Electric Vehicles (EVs) are becoming increasingly prevalent nowadays, with studies highlighting their potential as mobile energy storage systems to provide grid support. Realising this potential requires effective charging coordination, which are often formulated as mixed-integer programming (MIP) problems. However, MIP problems are NP-hard and often intractable when applied to time-sensitive tasks. To address this limitation, we propose a deep learning assisted approach for optimising a day-ahead EV joint routing and scheduling problem with varying number of EVs. This problem simultaneously optimises EV routing, charging, discharging and generator scheduling within a distribution network with renewable energy sources. A convolutional neural network is trained to predict the binary variables, thereby reducing the solution search space and enabling solvers to determine the remaining variables more efficiently. Additionally, a padding mechanism is included to handle the changes in input and output sizes caused by varying number of EVs, thus eliminating the need for re-training. In a case study on the IEEE 33-bus system and Nguyen-Dupius transportation network, our approach reduced runtime by 97.8% when compared to an unassisted MIP solver, while retaining 99.5% feasibility and deviating less than 0.01% from the optimal solution.

Modern electricity theft poses severe risks to power grid stability, particularly as cyber-attacks targeting Advanced Metering Infrastructure (AMI) become increasingly covert. This paper proposes a deep learning framework for Electricity Theft Detection (ETD) based on a Transformer encoder and a Dynamic-Weight Multi-Head Classifier (DW-MHC). The model extracts temporal load features via self-attention and employs specialized heads to capture diverse theft patterns, such as abrupt anomalies and gradual deviations. A soft-attention fusion mechanism adaptively integrates the head outputs for robust prediction. The framework also accommodates variability across residential and industrial users, whose load profiles may differ significantly in scale and regularity. Experimental results demonstrate the model's superior performance in detecting varied theft behaviors among consumers, achieving improved performance over traditional single-head and static classifiers.

Machine unlearning has become a focal point in recent research, yet the specific area of feature unlearning has not been thoroughly explored. Feature unlearning involves the elimination of specific features' effects from an already trained model, presenting distinct challenges that are still not comprehensively addressed. This paper presents a novel and straightforward approach to feature unlearning that employs a tactical shuffling of the features designated for removal. By redistributing the values of the features targeted for unlearning throughout the original training dataset and subsequently fine-tuning the model with this shuffled data, our proposed method provides a theoretical guarantee for effective feature unlearning. Under mild assumptions, our method can effectively disrupt the established correlations between unlearned features and the target outcomes, while preserving the relationships between the remaining features and the predicted outcomes. Our empirical studies across various datasets,validate that our approach not only successfully removes the effects of specified features but also maintains the informational integrity of the remaining features while achieving a faster convergence rate.

Heterogeneity arising from label distribution skew and data scarcity can cause inaccuracy and unfairness in intelligent communication applications that heavily rely on distributed computing. To deal with it, this article proposes a novel personalized federated learning algorithm, named federated contrastive shareable representations (FedCoSRs), to facilitate knowledge sharing among clients while maintaining data privacy. Specifically, the parameters of local models' shallow layers and typical local representations are both considered as shareable information for the server and are aggregated globally. To address performance degradation caused by label distribution skew among clients, contrastive learning is adopted between local and global representations to enrich local knowledge. Additionally, to ensure fairness for clients with scarce data, FedCoSR introduces adaptive local aggregation to coordinate the global model involvement in each client. Our simulations demonstrate FedCoSR's effectiveness in mitigating label heterogeneity by achieving accuracy and fairness improvements over existing methods on datasets with varying degrees of label heterogeneity.

Mobile edge computing (MEC) is a promising paradigm for real-time applications with intensive computational needs (e.g., autonomous driving), as it can reduce the processing delay. In this work, we focus on the timeliness of computational-intensive updates, measured by Age-of-Information (AoI), and study how to jointly optimize the task updating and offloading policies for AoI with fractional form. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. The uncertain edge load dynamics, the nature of the fractional objective, and hybrid continuous-discrete action space (due to the joint optimization) make this problem challenging and existing approaches not directly applicable. To this end, we propose a fractional reinforcement learning (RL) framework and prove its convergence. We further design a model-free fractional deep RL (DRL) algorithm, where each device makes scheduling decisions with the hybrid action space without knowing the system dynamics and decisions of other devices. Experimental results show that our proposed algorithms reduce the average AoI by up to 57.6% compared with several non-fractional benchmarks.

