Fair and Efficient Distributed EV Charging Coordination Using Threshold Cryptography and Machine Learning
Authors: Md. Mainul Islam, Muhammad Ismail, Hasan Kurban, Abdulrahman Takiddin, Erchin Serpedin
Organizations: Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA · Cybersecurity Education, Research, and Outreach Center (CEROC) and Department of Computer Science, Tennessee Tech University, Cookeville, TN 38505, USA · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar · Department of Electrical and Computer Engineering, FAMU-FSU College of Engineering, Florida State University, Tallahassee, FL 32310 USA
Distributed coordination of electric vehicle (EV) charging with the alternating direction method of multipliers (ADMM) keeps EV constraints private but assumes that every participant follows the algorithm. This assumption fails in practice, where a biased operator or a man-in-the-middle (MITM) attacker can send inconsistent signals to different EVs, and compromised EVs can deviate from their prescribed updates. We first prove that attacks by such arbitrarily malicious, i.e., Byzantine, participants do not prevent convergence and therefore remain undetected, and derive the most damaging attack in closed form. We then propose a framework that combines a threshold-signed broadcast with upload recomputation, which detects every deviation without false alarms at linear instead of quadratic communication cost. To keep the optimization running, each affected EV recovers locally with a certified, fleet-aware machine learning price forecast, and we prove that the optimization remains convergent with a recovery cost bounded by the shape of the forecast error. Simulation results with real-world load, price, and charging data show that a biased operator raises the annual cost of disadvantaged EVs by 132.7% and lowers that of advantaged EVs by 49.3% without changing the aggregate load, whereas the defense limits all cost changes to 2.6%. An external MITM attacker raises the cost of its victims by 57.6%, the peak load by 5.8%, and the grid cost by 15.8%, whereas the defense keeps them within 1.1%, 0.2%, and 0.3% of benign operation. With up to 70% of the EVs attacked, the recovery converges in at least 97.8% of the runs.
Figures & tables
Work
Byzantine parties
Stealth a
Detection
Trusted channel b
Liveness c
Guarantees
Messages d
Attacks by participating EVs [ 15 , 16 ]
EVs
Yes
None
N/A
No
Attack analysis
N/A
Detection of deviating aggregators [ 17 ]
Aggregators
Partly
Statistical
N/A
No
Empirical
N/A
Byzantine-robust gradient aggregation [ 18 , 19 ]
Workers
No
Filtering
No
Partly
Statistical error bound
O(N)
Resilient distributed optimization [ 20 , 21 ]
Neighbors
No
Filtering
Yes (P2P)
Partly
Approximate convergence
O(L)
Trust-based node isolation [ 22 ]
EVs, links
Partly
Threshold-based
Yes (P2P)
Partly
Convergence after isolation
O(L)
Blockchain-based coordination [ 23 ]
Coordinator, participants
No
Consensus
Yes (ledger)
No
Consensus
O(N2)
TABLE I: Comparison With Prior Work on Attacks in Distributed Optimization
Fig. 1: Charging station and non-EV load served by a common bus.
Fig. 2: Framework architecture and adversary positions.
Fig. 3: Message flow of one certified iteration.
Model
Training
Testing
R2
MAE
R2
MAE
MAPE (%)
Span ($/kWh)
LightGBM
0.9964
0.0047
0.9695
0.0139
6.20
0.0550
Random forest
0.9926
0.0055
0.9666
0.0140
6.32
0.0552
XGBoost
0.9959
0.0054
0.9678
0.0145
6.59
0.0570
SVR
0.9638
0.0135
0.9699
0.0150
6.60
0.0581
Gradient boosting
0.9907
0.0083
0.9683
0.0151
6.81
0.0589
TABLE II: Training and Test Performance of the Price Forecasters
Fig. 4: Uncoordinated versus coordinated charging on a high-demand day: (a) total bus load and (b) EV load. The red band covers 5%–95% of 200 random uncoordinated draws, and gray marks the peak-price hours.
Fig. 5: Load and price profiles: (a) load under A1, (b) load under A2, and (c) final prices under A1 and A2. The shaded hours carry the peak price.
Fig. 6: Annual charging cost per EV under (a) A1 and (b) A2.
Fig. 7: Charging schedules, with daily cost changes in parentheses: (a) benign, (b) attacked, and (c) recovered under A1; (d)–(f) the same under A2.
