KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 40

Some of the metrics are blocked by your
consent settings
Small-Signal Stability Enhancement Through Integration of Distributed Grid-Forming Loads Considering Multi-Agent Collaboration
(2025-01-01)
Ngamroo, Issarachai
;
Surinkaew, Tossaporn
;
Mitani, Yasunori
The integration of distributed controllable loads in future islanding microgrids (MGs) is growing. This creates new opportunities to actively shape grid frequency and voltage. As a result, it leads to the development of distributed grid-forming loads (DGFM-Ls). Simultaneously, it is equally crucial to ensure robustness, particularly in preserving small-signal stability amid the multi-agent collaboration. This paper presents a strategy for the small-signal stability enhancement in islanding MGs with DGFM-Ls. The small-signal models of the MG with DGFM-Ls are mathematically developed and analyzed. The multi-agent cooperation is modelled to improve the small-signal stability of the MG with DGFM-Ls. Additionally, uncertainties from multi-agent cooperation, such as partial or complete lack of measured signal observability, are considered. Data quality issues are also taken into account under various conditions. Simulation results are conducted in a MG with a significant penetration of inverter-based resources under various MG operating points and conditions such as topology changes and unavailability of certain agents.
Some of the metrics are blocked by your
consent settings
Improving Inertia Estimation Accuracy Using An Adaptive Framework for Centre of Inertia Selection
(2025-01-01)
Jamraspong, Panupong
;
Surinkaew, Tossaporn
;
Ngamroo, Issarachai
;
Watanabe, Masayuki
The centre of inertia (CoI) is essential for accurate system inertia estimation. Assuming the CoI is static and based on fixed measurements ignores the fact that it changes over time. This can lead to inaccurate estimates since the CoI shifts as system conditions change. To address this issue, this paper presents an adaptive data-driven CoI selection framework that dynamically selects the optimal CoI in a multi-measurement power system. The optimal CoI is used based on selected parameters to estimate the total inertia between any two regions. This process is conducted at each time interval or whenever stamped data from system measurements are received. Simulation results verify that the proposed adaptive CoI selection, compared to a conventional method where the CoI is fixed to a specific pair of measurements, provides more accurate estimation results under varying loading conditions, perturbations, and inertia levels. This paper also explores future developments and identify gaps, while also discussing potential directions for upcoming research works.
Some of the metrics are blocked by your
consent settings
Communication-Driven Learning-Based Harmonic Mitigation Approach for Grid-Forming Converters
(2025-01-01)
Surinkaew, Tossaporn
;
Ngamroo, Issarachai
This paper proposes a harmonic mitigation framework for multi-bus microgrids (MGs) that utilizes a communication-driven learning-based approach. A dedicated neural network is used to model additional intelligent control loops. We also develop a global harmonic distortion (GHD) matrix, formulated by the total harmonic distortion at each point of common coupling (PCC). The GHD specifically focuses on harmonic orders that exceed acceptable limits observed from multi-bus systems. The GHD is used as an input signal of the neural network. Based on the system conditions, the developed GHD allows the system to intelligently trigger the control signal whenever dominant harmonic orders are detected and need mitigation. Other input signals include the voltage and current vectors from all PCCs, which contain local harmonics. To train the network, various critical system operating points are collected as time-series data. At this stage, system parameters are not needed; however, secure communication for data transfer is considered instead. Consequently, the collected data are used to train the network using the developed loss functions that focus on harmonic mitigation. After network training, the output signal is sent to the summing points in the direct axis of the inner voltage and current control loops of different models of grid-forming IBRs units. Simulation results are verified in a modified multi-bus MG with IBRs under various operating conditions.
Some of the metrics are blocked by your
consent settings
A Wildfire Risk Impact Index (WRII) for Power Distribution Systems: Integrating GIS and AHP
(2025-01-01)
Phantanaikasem, Pongpavee
;
Jamroen, Chaowanan
;
Surinkaew, Tossaporn
Wildfires pose a significant threat to power distribution systems, leading to disruptions, infrastructure damage, and economic losses. The conventional fire weather index (FWI) is widely used for wildfire risk assessment, but primarily relies on meteorological factors and does not explicitly account for the spatial distribution of critical infrastructure. Therefore, this study proposes a new wildfire risk impact index (WRII) to assess wildfire risk and severity on power distribution systems. The WRII is developed using the geographic information system (GIS) and analytical hierarchy process (AHP), integrating multiple spatial variables (i.e., temperature, wind speed, relative humidity, and topography), hotspot proximity to key infrastructures (i.e., power distribution systems, fire stations, and roads), and the number of connected power system points. A case study in Chiang Mai, Thailand, is conducted using the QGIS to demonstrate the applicability of WRII and its superiority over the FWI. The results highlight spatial variations in wildfire risk, offering valuable insights for power system operators. The WRII enhances wildfire preparedness and mitigation strategies.