Electric vehicles (EVs) have the potential to serve as energy storage solutions through bidirectional charging technology, which allows them to both draw power from and feed power back into the grid, homes, or other vehicles. This capability enables EVs to reduce emissions, optimize costs, and support the grid by storing energy during periods of high production and supplying it when demand is high. In this vision paper, we focus on unlocking the potential of EVs as energy storage solutions while ensuring they remain readily available for transportation, their primary purpose. A significant research gap exists in that most current studies prioritize energy management, often using simplistic approaches that inadequately address the travel needs of EV owners. We believe the database community can be instrumental in maximizing the dual role of EVs as transportation and energy storage. We present a non-exhaustive list of research directions for various EV stakeholders, including individual EV owners, groups of independent yet cooperative EVs, commercial EV fleets, and autonomous EVs, and hope to inspire the database community for further exploration.

This article studies the synergy of solar-battery energy storage system (BESS) and develops a viable strategy for the BESS to unlock its economic potential by serving as a backup to reduce solar curtailments while also participating in the electricity market. We model the real-time bidding of the solar-battery system as two Markov decision processes for the solar farm and the BESS, respectively. We develop a novel deep reinforcement learning (DRL) algorithm to solve the problem by leveraging attention mechanism (AC) and multigrained feature convolution to process DRL input for better bidding decisions. Simulation results demonstrate that our AC-DRL outperforms two optimization-based and one DRL-based benchmarks by generating 23%, 20%, and 11% higher revenue, as well as improving curtailment responses. The excess solar generation can effectively charge the BESS to bid in the market, significantly reducing solar curtailments by 76% and creating synergy for the solar-battery system to be more viable.

This work presents Reputation-Based Streamlet (RBStreamlet), an improved version of the Streamlet consensus algorithm, designed to address limitations such as high bandwidth load and high communication complexity during the Propose and Vote phases. RBStreamlet introduces a reputation mechanism for leader election and fork selection, along with erasure coding and Merkle trees to reduce data transmission volume in the Propose phase. Furthermore, RBStreamlet leverages threshold signature technology to decrease the message complexity in the Vote phase. We implement the proposed RBStreamlet algorithm in a prototype blockchain system and build a network emulator to evaluate its performance under conditions resembling a practical wide-area network. Through extensive experiments, RBStreamlet demonstrates superior performance, scalability, and resilience to Byzantine attacks compared to the original Streamlet, especially in bandwidth-limited scenarios. These findings suggest its potential for practical applications in blockchain systems.

Effective energy management of electric vehicle (EV) charging stations is critical to supporting the transport sector's sustainable energy transition. This paper addresses the EV charging coordination by considering vehicle- to- vehicle (V2V) energy exchange as the flexibility to harness in EV charging stations. Moreover, this paper takes into account EV user experiences, such as charging satisfaction and fairness. We propose a Multi-Agent Reinforcement Learning (MARL) approach to coordinate EV charging with V2V energy exchange while considering uncertainties in the EV arrival time, energy price, and solar energy generation. The exploration capability of MARL is enhanced by introducing parameter noise into MARL's neural network models. Experimental results demonstrate the superior performance and scalability of our proposed method compared to traditional optimization baselines. The decentralized execution of the algorithm enables it to effectively deal with partial system faults in the charging station.

