Abstract With the rapid development of quantum machine learning, Quantum Long Short-Term Memory (QLSTM) have demonstrated quantum advantages in time series forecasting problems. Currently, it has found applications in fields such as financial market analysis, natural language processing, and weather forecasting, but its accuracy in regression problem prediction still shows deficiencies. To improve the prediction accuracy of the model, enhanced quantum long short-term memory by using bidirectional ring variational quantum circuit (EQLSTM) is proposed. We reconsidered and optimized the types, quantities, and arrangements of quantum gates, designing a bidirectional ring variational quantum circuit composed of CRX gates (Bi-VQC) to enhance its expressibility. Bi-VQC can more accurately describe and encode complex quantum state features, enabling the EQLSTM to better learn and represent the characteristics of the input data. In addition, Bi-VQC reduces the number of optimizable parameters and lowers the circuit load of the EQLSTM model. To validate the effectiveness of the proposed model, experiments are conducted to test and evaluate the EQLSTM using the Aggregated traffic in the United Kingdom academic network backbone. The experimental results confirm that the proposed EQLSTM model improves from 90.56\% to 97.57\% compared to the QLSTM model.
Abstract With the rapid development of quantum machine learning, Quantum Long Short-Term Memory (QLSTM) have demonstrated quantum advantages in time series forecasting problems. Currently, it has found applications in fields such as financial market analysis, natural language processing, and weather forecasting, but its accuracy in regression problem prediction still shows deficiencies. To improve the prediction accuracy of the model, enhanced quantum long short-term memory by using bidirectional ring variational quantum circuit (EQLSTM) is proposed. We reconsidered and optimized the types, quantities, and arrangements of quantum gates, designing a bidirectional ring variational quantum circuit composed of CRX gates (Bi-VQC) to enhance its expressibility. Bi-VQC can more accurately describe and encode complex quantum state features, enabling the EQLSTM to better learn and represent the characteristics of the input data. In addition, Bi-VQC reduces the number of optimizable parameters and lowers the circuit load of the EQLSTM model. To validate the effectiveness of the proposed model, experiments are conducted to test and evaluate the EQLSTM using the Aggregated traffic in the United Kingdom academic network backbone. The experimental results confirm that the proposed EQLSTM model improves from 90.56% to 97.57% compared to the QLSTM model.
Quantum Long Short-Term Memory (QLSTM) networks represent a promising direction in quantum machine learning but face challenges including parameter scaling, barren plateaus, and limitations of Noisy Intermediate-Scale Quantum (NISQ) hardware. This paper proposes the Tunable Ring Quantum LSTM (TRQLSTM) framework, integrating rotational encoding channels with a bidirectional ring Variational Quantum Circuit (VQC) architecture. Empirical evaluation on financial, weather, and electricity benchmarks demonstrates that TRQL-STM achieves a 98.7% parameter reduction over a classical LSTM while delivering a 95.1% MAE improvement on the Apple stock financial benchmark (AAPL). The bidirectional ring topology alone accounts for an 87.3% improvement over a standard QLSTM at identical parameter count. Expressibility is preserved at approximately 90% of a fully parameterised QLSTM, confirmed via KL divergence from the Haar random distribution. By combining optimised quantum gates, a bidirectional VQC layout, and multimodal encoding within a single circuit, TRQLSTM provides a practical pathway toward scalable quantum-classical sequential learning systems.
Time series forecasting is vital in many fields, including energy demand prediction and financial markets. Long Short-Term Memory (LSTM) networks have demonstrated strong performance in capturing temporal dependencies in sequential data. However, traditional LSTM face challenges such as vanishing gradients and limited capabilities in modeling long-term dependencies, especially with complex, high-dimensional data. The model integrates Variable Quantum Circuit (VQC) into a modified LSTM (mLSTM) structure, taking advantage of quantum properties such as superposition and entanglement to improve memory retention and computational efficiency. We would like to introduce modified Quantum Long Short-Term Memory (mQLSTM), which is specifically designed for photovoltaic (PV) energy forecasting. Key improvements include a quantum memory mechanism that mitigates loss of information over extended sequences, a redesigned forget gate to enhance long-term learning and an Exponentially Weighted Feature (EWF) layer to accelerate convergence and enhance generalization. This paper highlights the potential of quantum-enhanced deep learning architectures to advance time series forecasting and opens new directions for practical applications in renewable energy and beyond.