Some of the metrics are blocked by your
consent settings
Intelligence-Driven Grid-Forming Converter Control for Islanding Microgrids
(2025-01-01)
Ngamroo, Issarachai
;
Surinkaew, Tossaporn
;
Mitani, Yasunori
In modern microgrids (MGs) with high penetration of distributed energy resources (DERs), system reconfiguration occurs more frequently and becomes a significant issue. Fixed-parameter controllers may not handle these tasks effectively, as they lack the ability to adapt to the dynamic conditions in such environments. This paper proposes an intelligence-driven grid-forming (GFM) converter control method for islanding MGs using a robustness-guided neural network (RNN). To enhance the adaptability of the proposed method, traditional proportional-integral controllers in the GFM primary control loops are entirely replaced by the RNN. The RNN is trained by a robustness-guided strategy to replicate their robust behaviors. All the training stages are purely data-driven methods, which means that no system parameters are required for the controller design. Consequently, the proposed method is an intelligence-driven modelless GFM converter control. Compared with traditional methods, the simulation results in all testing scenarios show the clear benefits of the proposed method. The proposed method reduces overshoots by more than 71.24%, which keeps all damping ratios within the stable region and provides faster stabilization. In comparison to traditional methods, at the highest probability, the proposed method improves damping by over 14.7% and reduces the rates of change of frequency and voltage by over 59.97%. Additionally, the proposed method effectively suppresses the interactions between state variables caused by inverter-based resources, with frequencies ranging from 1.0 Hz to 1.422 Hz. Consequently, these frequencies contribute less than 19.79% To the observed transient responses.
Some of the metrics are blocked by your
consent settings
Embedded Intelligent Reactive Power Control for Distributed Controllable Loads to Support Grid Voltage Considering Islanding Conditions
(2025-01-01)
Surinkaew, Tossaporn
;
Pinthurat, Watcharakorn
;
Yang, Jun
;
Ngamroo, Issarachai
The increasing integration of distributed energy resources (DERs) along with distributed controllable loads (DCLs), presents significant challenges for maintaining grid stability and effectively incorporating these resources. Traditionally, DERs have supported microgrid (MG) stability primarily through active power control loops, which has limited their ability to manage power output effectively. This paper introduces a novel embedded intelligent reactive power control framework for DCLs, designed to bolster grid voltage stability during islanding conditions. This framework seamlessly integrates reactive power control loops as ancillary services within DCLs, which can also support other grid-forming (GFM) resources. The DCL is modeled with grid-following (GFL) control loops, which incorporate an embedded intelligent reactive power control loop into the voltage control system. The proposed intelligent framework applies a modified long-short term memory neural network to imitate reactive power behavior. The network is trained with the special loss function to minimize voltage variation. This enables the intelligent GFL control to accurately follow voltage and frequency references from the GFM resources and adapt to unexpected islanding scenarios. Simulation results in a low-inertia MG with DERs confirm the superiority of the proposed framework. It outperforms conventional methods, including mixed H<inf>2</inf>/H∞ strategy, model predictive control, and convolutional neural network. Through a comprehensive evaluation, the proposed strategy shows superior performance in transient response, voltage stability, power dynamics, statistical analysis, and damping performance.
Some of the metrics are blocked by your
consent settings
An Intelligent Voltage Control With Power Loss Model Integration in Active Distribution Network
(2025-01-01)
Pinthurat, Watcharakorn
;
Deanseekeaw, Anurak
;
Surinkaew, Tossaporn
;
Boonraksa, Terapong
;
Boonraksa, Promphak
The increasing integration of renewable energy sources (RESs), particularly distributed PV systems, poses significant challenges to voltage stability in modern distribution systems. Existing studies use reactive power control to address voltage deviations but incur high losses, with no systematic solution achieving both voltage regulation and loss minimization. This paper proposes a novel voltage control strategy based on multi-agent deep reinforcement learning (MADRL), leveraging decentralized agent coordination to maintain voltage levels while minimizing PV inverter and system losses. Also, a new framework is formulated based on a Markov game, wherein each PV inverter operates as an autonomous agent that adjusts its reactive power output via a centralized training process. The agents, defined as PV inverters, employ the multi-agent twin-delayed deep deterministic policy gradient algorithm to collaboratively minimize voltage deviations. Through the use of local observations and shared global information during training, agents learn robust control policies that generalize to varying conditions and enable decentralized execution without ongoing coordination. Performance of the proposed control strategy is validated on a modified IEEE 33-node distribution system under high variability in PV generation and load demand. Results show that the proposed control strategy significantly improves voltage regulation and reduces power losses compared to state-of-the-art MADRL techniques.