Residential occupancy detection has become an enabling technology in today's urbanized world for various smart home applications, such as building automation, energy management, and improved security and comfort. Digitalization of the energy system provides smart meter data that can be used for occupancy detection in a non-intrusive manner without causing concerns regarding privacy and data security. In particular, deep learning techniques make it possible to infer occupancy from low-resolution smart meter data, such that the need for accurate occupancy detection with privacy preservation can be achieved. Our work is thus motivated to develop a privacy-aware and effective model for residential occupancy detection in contemporary living environments. Our model aims to leverage the advantages of both recurrent neural networks (RNNs), which are adept at capturing local temporal dependencies, and transformers, which are effective at handling global temporal dependencies. Our designed hybrid transformer-RNN model detects residential occupancy using hourly smart meter data, achieving an accuracy of nearly 92% across households with diverse profiles. We validate the effectiveness of our method using a publicly accessible dataset and demonstrate its performance by comparing it with state-of-the-art models, including attention-based occupancy detection methods.

With the advances in the Internet-of-Things technology, electric vehicles (EVs) have become easier to schedule in daily life, which is reshaping the electric load curve. It is important to design efficient charging algorithms to mitigate the negative impact of EV charging on the power grid. This article investigates an EV charging scheduling problem to reduce the charging cost while shaving the peak charging load, under unknown future information about EVs, such as arrival time, departure time, and charging demand. First, we formulate an EV charging problem to minimize the electricity bill of the EV fleet and study the EV charging problem in an online setting without knowing future information. We develop an actor–critic learning-based smart charging algorithm (SCA) to schedule the EV charging against the uncertainties in EV charging behaviors. The SCA learns an optimal EV charging strategy with continuous charging actions instead of discrete approximation of charging. We further develop a more computationally efficient customized actor–critic learning charging (CALC) algorithm by reducing the state dimension and thus improving the computational efficiency. Finally, simulation results show that our proposed SCA can reduce EVs’ expected cost by 24.03%, 21.49%, 13.80%, compared with the eagerly charging algorithm, online charging algorithm, reinforcement learning (RL)-based adaptive energy management algorithm, respectively. CALC is more computationally efficient, and its performance is close to that of SCA with only a gap of 5.56% in the cost.

With the booming of smart grid, the ubiquitously deployed smart meters constitutes an energy Internet of Things (IoT). This article develops a novel blockchain-based transactive energy management (TEM) system for IoT-aided smart homes. We consider a holistic set of options for smart homes to participate in transactive energy. Smart homes can interact with the grid to perform vertical transactions, e.g., feeding in extra solar energy to the grid and providing demand response service to alleviate the grid load. Smart homes can also interact with peer users to perform horizontal transactions, e.g., peer-to-peer energy trading. However, conventional TEM method suffers from the drawbacks of low efficiency, privacy leakage, and single-point failure. To address these challenges, we develop a privacy-preserving distributed algorithm that enables users to optimally manage their energy usages in parallel via the smart contract on the blockchain. Further, we design an efficient blockchain system tailored for IoT devices and develop the smart contract to support the holistic TEM system. Finally, we evaluate the feasibility and performance of the blockchain-based TEM system through extensive simulations and experiments. The results show that the blockchain-based TEM system is feasible on practical IoT devices and reduces the overall cost by 25%.

Transactive energy plays a key role in the operation and energy management of future power systems. However, the conventional operational mechanism, which follows a centralized design, is often less secure, vulnerable to malicious behaviors, and suffers from privacy leakage. In this article, we introduce blockchain technology in transactive energy to address these challenges. Specifically, we develop a novel blockchain-based transactive energy framework for prosumers and design a decentralized energy trading algorithm that matches the operation of the underlying blockchain system. We prove that the trading algorithm improves the individual benefit and guarantees the socially optimal performance, and thus, incentivizes prosumers to join the transactive energy platform. Moreover, we evaluate the feasibility of the transactive energy platform throughout the implementation of a small-scale network of Internet of Things devices and extensive simulations using real-world data. Our results show that this blockchain-based transactive energy platform is feasible in practice, and the decentralized trading algorithm reduces the user's individual cost by up to 77% and lowers the overall cost by 24%.

