Linghua Zhang

Dr. Linghua Zhang

orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 December 2019 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
LYLiang Yu
Liang Yu
WXWeiwei Xie
Weiwei Xie
DXDi Xie
Di Xie
YZYulong Zou
Yulong Zou
DZDengyin Zhang
Dengyin Zhang
TJTao Jiang
Tao Jiang
In this paper, we investigate an energy cost minimization problem for a smart home in the absence of a building thermal dynamics model with the consideration of a comfortable temperature range. Due to the existence of model uncertainty, parameter uncertainty (e.g., renewable generation output, non-shiftable power demand, outdoor temperature, and electricity price) and temporally-coupled operational constraints, it is very challenging to design an optimal energy management algorithm for scheduling Heating, Ventilation, and Air Conditioning (HVAC) systems and energy storage systems in the smart home. To address the challenge, we first formulate the above problem as a Markov decision process, and then propose an energy management algorithm based on Deep Deterministic Policy Gradients (DDPG). It is worth mentioning that the proposed algorithm does not require the prior knowledge of uncertain parameters and building thermal dynamics model. Simulation results based on real-world traces demonstrate the effectiveness and robustness of the proposed algorithm.

17 January 2022 in IET Generation, Transmission & Distribution
Verified
Journal Article
Open access
PDF file
CTCheng Tong
Cheng Tong
LZLinghua Zhang
Linghua Zhang
HLHao Li
Hao Li
YDYin Ding
Yin Ding
Accurate load forecasting is essential for ensuring safe, stable, and economical operation of energy internet. Temporal convolutional networks (TCNs) have demonstrated superior performance, when compared to recurrent neural network models, since their introduction in electrical load forecasting. However, the current TCN‐based models are unable to obtain a large receptive field and strong long‐time feature extraction capability owing to the specific kernel size of the 1D convolution structure. This paper proposes a temporal inception convolutional network based on multi‐head attention (TICN‐Att) for ultra‐short‐term load prediction. By introducing an inception structure into the TCN, the proposed model can extract multi‐dimensional information from the input features, through the multiple hidden convolutional kernels of different scales, without stacking layers depth‐wise. Simultaneously, by introducing a multi‐head attention mechanism, the TICN‐Att model has a long time‐dependent extraction capability, similar to that of the long short‐term memory network models. The generalization and validity of the model are tested using the global energy forecasting competition (GEFCOM2014) dataset, electrical load data of a city in Jiangsu (China), and PJM power system dataset. The experimental results demonstrated that the proposed model has the best prediction effect, compared to the other state‐of‐the‐art models.

14 June 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
FHFeng Hu
Feng Hu
LZLinghua Zhang
Linghua Zhang
JWJiaqi Wang
Jiaqi Wang
To enhance the safety of grid operations, this paper proposes a high-precision short-term photovoltaic (PV) power forecasting method that integrates information from surrounding PV stations and deep learning prediction models. The proposed method utilizes numerical weather prediction (NWP) data of the target PV station and highly correlated features from nearby stations as inputs. This study first analyzes the correlation between irradiance and power sequences and calculates a comprehensive similarity index based on distance factors. Stations with high-similarity indices are selected as data sources. Subsequently, Bayesian optimization is employed to determine the optimal data fusion ratio. The selected data are then used to model power predictions through the convolutional long short-term memory with attention (Conv-LSTM-ATT) deep neural network. Experimental results show that the proposed model significantly outperforms three classical models in terms of forecasting accuracy. The data fusion strategy determined by Bayesian optimization reduces the root mean square error (RMSE) of the test set by 20.04%, 28.24%, and 30.94% under sunny, cloudy, and rainy conditions, respectively.