Some of the metrics are blocked by your
consent settings
Two-Stage Small-Signal Stability-Assisted Framework Using Controllable Loads in Reconfigurable Microgrids
(2025-01-01)
Surinkaew, Tossaporn
;
Pinthurat, Watcharakorn
;
Marungsri, Boonruang
;
Hredzak, Branislav
Reconfiguration in low-inertia microgrids (MGs) can often result in a critical small-signal stability margin. In this condition, the ability of inverter-based resources (IBRs) to provide voltage and frequency support may be insufficient. To maintain stable operation without interruptions, this paper presents a control strategy that first evaluates the effect of MG reconfiguration on system stability and then employs controllable loads as an enhancement mechanism to improve small-signal stability in scenarios involving reconfigurable MGs, particularly during islanded operation or high-demand situations such as sudden load changes or fault recovery. Mathematical models of system reconfiguration are presented. Then, we demonstrate how reconfiguration in MGs can result in marginal small-signal stability. The proposed framework operates in two stages: (i) assessing optimal breaker/switch configurations to ensure a baseline stability margin, and (ii) using controllable loads to fine-tune and improve damping performance. It is shown that the proposed framework can shift stability from critical or unstable levels to an acceptable range, making the initial conditions of reconfigured MGs feasible. Simulation results in a reconfigurable MG with different portions of IBRs and controllable loads demonstrate the effectiveness of the proposed framework in using controllable loads to successfully enhance small-signal stability. The proposed strategy ensures that the reconfigured MGs remain stable after reconfigurations.
Some of the metrics are blocked by your
consent settings
An overview of reinforcement learning-based approaches for smart home energy management systems with energy storages
(2024-09-01)
Pinthurat, Watcharakorn
;
Surinkaew, Tossaporn
;
Hredzak, Branislav
The paper's state-of-the-art review focuses on an in-depth evaluation of smart home energy management systems which employ reinforcement learning-based methods to integrate energy storages. In order to optimize energy consumption and improve overall sustainability while maintaining technical and economic constraints, the paper first investigates the multi-faceted aspects of integrating energy storages into smart homes. Second, an overview of a smart home system and a theoretical background of reinforcement learning-based algorithms are given and discussed. Consequently, this study delves into the challenges and benefits of integrating energy storage, specifically looking at ways to lessen the impact of renewable sources’ intermittency, improve grid stability, and streamline efficient energy storage management. Thirdly, the paper highlights the beneficial features of smart home energy storage integration, including reduced costs, increased system resilience, and improved energy efficiency. Therefore, cutting-edge reinforcement learning-based methods utilized in smart home energy management systems that incorporate energy storage are thoroughly examined by evaluating their effectiveness and adaptability, taking into account both multi-agent and single-agent reinforcement learning-based methods. Finally, the study identifies potential research directions, including the development of hybrid reinforcement learning algorithms, integration of demand-side management strategies, and addressing privacy and security concerns in reinforcement learning-based smart home energy management systems. While some research has made use of single-agent reinforcement learning, smart home energy storage systems that use energy storages seldom use multi-agent reinforcement learning techniques. Researchers, practitioners, and policymakers will be able to use this work as a foundation to build smart, sustainable home energy systems.
Some of the metrics are blocked by your
consent settings
Simultaneous Voltage Regulation and Unbalance Compensation in Distribution Systems With an Information-Driven Learning Approach
(2024-04-01)
Pinthurat, Watcharakorn
;
Surinkaew, Tossaporn
;
Hredzak, Branislav
High penetration and uneven allocation of single-phase and three-phase loads together with photovoltaic (PV) sources in low-voltage distribution systems can result in voltage unbalance and voltage regulation challenges. Previous approaches that treated the voltage unbalance and the voltage regulation as separate problems may have overlooked their interdependencies, thus potentially limiting the effectiveness of those methods. This article proposes a novel framework that can regulate the bus voltages and compensate for the voltage unbalance simultaneously, without requiring any information on phase connection of single-phase PV inverters. The proposed framework is designed based on a Markov game. The bus voltage deviation and the voltage unbalance factor (VUF) are used to define the reward function. Local observation states are obtained from smart meters, and the reactive current of the PV-based voltage source inverter (VSI) is defined as the action within the framework. The framework employs a multiagent deep deterministic policy gradient (known as multiagent deep deterministic policy gradient) algorithm that incorporates centralized training and decentralized execution. It is utilized to solve the framework. To ensure its effectiveness, the framework is trained and tested using real data acquired from smart meters. This data encompasses information on PV generation and load demand. The obtained results demonstrate that the bus voltages are regulated close to their nominal value and the VUF is maintained at less than 2% while the PV-VSIs operate within predefined limits.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results