Renewable energy generations and energy storage are playing increasingly important roles in serving consumers in power systems. This paper studies the market competition between renewable energy suppliers with or without energy storage in a local energy market. The storage investment brings the benefits of stabilizing renewable energy suppliers' outputs, but it also leads to substantial investment costs as well as some surprising changes in the market outcome. To study the equilibrium decisions of storage investment in the renewable energy suppliers' competition, we model the interactions between suppliers and consumers using a three-stage game-theoretic model. In Stage I, at the beginning of the investment horizon (containing many days), suppliers decide whether to invest in storage. Once such decisions have been made (once), in the day-ahead market of each day, suppliers decide on their bidding prices and quantities in Stage II, based on which consumers decide the electricity quantity purchased from each supplier in Stage III. In the real-time market, a supplier is penalized if his actual generation falls short of his commitment. We characterize a price-quantity competition equilibrium of Stage II in the local energy market, and we further characterize a storage-investment equilibrium in Stage I incorporating electricity-selling revenue and storage cost. Counter-intuitively, we show that the uncertainty of renewable energy without storage investment can lead to higher supplier profits compared with the stable generations with storage investment due to the reduced market competition under random energy generation. Simulations further illustrate results due to the market competition. For example, a higher penalty for not meeting the commitment, a higher storage cost, or a lower consumer demand can sometimes increase a supplier's profit. We also show that although storage investment can increase a supplier 's profit, the first-mover supplier who invests in storage may benefit less than the free-rider competitor who chooses not to invest in storage.

Renewable energy resources are playing an increasingly important role in serving consumers at the distribution level of power systems. This paper studies a duopoly two-settlement local renewable energy market, in which one energy supplier has controllable generations (with the help of energy storage) while the other supplier has random generations. In the day-ahead energy market, suppliers determine the bidding prices and quantities, and then consumers decide the energy quantity to purchase from each supplier. In the real-time energy market, a supplier gets penalized if he cannot deliver the amount of energy as committed in the day-ahead market. We formulate the interactions between suppliers and consumers in the day-ahead market as a two-stage problem. The two-dimensional bidding strategies (price and quantity) in the day-ahead market together with the penalty in the real-time market increase the complexity of the equilibrium analysis. To address such a challenge, we first derive weakly dominant bidding quantity strategies for both suppliers, and then characterize the corresponding pure and mixed price equilibrium. We demonstrate that the supplier with controllable generations can earn a much higher payoff than the supplier with random generations. In some cases, however, we show the perhaps counterintuitive result that a higher penalty or a higher variance of random generations may increase both suppliers' payoffs.

This paper develops a novel business model to enable virtual storage sharing among a group of users. Specifically, an aggregator owns a central physical storage unit and virtualizes the physical storage into separable virtual storage capacities that can be sold to users. Each user purchases the virtual storage capacity, and schedules the charge and discharge of the virtual storage to reduce his peak power consumption. We formulate the interaction between the aggregator and users in each operation horizon as a two-stage problem. At the beginning of the operation horizon, the aggregator first determines the unit price of virtual storage capacity to maximize her profit in Stage 1, and users decide the capacities to purchase and the storage scheduling during the operation horizon in Stage 2. Since the closed-form solution is not available and the decisions are coupled across the two stages, we characterize the solutions of the two-stage problem based on parametric linear programming. Simulation results show that compared to the case where each user acquires his own physical storage, storage virtualization reduces the overall physical capacity needed for all users by 34.9%, and the overall physical power rating by 45.1%.

This paper studies the energy trading among multiple connected microgrids, and analyzes the impacts of such trading on the microgrids' costs. In our model, microgrids with excessive power generations can trade with other microgrids in deficit of power supplies for mutual benefits. We design a bargaining-based energy trading market, where all the interconnected microgrids cooperatively decide the amount of energy trade and the associated payments. We propose a decentralized algorithm to solve the bargaining problem, with minimum information exchange overhead. Numerical studies based on realistic data demonstrate the effectiveness of the bargaining-based energy trading market design, and show that the reduction of total cost of the interconnected-microgrids system can be up to 22% comparing with the case of no trading.