20 January 2020 in Electronics
Verified
Journal Article
Open access
PDF file
LDLiufeng Du
Liufeng Du
LZLinghua Zhang
Linghua Zhang
XWXu Wang
Xu Wang
In this paper, we analyze the characteristics of the load forecasting task in the Energy Internet context and the deficiencies of existing methods and then propose a data driven approach for one-hour-ahead load forecasting based on the deep learning paradigm. The proposed scheme involves three aspects. First, we formulate a historical load matrix (HLM) with spatiotemporal correlation combined with the EI scenario and then create a three-dimensional historical load tensor (HLT) that contains the HLMs for multiple consecutive time points before the forecasted hour. Second, we preprocess the HLT leveraging a novel low rank decomposition algorithm and different load gradients, aiming to provide a forecasting model with richer input data. Third, we develop a deep forecasting framework (called the 3D CNN-GRU) featuring a feature learning module followed by a regression module, in which the 3D convolutional neural network (3D CNN) is used to extract the desired feature sequences with time attributes, while the gated recurrent unit (GRU) is responsible for mapping the sequences to the forecast values. By feeding the corresponding load label into the 3D CNN-GRU, our proposed scheme can carry out forecasting tasks for any zone covered by the HLM. The results of self-evaluation and a comparison with several state-of-the-art methods demonstrate the superiority of the proposed scheme.

13 January 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CTCheng Tong
Cheng Tong
LZLinghua Zhang
Linghua Zhang
YDYin Ding
Yin Ding
Dong YueDong Yue
Dong Yue
The rapid expansion of Electric Internet of Things (EIoT) systems has led to an increased demand for accurate and secure methodologies capable of handling short-term energy information forecasting, which is crucial for optimizing energy management and maintaining smart grid stability. Current federated learning (FL) frameworks, however, struggle to cope with the inherent heterogeneity of devices and the constrained communication environments typical in EIoT settings. To overcome these challenges, we introduce the Federated Heterogeneity-Aware Adaptive Framework (FedHA), a novel approach that combines an Adaptive Asynchronous Federated Aggregation (AAF) framework with a Hierarchical Knowledge Distillation (HKD) strategy. The AAF framework reduces global model aggregation time and minimizes the impact of straggling clients by enabling parallel training and dynamically adjusting learning rates based on client participation. Concurrently, HKD improves the stability and consistency of model convergence, particularly in non-IID data scenarios, by distilling and leveraging knowledge from clients that most accurately represents the global gradient direction. Furthermore, we developed FedHAL, a light-weight version of FedHA, which optimizes communication efficiency, making it ideal for deployment in resource-constrained edge environments. Extensive experiments on real-world EIoT datasets confirm that FedHA outperforms existing FL algorithms in terms of both prediction accuracy and adaptability, underscoring its potential for widespread application in dynamic and diverse EIoT contexts.

19 June 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CTCheng Tong
Cheng Tong
LZLinghua Zhang
Linghua Zhang
YDYin Ding
Yin Ding
Dong YueDong Yue
Dong Yue
As renewable energy resources increasingly integrate and dynamic user loads emerge, precise short-term forecasting across various scenarios becomes crucial for the efficient operation of modern power systems. Federated learning (FL) presents an effective solution for forecasting that safeguards privacy and security through model aggregation without sharing sensitive raw data. In the Electric Internet of Things (EIoT), the heterogeneity of clients can complicate model convergence, challenging the efficiency of the current Federated Averaging (FedAvg)-based methods. To address this, our analysis of regression challenges within the EIoT and the unique attributes of FL methods has led to the development of a novel algorithm: FedMR (Federated Mutual Knowledge Distillation Learning for Regression), aiming to deliver superior forecasting precision and efficiency at a reduced cost. FedMR utilizes the models and min-max labels from distributed clients, enabling its embedded generator to assimilate global knowledge and synthesize data in a normal distribution pattern. This feature enhances training across a spectrum of user environments. Demonstrated through testing on three open EIoT datasets, FedMR showcases high efficiency, accuracy, and adaptability across diverse client participation scenarios. Additionally, our research delves into the application of FedMR in managing device heterogeneity, a common issue in the EIoT systems. By focusing on sharing only the regression layers of clients, our proposed FedMRL(ightweight) pioneers a model-agnostic aggregation approach in short-term forecasting, effectively achieving a harmonized balance of accuracy and efficiency.