Metric
Benign
A1: Biased operator
A2: MITM attacker
Undefended
Defended
Undefended
Defended
Change of J (%)
0.0
−0.2
−0.1
15.8
−0.3
LFS (%)
3.9
5.6
4.0
−1.6
4.1
Peak load change (%)
0.0
−1.7
−0.1
5.8
−0.1
Total EV payments ($)
928.6
926.5
927.4
1113.3
925.7
Station profit ($)
43.9
43.9
43.9
49.8
43.9
TABLE III: Case-Study Results Without and With the Proposed Defense
Fig. 8: Comparison of recovery rules over 77 held-out days: (a) convergence rate and (b) cost change of the attacked EVs. Markers show means, and bars show standard deviations over the days.
Fig. 9: Scalability of the defense: (a) iterations to convergence over all 365 daily instances, (b) latency of a certified iteration, and (c) messages per iteration.
Quantity
Plain ADMM
Proposed
P2P echo
Messages
2N=284
4N=568
2N2+N=40,470
Payload per EV (B)
384
722
384(2N+1)
Data volume (kB)
54.5
102.5
15,540
EV computation
4.3 μ s
2.5 ms
N checks
Operator computation
17.0 μ s
12.8 ms
–
Latency per iteration
0.021 ms
15.4 ms
–
TABLE IV: Computation and Communication Cost per Iteration ( N=142 )
Cyberattack detection in electric vehicle charging infrastructure is complicated by legitimate post-activation revisions to requested energy and departure time. Charging manipulation attacks can exploit the same interface and variables; therefore, detecting a request change alone does not establish malicious intent. This paper develops a leakage-controlled session-level benchmark that preserves the ordered inputs of real Adaptive Charging Network (ACN) sessions and models legitimate revisions as normal behavior. A fixed pool keeps each generated attack in its source session's split and contains six physically motivated attacks and their coordinated variants. We compare 22 profile-only, transition-aware, and context-stratified model families under common source-grouped folds, attack data, and operating constraints. The proposed Dual-Branch Masked-Autoencoder (Masked-AE) Transition Boost model evaluates whether the current request is normal and whether its producing transition resembles an observed benign update. Its state branch combines masked reconstruction with a radial-basis-function one-class support boundary, while its transition branch combines masked reconstruction with shrinkage covariance distance. Source-grouped five-fold cross-validation selects complete configurations under explicit overall-normal and benign-update acceptance constraints; disjoint normal data then calibrate the final threshold before one test evaluation. The developed dual-branch model provides the strongest robust validation performance while detecting malicious request manipulations without learning to reject legitimate user choices.
Hannan Chen, Roshni Anna Jacob, Jie Zhang
Department of Mechanical Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA
The electrification of transportation through electric vehicles introduces new challenges for power grid management, such as increased peak demand, voltage fluctuations, line overloads, and the integration of variable renewable energy sources. To enable efficient integration of EVs while minimizing costs for users and avoiding network overloads, implicit coordination between EVs is required. This work compares two independent multi-agent reinforcement learning approaches for optimizing such decentralized EV charging: contextual combinatorial bandits and policy gradient algorithms. Using a realistic simulation environment with autonomous agents making decisions based on local environmental information (including price signals, state-of-charge, and temporal constraints), we evaluate their performance across varying congestion levels, and mixed-strategy configurations with heterogeneous agent groups under dynamic electricity pricing derived from real photovoltaic production data.
Mitigating cybersecurity risk in electric vehicle (EV) charging demand forecasting plays a crucial role in the safe operation of collective EV chargings, the stability of the power grid, and the cost-effective infrastructure expansion. However, existing methods either suffer from the data privacy issue and the susceptibility to cyberattacks or fail to consider the spatial correlation among different stations. To address these challenges, a federated graph learning approach involving multiple charging stations is proposed to collaboratively train a more generalized deep learning model for demand forecasting while capturing spatial correlations among various stations and enhancing robustness against potential attacks. Firstly, for better model performance, a Graph Neural Network (GNN) model is leveraged to characterize the geographic correlation among different charging stations in a federated manner. Secondly, to ensure robustness and deal with the data heterogeneity in a federated setting, a message passing that utilizes a global attention mechanism to aggregate personalized models for each client is proposed. Thirdly, by concerning cyberattacks, a special credit-based function is designed to mitigate potential threats from malicious clients or unwanted attacks. Extensive experiments on a public EV charging dataset are conducted using various deep learning techniques and federated learning methods to demonstrate the prediction accuracy and robustness of the proposed approach.
Yi Li, Renyou Xie, Chaojie Li +2
College of Electronic and Information Engineering, Southwest University · Department of Electrical Engineering, City University of Hong Kong, Hong Kong · Department of Electrical and Electronic Engineering, the University of Hong Kong, Hong Kong