Forecasting weather is critical in different application sectors and affects decision-making and resource distribution. Long Short-Term Memory (LSTM) models are popular, but they can be improved even further with the use of quantum computing techniques. This paper discusses a Quantum Long Short-Term Memory (QLSTM) simulated in PennyLane-based simulators. According to the experimental results, the suggested QLSTM model produced a mean absolute error (MAE) of 0.009066, a test mean square error (MSE) of 0.000162, and a coefficient of determination (R2) of 0.999846, surpassing both quantum models and classical baselines. These results highlight the potential of quantum-assisted architectures to improve accuracy in weather prediction. The research advances weather forecasting and contributes to quantum computing applications, guiding researchers in developing precise weather prediction models and enhancing decision-making in weather-sensitive domains. The proposed 4-qubit quantum model was tested with noise models, and it demonstrated high learning efficiency and strong robustness against realistic NISQ-level noise, maintaining stable optimization and low error even under moderate perturbations. • Quantum LSTM Development: The classical LSTM was extended into the quantum domain using Variational Quantum Circuits (VQCs) for feature extraction and data compression, applied to weather prediction tasks. • Experimental Evaluation: Three QLSTM variants (4, 6, and 8 qubit) were tested on two weather datasets and compared with classical LSTM and state-of-the-art QLSTM models. • Performance and Robustness: The QLSTM models outperformed baseline models, with the 4-qubit model showing strong learning efficiency and robustness under realistic NISQ-level noise.
Short-term solar irradiance prediction is critical for efficient power scheduling, the design of solar-integrated energy management systems, and maintaining grid stability. However, the inherent variability of solar energy introduces fluctuations in power output, and posing challenges for reliable grid operation. Leveraging recent advancements in quantum computing, the current work proposes a hybrid quantum-driven neural network for solar irradiance prediction, combining successive variational mode decomposition (SVMD) with an improved quantum long short-term memory (IQLSTM) network. To enhance circuit expressibility, a robust variational quantum circuit (RVQC) incorporating controlled-X (CRX) gates is embedded within the quantum long short-term memory (QLSTM) architecture. In the RVQC, a circular topology with two-way connections is employed to optimize qubit interconnections and strengthen entanglement. The proposed model is evaluated using two solar irradiance datasets of Hyderabad (2019) and Bengaluru (2019, 2018), obtained from the National Renewable Energy Laboratory (NREL). To assess the effectiveness of the proposed circuit, evaluations are carried out under varying weather conditions and across multiple forecasting horizons, and results are compared against classical LSTM and other quantum-based networks like quantum gate recurrent units (QGRUs), quantum support vector machine (QSVM) and QLSTM. Furthermore, the model is evaluated under noisy quantum environments to approximate realistic Noisy Intermediate-Scale Quantum (NISQ) hardware conditions, enabling the assessment of its robustness under practical quantum computing constraints. Experimental results demonstrate that the proposed model achieves superior predictive accuracy and robustness compared with existing classical and quantum-based approaches.
Traditional CNC machine tool thermal error compensation methods face significant limitations in handling large-scale time-series data and addressing model complexity, making it difficult to meet the high-precision demands of modern manufacturing. To address these challenges, this study introduces quantum computing technology and proposes a thermal error compensation method based on the Quantum Long Short-Term Memory (QLSTM) model. This model combines the strengths of LSTM in time-series data modeling with the computational efficiency of quantum computing. By optimizing the design structure of the Variational Quantum Circuit (VQC), the model significantly improves the accuracy of thermal error prediction. This research evaluates the model's performance under various spindle speed conditions, including four sets of long-duration fixed-speed data and two sets of long-duration variable-speed configurations simulating actual machining scenarios. Experimental results demonstrate that the model effectively reduces the maximum peak-to-peak error of the workpiece to within 19 μm. Furthermore, by optimizing the VQC, the calculation time of the model is reduced by nearly 66%, and the error improvement percentage (EIP%) reaches 66.67%, enhancing machining accuracy.
Merger of Quantum computing and Machine learning explores a new shift in artificial intelligence. Quantum neural networks and parameterized quantum circuits are tools that enable the merger of these two branches. Here, we use Quantum circuit enabled long short term memory (QLSTM) neural network to forecast time series data. We show the efficacy of quantum computing by conducting experiments on two different time series data sets. In our first experiment, we are predicting the amount of rainfall fall and the second experiment has electric load (power) prediction. Our dataset for rainfall prediction includes hourly information on the weather conditions i.e., wind speed, wind direction, minimum and maximum temperatures, and pressure with the amount of rain falls. For electric load (power generation) dataset, few of the features include amount of biomass, amount of fossil brown coal/ignite, amount of fossil coal derived gas, nuclear power, solar power, and the corresponding wind velocity forecasts. We compare the training as well as the test loss of classical Bidirectional LSTM (BILSTM) and the Quantum BILSTM and observe that LSTM based on quantum approach reduces both the training and test loss considerably when compared to its classical part with very few epochs of training.