Aug 2026· International Conference on Industrial IoT, Big Data, and Smart Cities· Vol 14325, pp. 1432514 - 1432514-9· 0 citations· 12 references
Engineering
TL;DR
An end-to-end joint control framework driven by digital twin technology, combining deep feature extraction from big data with physical prior machine learning is proposed, which greatly broadens the theoretical control extreme bandwidth of the urban wide-area multi-source heterogeneous equipment cluster without overshoot collaborative operation.
Abstract
To address the issues of prediction divergence and severe lag in the execution of closed-loop control commands in complex energy distribution networks of smart cities when dealing with high-frequency nonlinear load disturbances, this paper proposes an end-to-end joint control framework driven by digital twin technology, combining deep feature extraction from big data with physical prior machine learning. This system eliminates hardware transient signal distortion by constructing a parallel digital space. Based on this, a joint topology prediction network using Long Short-Term Memory Graph Attention (LSTM-GAT) coupled with an energy Kirchhoff constrained functional is designed and trained. Furthermore, a null neural network (ZNN) control law with continuous-time derivative feedforward compensation is innovatively implanted into the execution layer, completely blocking the multi-level compound error accumulation chain of prediction drift to the physical execution layer. Rigorous comparative experimental data from offline and edge heterogeneous computing platforms show that, when facing extreme anti-mutation disturbances, the mean absolute percentage error (MAPE) of this fused scheduling network successfully converges to an extremely low threshold of 1.85%, and the system's single-time multi-dimensional perception command closed-loop issuance delay is compressed to an extreme physical boundary of 18.4ms. The quantitative mediation effect verification system confirms that the noise reduction physical smoothing mediation transmission efficiency of the architecture reaches 0.308, which greatly broadens the theoretical control extreme bandwidth of the urban wide-area multi-source heterogeneous equipment cluster without overshoot collaborative operation.
The high rate of expansion in smart cities has made their traffic system more demanding and efficient in-service delivery systems. The new technologies of Artificial Intelligence (AI) and Digital Twin (DT) have been introduced to solve these urban challenges. This is a critical review paper on AI-driven digital twin systems that find their application in smart management of traffic and optimization of a public service.
The paper comprehensively conducts the systematic review of the recent sources (published in 2020-2026) covering the theme of intertwining AI methods, including machine learning, deep learning, and reinforcement learning with the concept of the digital twin. These technologies make it possible to monitor, simulate and make data-driven decisions in cities in real-time. The major applications that have been discussed include adaptive traffic signal control, prediction of congestion, optimization of emergency response, and planning urban mobility.
Moreover, the paper assesses the system architectures, data sites like IoT sensors and vehicular networks, and computational models like cloud and edge computing that can support such solutions. The comparative analysis of the existing studies shows the benefit of increased efficiency of traffic
In spite of these advantages, there are also a number of issues such as heterogeneity of data, scalability issues, privacy and high implementation costs. Research gaps and future directions are also established based on emerging technologies in the review 5G/6G, explainable AI and big scale 5G/6G digital twin ecosystem to build sustainable smart cities of the future.
Vaibhavi Vashi· Journal of Global Economics· 0 citations
A deep learning framework based on a Mamba-driven state-space model architecture for comprehensive PQ disturbance classification is proposed and results indicate that the proposed method is well-suited for real-time smart grid monitoring and intelligent protection systems.
Pintu Das, Chandan Jana, Sannistha Banarjee et al.· Engineering Research Express· 0 citations
The high penetration of renewable energy and the large-scale integration of electric vehicles have significantly enhanced the nonlinearity and non-stationarity of the smart grid load sequence. Traditional time series models struggle to meet the prediction requirements in complex scenarios. This paper focuses on three kinds of deep learning load forecasting methods: recurrent neural network variants, CNN hybrid architectures, and Transformers, and systematically conducts a comparative analysis of them from three dimensions: prediction accuracy, long-term dependency modeling ability and computational efficiency. The results show that the three types of architectures each have distinct advantages, and there is no universal optimal solution: the recurrent variant balances accuracy and efficiency in stationary short-term prediction, the CNN hybrid architecture is more robust in strong coupling scenarios such as extreme weather, and the Transformers' trend modeling ability is outstanding but the computational cost for long sequences is large. The pros and cons of each method are highly dependent on the stationarity of the specific scenario, the forecasting horizon, and resource constraints. The model selection must be based on the task characteristics rather than the pursuit of general solutions.
