Skip to main content

Advanced AI Applications for Modelling, Optimization, Control, and Planning of Smart Grid

143kviews
Multi-layer state of health balancing control for a battery-based energy storage system to extend cycle life based on active equalization circuits
ORIGINAL RESEARCH
30 September 2022
Multi-layer state of health balancing control for a battery-based energy storage system to extend cycle life based on active equalization circuits
Xiaohang Li, 4 more and Jeremy Smith
State-of-health (SoH) imbalance of batteries brings the waste of capacity, the loss of cycle life and the additional maintenance cost to the BESS. The SoH imbalance widely exists among the battery packs in parallel and battery cells in series, while the current SoH balancing methods can only achieve the SoH equalization of the parallel layer or the series layer separately. This paper proposed a modified multi-layer SoH balancing control method for BESS based on the active equalization circuits. It can attain the SoH equalization among battery packs in parallel layer and battery cells in series layer simultaneously. In parallel layer, the SoH is balanced by controlling the output current of battery packs. The power distribution is determined by the initial equivalent SoH of each pack. In series layer, the series-connected battery cells among each pack will be equalized individually by offering disparate balancing currents with the fly-back converter equalization technique. Furthermore, unlike the common passive equalization technique using the shunt resistor to dissipate the redundant energy in cells with higher SoH, the fly-back converter equalization topology transfers the redundant energy from the cells with higher SoH to the cells with lower SoH, which achieves higher capacity and energy utilization efficiency. Simulation result based on a 3-packs-15-cells BESS verified the effectiveness of the proposed method. This method further prolong the cycle life of BESS about 52.9% and 18.3% comparing with the conventional active SoC balancing control and the existing multi-layer SoH equalization scheme, respectively.

4,551 views

10 citations

A new framework for short-term wind power probability forecasting considering spatial and temporal dependence of forecast errors
ORIGINAL RESEARCH
7 September 2022
A new framework for short-term wind power probability forecasting considering spatial and temporal dependence of forecast errors
Yong Sun, 3 more and Chaoyu Shi
The Since deterministic prediction errors of wind power cannot be avoided, probabilistic prediction can adequately describe the uncertainty of wind power and thus provide further guidance to dispatching authorities for decision making. Current probabilistic prediction methods for wind power are still incomplete in mining its physical variation process. Therefore, this paper constructs a new framework for short-term wind power probabilistic forecasting considering the spatio-temporal dependence of errors by mining the spatio-temporal characteristics of historical wind power data and numerical weather forecasts at numerical weather prediction (NWP). Firstly, the deterministic prediction results are obtained by an improved deep belief network (DBN); then, a multi-location NWP is introduced to propose a multi-level error scenario partitioning method considering the spatio-temporal dependence property. Finally, a new error sample set is formed by reconstructing the kernel density estimation method to adapt the modeling, and the short-term wind power probability prediction at different confidence levels is carried out. It is thus concluded that the effectiveness of the overall framework under the probabilistic prediction considering spatio-temporal dependence is verified in a wind farm in Jilin, China, and the prediction accuracy is effectively and significantly improved compared with the same confidence level, and the coverage of the evaluation index prediction interval is improved by 1.23%, 0.72%, and 0.80%, and the average bandwidth of the prediction interval is reduced by 2.14%, 1.40%, and 0.63%, which confirms the proposed the effectiveness and feasibility of the method.

2,973 views

8 citations

ORIGINAL RESEARCH
6 September 2022
Fault mechanisms and diagnosis methods for typical load mutation problems of turbo-generator sets
Kun Yao, 4 more and Yong Cao

2,656 views

4 citations

CORRECTION
31 August 2022
Corrigendum: Coot Algorithm for Optimal Carbon–Energy Combined Flow of Power Grid With Aluminum Plants
Liangdong Qin, 5 more and Yujun Lin

993 views

1 citations

ORIGINAL RESEARCH
12 August 2022
A Dynamic Evaluation Method for High-Permeability New Energy Distribution Network Planning Considering Multistage Development Trends
Junxiao Zhang, 4 more and Zuogang Guo

1,574 views

10 citations

BRIEF RESEARCH REPORT
26 July 2022
Short-Term Power Prediction of a Wind Farm Based on Empirical Mode Decomposition and Mayfly Algorithm–Back Propagation Neural Network
Zeweiyi Gong, 6 more and Hong Yu