ABSTRACT The capacity of wireless networks can be improved by the use of multi‐channel multi‐interface (MCMI), multi‐packet reception (MPR), and directional antenna (DA). MCMI can provide the concurrent transmission in different channels for each node with multiple interfaces; MPR offers an increased number of concurrent transmissions on the same channel; DA can be more effective than omni‐DA by reducing interference and increasing spatial reuse. This paper explores the capacity of wireless networks that integrate MCMI, MPR, and DA technologies. Unlike some previous research, which only employed one or two of the aforementioned technologies to improve the capacity of networks, this research captures the capacity bound of the networks with all the aforementioned technologies in arbitrary and random wireless networks. The research shows that such three‐technology networks can achieve at most capacity gain in arbitrary networks and capacity gain in random networks compared with MCMI wireless networks without DA and MPR. The paper also explored and analyzed the impact on the network capacity gain with different , θ, and k‐MPR ability. Copyright © 2012 John Wiley & Sons, Ltd.

Active queue management (AQM) mechanism is a powerful method, which aims to assist the TCP congestion control and to improve the trade-off between queuing delay and link utilization. Traditional price-based AQM algorithms suffer from sluggish response, poor robustness, and lack adequate adaptability against dynamic traffics. To improve AQM performance, this paper introduces artificial intelligence methods to design a sophisticated AQM algorithm. In particular, a fuzzy neuron price is developed for congestion detection. Hebbian learning rule and fuzzy logic theory are employed to configure the control parameters automatically for better adaptability and robustness. Simulation results demonstrate that our proposed scheme is stable, responsive and performs robustly against time-varying network dynamics. It is superior to other peer AQM algorithms in various performance indicators, such as stability and jitter of queue length as well as packet loss.

The TCP/AQM dynamics is modeled as a time-delay congestion control system, in which the round trip time (RTT) has great influence on the system stability and network performance. Most of the existing active queue management (AQM) algorithms suffer from performance degradation, and fail to provide quality of service (QoS) when the RTT delay becomes remarkable. To address the problem, we present an efficient queue management method, which uses an enhanced Smith predictor to compensate for the RTT delay. An adaptation rule is designed for the gain of the estimated model via Lyapunov stability theory to improve the robustness of Smith predictor. Converting the Smith predictor to its equivalent structure, we derive the AQM controller from the internal model control technique and obtain an executable proportional-integral (PI) controller, which can be easily implemented due to its simple form. By simulations, it is demonstrated that our proposed method could improve QoS in large delay networks and outperforms other competitive AQM schemes in terms of stability and robustness.

Congestion control can be regarded a distributed system, which consists of source algorithm like TCP, and link algorithm, such as active queue management (AQM). Shadow price has been derived from optimization theory to be implemented in routers as the AQM algorithm. In this paper, a control theoretic approach to analysis and design of the price is presented to enhance the AQM performance. We analyze the dynamics of random exponential marking (REM) and propose an efficient price-based AQM algorithm. The proposed method uses an effective price with proportional-integral-derivative (PID) property to detect and control congestion proactively. Online learning rules are introduced to adjust the parameters of the effective price for improving adaptability and robustness in nonlinear and time-varying networks. The stability of the system is also analyzed via the Lyapunov stability theory. By extensive simulations, the results verify that our proposed method outperforms many competitive AQM schemes in terms of stability, response and robustness under various network scenarios. The proposed method is able to maintain stable queue size, small jitter, low packet loss and improves the trade-off between queuing delay and link utilization.

Adaptive virtual queue (AVQ) algorithm is an effective method aiming to achieve low loss, low delay and high-link utilisation at the link. However, it is difficult to guarantee fast response, strong robustness and good trade-off over a wide range of network dynamics. The authors propose a stabilising active queue management (AQM) algorithm – effective-AVQ, as an extension of AVQ, to improve the responsiveness and robustness of the transmission control protocol (TCP)/AQM system. Specifically, a proportional integral derivative (PID) neuron is introduced to tune the virtual link capacity dynamically. Also we derive the parameter self-tuning mechanism for the PID neuron from the Hebbian learning rule and gradient descent approach. The stability condition of the closed-loop system is presented based on the time-delay control theory. The performance of effective-AVQ is validated in the NS2 platform. Simulation results demonstrate that effective-AVQ outperforms AVQ in terms of steady-state and transient performance. It achieves fast response, expected link utilisation, low queue size and small delay jitter, being robust against dynamic network changes.