Qiuhui Jiang· Applied and Computational En...· 0 citations
Growing reliance on distributed, weather-dependent renewable sources brings sizable variability, uncertainty, and stability problems to today's power grids. This work proposes an AI-driven digital twin (DT) framework that pairs a real-time physical-data grid model with a layered AI optimisation engine made up of an LSTM/Transformer forecaster, a graph neural network (GNN) state estimator, and a deep reinforcement learning (DRL) dispatch controller. The twin continually mirrors the physical grid, supporting scenario simulation, predictive fault detection, and closed-loop control recommendations before any action is applied to the real system. A case study on a modified IEEE 33-bus feeder with solar PV and wind generation shows the framework raises renewable utilisation by 19 points, cuts curtailment by 28 points, and lowers fault response time by 68.2% versus a conventional energy-management system. These results suggest AI-enhanced digital twins are a scalable route to self-optimising, resilient renewable-heavy grids.
Dr. G. Sripriya, V. S. Guhan, A. S. Nandha Kisore· International Journal of Adv...· 0 citations
The increasing pace of urbanization and climate change necessitate a holistic assessment of building energy performance during the early design phase. This study proposes an Evolutionary Field Optimization (EFO)-based multi-input multi-output artificial neural network (MIMO-ANN) model to simultaneously predict the heating load, cooling load, CO2 emissions, and lighting energy consumption of smart buildings. The model’s dataset consists of 7963 observations generated via EnergyPlus building energy simulations of standardized TOKİ residential units constructed post-earthquake in Türkiye. No operational or physically measured building energy consumption data were used in the model development process. For the validation setting, the simulation-generated dataset was split into training (60%), validation (10%), and test (30%) subsets. The EFO algorithm was employed to automatically optimize the ANN architecture by dynamically determining the optimal number of hidden layers and neurons. The optimization process demonstrated strong global search capability and fast convergence, reducing the objective function by approximately 86% within 10 iterations. Experimental results on the test subset showed exceptional predictive accuracy for simulation data, with test R2 values ranging from 0.9996 to 0.9998 across all four outputs, indicating that the optimized network topology effectively avoided overfitting. While the model’s performance under real-world operational uncertainties and varying occupant behaviors remains to be fully investigated, the proposed EFO-ANN framework provides a computationally efficient and highly accurate analytical core for early-stage design. It serves as a strategic decision-support tool intended for architects and engineers designing post-disaster housing, public authorities forming national energy efficiency policies, and developers building predictive engines for digital twin-enabled smart building systems.
Ebru Doğan Koç, Gurkan Kavuran, Gonca Özer Yaman et al.· Sustainability· 0 citations
Accurate short-term load forecasting (STLF) is essential for modern grid operations, enabling efficient scheduling, demand response, and renewable energy integration. This paper presents a systematic comparison of five forecasting architectures applied to a large dataset of 98 residential homes, with 1-minute and 15-minute smart meter readings spanning 2015-2023. The models include an XGBoost pipeline with extensive feature engineering, a tuned CatBoost implementation, a feedforward neural network with multi-output regression, a multi-scale convolutional Kolmogorov-Arnold network (MCKAN), and a long short-term memory (LSTM) network with a 7-day lookback. All models are trained globally, pooling data across homes while incorporating home-specific categorical variables, including an assignment to a simulated microgrid topology with nine kiosks and three phases. Hyperparameter optimization is performed using Optuna and Keras Tuner. CatBoost achieves the lowest test MAE across all horizons, from 0.4089 (15-minute) to 0.7419 (30-day), outperforming XGBoost by 4-10% and deep learning models by larger margins. The findings support Sustainable Development Goals 7, 9, and 13 and provide actionable insights for energy management, particularly in the South African context of load shedding and grid decarbonization.
Mukovhe Ratshitanga, Pfano Nemakonde, Komla A. Folly et al.· 2026 6th International Confe...· 0 citations