1,955 views

4 citations

It is necessary to predict solar photovoltaic (PV) output and load profile to guarantee the security, stability, and reliability of hybrid solar power systems. Severe frequency fluctuations in hybrid solar systems are expected due to the intermittent nature of the solar photovoltaic (PV) output and the unexpected variation in load. This paper proposes designing a PID controller along with the integration of a battery energy storage system (BESS) and plug-in hybrid electric vehicle (PHEV) for frequency damping in the hybrid solar power system. The solar PV output is predicted with high accuracy using artificial neural networks (ANN) given that solar irradiance and cell temperature are inputs to the model. The variation in load is also forecasted considering the factors affecting the load using ANN. Optimum values of the PID controller have been found using genetic algorithm, particle swarm optimization, artificial bee colony, and firefly algorithm considering integral absolute error (IAE), integral square error (ISE), and integral time absolute error (ITAE) objective functions. IAE, ISE, ITAE, Rise time, settling time, peak overshoot and maximum frequency deviation have been measured for comparison and effectiveness. The transient behavior has been further improved by utilizing the power from BESS/PHEV to the power system. The results demonstrate the efficacy of the suggested design for frequency control using the genetic algorithm method along with ISE objective function compared with those obtained from the conventional, particle swarm optimization, artificial bee colony, and firefly algorithm techniques.

4,339 views

21 citations

An AGC Dynamic Optimization Method Based on Proximal Policy Optimization
ORIGINAL RESEARCH
13 July 2022
An AGC Dynamic Optimization Method Based on Proximal Policy Optimization
Zhao Liu, 3 more and Yanshun Zhao
The increasing penetration of renewable energy introduces more uncertainties and creates more fluctuations in power systems than ever before, which brings great challenges for Automatic Generation Control (AGC). It is necessary for grid operators to develop an advanced AGC strategy to handle fluctuations and uncertainties. AGC dynamic optimization is a sequential decision problem that can be formulated as a discrete-time Markov decision process. Therefore, this paper proposes a novel framework based on Proximal Policy Optimization (PPO) reinforcement learning algorithm to optimize power regulation among each AGC generator in advance. Then, the detailed modeling process of reward functions, state and action spaces designing is presented. The application of the proposed PPO-based AGC dynamic optimization framework is simulated on a modified IEEE 39-bus system, and compared with the classical proportional−integral (PI) control strategy and other reinforcement learning algorithms. The results of the case study show the framework proposed in this paper can make the frequency characteristic better satisfy the Control Performance Standard (CPS) under the scenario of large fluctuations in power systems.

5,248 views

18 citations

ORIGINAL RESEARCH
30 June 2022
A Non-Intrusive Residential Electric Bicycle Load Monitoring Method Based on Hybrid Feature Bitmap and DeiT
Qifeng Huang, 6 more and Haibo Xu
A Non-Intrusive Residential Electric Bicycle Load Monitoring Method Based on Hybrid Feature Bitmap and DeiT
Taking into account the energy management and fire safety, Electric bicycle is one of most significant household loads required real-time sensing for non-intrusive load monitoring. V-I trajectories, power quantities, harmonic characteristics are the basic selection in feature space for appliances identification. Based on the study of the charging mode of electric bicycle, this paper expands the V-I trajectory into V-△I trajectory for gaining the load signature with multi appliances working the simultaneously. We perform linearly interpolation and pixelation to obtain a bitmap of V-△I trajectory. Meanwhile, active and harmonic features are encoded and combined to form a hybrid feature bitmap, which is unique to compensate for the high harmonic feature loss caused by the pixelation of the V-△I trajectory. Further, we train the DeiT model on the self-built datasets, and performed two experiments under single and superposition working conditions for electric bicycles. Our case results indicate that the Diet model using hybrid feature bitmap offers better overall precision of prediction of electric bicycle, against other deep convolutional neural networks.

3,795 views

5 citations

OPINION
30 June 2022
A Hierarchical Distributed Operational Framework for Renewables-Assisted 5G Base Station Clusters and Smart Grid Interaction
Yifang Fan, 3 more and Hanrui Ran

1,791 views

6 citations

Reactive Voltage Control of Wind Farm Based on Tabu Algorithm
ORIGINAL RESEARCH
15 June 2022
Reactive Voltage Control of Wind Farm Based on Tabu Algorithm
Xin Ren, 6 more and Wei Wang
In view of the current wind farms are mostly multi-wind turbines, and it is difficult to accurately control a single wind turbine, the paper proposes a reactive power and voltage coordinated control strategy suitable for doubly-fed wind farms. The strategy is mainly divided into three layers. The first is the field group layer, which can obtain the reactive power compensation task of the entire field group according to the current voltage and voltage indicators of the field group collection station. The second is the field layer, according to the reactive power compensation tasks issued by the field group layer, the reactive power tasks are allocated to each field area based on the tabu search algorithm or the equal margin method. The third is the equipment layer, which allocates equal margins in the area according to the reactive power compensation tasks assigned by the field layer. At the field layer, this paper divides 66 wind turbines into 5 field areas to solve the reactive power compensation distribution task according to the voltage sensitivity characteristics of the wind turbines on different feeders.

2,210 views

10 citations