF in mesh networks. The OPF problem is first formulated as a difference-of-convex (DC) programming problem, then efficiently solved by a penalty convex concave procedure (CCP). CCP iteratively linearizes the concave parts of the power flow constraints and solves a convex approximation of the DCP problem. Numerical tests show that the proposed method can find a global or near-global optimal solution to the AC OPF problem, and outperforms those semidefinite programming (SDP) based algorithms.

Xu Yang, Chenhui Lin, Haotian Liu et al.

As large-scale distributed energy resources are integrated into the active distribution networks (ADNs), effective energy management in ADNs becomes increasingly prominent compared to traditional distribution networks. Although advanced reinforcement learning (RL) methods, which alleviate the burden of complicated modelling and optimization, have greatly improved the efficiency of energy management in ADNs, safety becomes a critical concern for RL applications in real-world problems. Since the design and adjustment of penalty functions, which correspond to operational safety constraints, requires extensive domain knowledge in RL and power system operation, the emerging ADN operators call for a more flexible and customized approach to address the penalty functions so that the operational safety and efficiency can be further enhanced. Empowered with strong comprehension, reasoning, and in-context learning capabilities, large language models (LLMs) provide a promising way to assist safe RL for energy management in ADNs. In this paper, we introduce the LLM to comprehend operational safety requirements in ADNs and generate corresponding penalty functions. In addition, we propose an RL2 mechanism to refine the generated functions iteratively and adaptively through multi-round dialogues, in which the LLM agent adjusts the functions' pattern and parameters based on training and test performance of the downstream RL agent. The proposed method significantly reduces the intervention of the ADN operators. Comprehensive test results demonstrate the effectiveness of the proposed method.

Xu Yang, Chenhui Lin, Haotian Liu et al.

With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex multi-scenario, multi-objective problem. Although expert engineers have developed numerous domain specific models (DSMs) to address distinct technical problems, mastering, integrating, and orchestrating these heterogeneous DSMs still entail considerable overhead for ADN operators. Therefore, an intelligent approach is urgently required to unify these DSMs and enable efficient coordination. To address this challenge, this paper proposes the ADN-Agent architecture, which leverages a general large language model (LLM) to coordinate multiple DSMs, enabling adaptive intent recognition, task decomposition, and DSM invocation. Within the ADN-Agent, we design a novel communication mechanism that provides a unified and flexible interface for diverse heterogeneous DSMs. Finally, for some language-intensive subtasks, we propose an automated training pipeline for fine-tuning small language models, thereby effectively enhancing the overall problem-solving capability of the system. Comprehensive comparisons and ablation experiments validate the efficacy of the proposed method and demonstrate that the ADN-Agent architecture outperforms existing LLM application paradigms.

Haotian Liu, Wenchuan Wu

In Volt/Var control (VVC) of active distribution networks(ADNs), both slow timescale discrete devices (STDDs) and fast timescale continuous devices (FTCDs) are involved. The STDDs such as on-load tap changers (OLTC) and FTCDs such as distributed generators should be coordinated in time sequence. Such VCC is formulated as a two-timescale optimization problem to jointly optimize FTCDs and STDDs in ADNs. Traditional optimization methods are heavily based on accurate models of the system, but sometimes impractical because of their unaffordable effort on modelling. In this paper, a novel bi-level off-policy reinforcement learning (RL) algorithm is proposed to solve this problem in a model-free manner. A Bi-level Markov decision process (BMDP) is defined to describe the two-timescale VVC problem and separate agents are set up for the slow and fast timescale sub-problems. For the fast timescale sub-problem, we adopt an off-policy RL method soft actor-critic with high sample efficiency. For the slow one, we develop an off-policy multi-discrete soft actor-critic (MDSAC) algorithm to address the curse of dimensionality with various STDDs. To mitigate the non-stationary issue existing the two agents' learning processes, we propose a multi-timescale off-policy correction (MTOPC) method by adopting importance sampling technique. Comprehensive numerical studies not only demonstrate that the proposed method can achieve stable and satisfactory optimization of both STDDs and FTCDs without any model information, but also support that the proposed method outperforms existing two-timescale VVC methods.

Haotian Liu, Wenchuan Wu

The distributed Volt/Var control (VVC) methods have been widely studied for active distribution networks(ADNs), which is based on perfect model and real-time P2P communication. However, the model is always incomplete with significant parameter errors and such P2P communication system is hard to maintain. In this paper, we propose an online multi-agent reinforcement learning and decentralized control framework (OLDC) for VVC. In this framework, the VVC problem is formulated as a constrained Markov game and we propose a novel multi-agent constrained soft actor-critic (MACSAC) reinforcement learning algorithm. MACSAC is used to train the control agents online, so the accurate ADN model is no longer needed. Then, the trained agents can realize decentralized optimal control using local measurements without real-time P2P communication. The OLDC with MACSAC has shown extraordinary flexibility, efficiency and robustness to various computing and communication conditions. Numerical simulations on IEEE test cases not only demonstrate that the proposed MACSAC outperforms the state-of-art learning algorithms, but also support the superiority of our OLDC framework in the online application.

Haotian Liu, Wenchuan Wu

Model-based Vol/VAR optimization method is widely used to eliminate voltage violations and reduce network losses. However, the parameters of active distribution networks(ADNs) are not onsite identified, so significant errors may be involved in the model and make the model-based method infeasible. To cope with this critical issue, we propose a novel two-stage deep reinforcement learning (DRL) method to improve the voltage profile by regulating inverter-based energy resources, which consists of offline stage and online stage. In the offline stage, a highly efficient adversarial reinforcement learning algorithm is developed to train an offline agent robust to the model mismatch. In the sequential online stage, we transfer the offline agent safely as the online agent to perform continuous learning and controlling online with significantly improved safety and efficiency. Numerical simulations on IEEE test cases not only demonstrate that the proposed adversarial reinforcement learning algorithm outperforms the state-of-art algorithm, but also show that our proposed two-stage method achieves much better performance than the existing DRL based methods in the online application.

Xin Chen, Wenchuan Wu, Boming Zhang

To settle a large-scale integration of renewable distributed generations (DGs), it requires to assess the maximal DG hosting capacity of active distribution networks (ADNs). For fully exploiting the ability of ADNs to accommodate DG, this paper proposes a robust comprehensive DG capacity assessment method considering three-phase power flow modelling and active network management (ANM) techniques. The two-stage adjustable robust optimization is employed to tackle the uncertainties of load demands and DG outputs. With our method, system planners can obtain the maximum penetration level of DGs with their optimal sizing and sitting decisions. Meanwhile, the robust optimal ANM schemes can be generated for each operation time period, including network reconfiguration, on-load-tap-changers regulation, and reactive power compensation. In addition, a three-step optimization algorithm is proposed to enhance the accuracy of DG capacity assessment results. The optimality and robustness of our method are validated via numerical tests on an unbalanced IEEE 33-bus distribution system.

Weiye Zheng, Wenchuan Wu, Antonio Gomez-Exposito et al.

This paper proposes a fully distributed robust state-estimation (D-RBSE) method that is applicable to multi-area power systems with nonlinear measurements. We extend the recently introduced bilinear formulation of state estimation problems to a robust model. A distributed bilinear state-estimation procedure is developed. In both linear stages, the state estimation problem in each area is solved locally, with minimal data exchange with its neighbors. The intermediate nonlinear transformation can be performed by all areas in parallel without any need of inter-regional communication. This algorithm does not require a central coordinator and can compress bad measurements by introducing a robust state estimation model. Numerical tests on IEEE 14-bus and 118-bus benchmark systems demonstrate the validity of the method.