As the wireless network scales up in size and complexity, the need to study the scalability and behaviors of these networks and their protocols becomes essential. Opportunistic routing utilizes broadcast nature of wireless network, and significantly increases the unicast throughput. However, all of the current opportunistic routing protocols have to rely on the whole topology information. This indeed restricts to applying the opportunistic routing to large-scale wireless networks, due to the huge cost of the control overheads needed for building a network graph at each node. In this paper, we propose the localized opportunistic routing (LOR) protocol, which utilizes the distributed minimum transmission selection (MTS) algorithm to partition the topology into several nested close-node-sets (CNS) with {local information}. It can locally realize the optimal opportunistic routing for large-scale wireless networks with low control overhead cost. Extensive simulation results show that in large-scale wireless environments, LOR can dramatically improve the performances over ExOR, MORE, in terms of control overhead, end-to-end delay and throughputs.

Most of the existing congestion control schemes cannot guarantee the quality of service in wide-area networks with large round trip time (RTT). Aiming at the above problem, a two-degree-of-freedom congestion control strategy (named TCC) is proposed for improving the stability and robustness of the TCP/AQM system. TCC employs a modified Smith predictor with two additional controllers to compensate for the RTT delay. The feedback controller is designed by the internal model control theory for fast set-point tracking. The disturbance rejection controller is derived from frequency-domain analysis to reject external disturbance. Simulation results in NS2 demonstrate that TCC can effectively overcome the negative influence cased by time delay and disturbance. Compared with other congestion control schemes, our proposed method is superior in stabilizing the queue length with small jitters and rejecting disturbances.

Active queue management (AQM) is an effective method acting on routers to improve the performance of end-to-end congestion control. However, most of the current AQM schemes are sensitive to network configurations as well as parameterization problems. In this paper, we propose a self-tuning congestion control scheme, named SPC. An enhanced price with proportional-integral-derivative control property is introduced into SPC to improve its capability of detecting and controlling network congestion. Then, we present a simple and effective discrete model to depict the TCP/SPC behaviors, and design an optimization rule for the key parameter of SPC to minimize the error and jitter of queue size. Simulation results in NS2 demonstrate that SPC is stable, responsive and robust in various network scenarios. It can quickly regulate the queue length to the target with small jitter, achieving satisfactory performance, such as low packet loss ratio and high link utilization.

NA

Numerous active queue management (AQM) schemes have been proposed to stabilize the queue length in routers, but most of them lack adequate adaptability to TCP dynamics, due to the nonlinear and time-varying nature of communication networks. To deal with the above problems, we propose an intelligent price-based congestion control algorithm named IPC. IPC measures congestion through using an intelligent price derived from neural network. To meet the purpose of AQM, we design learning algorithms to optimize the weights of neural network and the key parameter of IPC automatically. IPC acts as an adaptive controller which is able to detect both incipient and current congestion proactively and adaptively under dynamic network conditions. The simulation results demonstrate that IPC significantly outperforms the well-known AQM algorithms in terms of stability, responsiveness and robustness over a wide range of network scenarios.

Active queue management (AQM) mechanism plays an important role in network congestion control. In this paper, we propose an effective AQM algorithm, named adaptive real queue control (ARQC). In particular, an explicit congestion indicator, virtual regulating time, is designed to detect network congestion. Then by analyzing the queuing system on routers, we present the guideline to calculate the dropping/marking probability. Also we provide the tuning rules for the control parameters based on the discrete model of TCP dynamics. Simulation results demonstrate that ARQC outperforms the other AQM schemes in terms of stability, responsiveness and robustness in dynamic networks. Moreover, it achieves smaller queue length jitter, less packet loss and better trade-off between delay and link utilization.