HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems

Poushali Sengupta; Sabita Maharjan; Frank Eliassen; Yan Zhang

cs.AIOct 1, 2026

HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems

Authors: Poushali Sengupta, Sabita Maharjan, Frank Eliassen, Yan Zhang

Organizations: Department of Informatics, University of Oslo, 0316 Oslo, Norway

Abstract

Balancing electricity demand and supply is increasingly difficult due to the inherent intermittency of renewable power generation and the stochastic power consumption. Grid operators require fine-grained, decision-relevant insights into household energy consumption to manage peak loads and design responsive tariffs, but increased transparency at this level raises significant privacy concerns. Traditional methods for explainable AI (XAI) can reveal sensitive information, while standard privacy techniques often reduce the usefulness of explanations. To address this issue, we introduce HXAI, a hierarchical framework that preserves privacy while enabling reasonable explainable analysis for grid-level demand management. HXAI consists of two main components: (1) a local model that generates fine-grained explanations within a secure, private environment, and (2) a zonal model that aggregates these explanations to support grid-level analysis while enforcing privacy through flexible privacy-budget management. We explicitly limit cumulative privacy exposure under repeated operator queries and show that the proposed framework preserves decision-relevant information without compromising household privacy. Experiments on both simulated and real-world energy datasets demonstrate that HXAI provides useful insights for zonal load management while ensuring that appliance-level consumption remains local and is never transmitted to grid operators. Our results show that preserving the semantic structure of explanations, rather than minimizing numerical error, is the key to XAI under differential privacy. This framework provides a way to achieve both privacy and explainability in energy management.

Figures & tables

Symbol	Meaning
$i\in\{1,\dots,H\}$	Household (data owner) index
$k\in\{1,\dots,d\}$	Appliance / device category index
$t\in\{1,\dots,T\}$	Time index
$D_{\mathrm{local},i}$	Local multivariate time series of household $i$
$x_{i,k,t}$	Consumption of appliance $k$ at time $t$ in household $i$
$f_{\mathrm{local},i}$	Local prediction model of household $i$

TABLE II: Notation used throughout HXAI

Panel of Figure 2 — Fig. 1: End-to-end HXAI workflow. Queries are authorized via an Information Control Agreement (ICA) and executed inside a trusted Private Data Box. Local explanations remain noise-free, while only differentially private summaries are aggregated at the zonal level.

Panel of Figure 3 — Fig. 2: Explanation quality as a function of the privacy budget $\epsilon$ across three real-world datasets. Each panel reports mean absolute error (MAE), ranking stability (Spearman), and cosine utility. Shaded regions indicate one standard deviation across random seeds.

Panel of Figure 4 — Fig. 3: Comparison of oracle, local-DP, and zonal-DP SHAP bar plots at moderate privacy ( $\epsilon\approx 1.05$ ). Local explanations suffer from sign flips and unstable ordering, while zonal HXAI explanations preserve dominant features and semantic structure.

Dataset	Method	Utility $\uparrow$	Rank $\uparrow$	MAE $\downarrow$
Appliances	HXAI (same $\epsilon$ )	0.9999	0.9991	0.25
Bike	HXAI (same $\epsilon$ )	0.9999	0.9854	0.25
Household	HXAI (neg. $\epsilon$ )	0.9908	0.4162	0.22
Appliances	Central DP	0.65	0.45	29.45
Household	Central DP	0.74	0.17	0.45

TABLE III: Best explanation quality achieved per dataset and method (mean

\pm

std over seeds).

Panel of Figure 6 — Fig. 4: Top-10 feature rank-flow trajectories under increasing privacy noise for HXAI. Near-diagonal trajectories indicate stable semantic ordering. Negotiated privacy allocation yields tighter rank trajectories in heterogeneous attribution regimes.

Panel of Figure 7 — Fig. 5: Comparison of Top-10 feature rank-flow trajectories under increasing privacy noise for the UCI Appliances dataset. Central DP-SHAP exhibits unstable and crossing rank trajectories even in a homogeneous attribution regime, while HXAI preserves near-diagonal, stable rank structure.

Fig. 6: Noise-free local SHAP explanation for an individual household. The plot shows how different appliances contribute to energy consumption over time. This report is computed and consumed locally within the household’s Private Data Box and is never shared externally.

Fig. 7: Zonal SHAP explanations before and after privacy-preserving noise application. While noise introduces small numerical variability, the relative importance and ordering of dominant appliances remain stable.

Fig. 8: Zonal energy consumption report with and without privacy noise. Aggregation suppresses noise while preserving overall demand patterns relevant for grid operation.

Fig. 9: Privacy budget negotiation for an individual household: (a) initial strict privacy budget resulting in low utility, (b) negotiated privacy–utility trade-off with stabilized utility at $\epsilon=6.73$ , and (c) corresponding local SHAP explanation at the negotiated budget, preserving semantic structure.

Fig. 10: Predicted hourly electricity prices before and after an appliance upgrade intervention informed by zonal HXAI explanations. Peak prices are significantly reduced, resulting in a smoother and more stable price curve.

Fig. 11: Utility comparison between specific (appliance-level) and general (aggregate) queries under differential privacy. Specific queries provide higher utility but consume more privacy budget.

Fig. 12: Accumulated privacy leakage and utility over repeated queries. Once the negotiated privacy budget is exhausted, households automatically deny further queries.

Panel of Figure 15 — Fig. 13: Query handling and privacy accounting workflow in HXAI.

Explore similar work

Apr 27, 2026cs.CR

X-NegoBox: An Explainable Privacy-Budget Negotiation Framework for Secure Peer-to-Peer Energy Data Exchange

The decentralization of modern energy systems is transforming consumers into prosumers who continuously exchange data with aggregators, peers, and market operators. While such data is essential for peer-to-peer trading, demand response, and distributed forecasting, it can reveal sensitive household patterns and introduce privacy risks. Existing data sharing mechanisms rely on fixed policies or predefined differential privacy budgets, limiting their ability to adapt to variations in reliability, data sensitivity, and request purpose. As a result, prosumers rarely receive explanations for why a request is accepted, rejected, or modified, reducing trust and participation. To address these limitations, we propose X-NegoBox, an explainable negotiation framework for adaptive privacy budgeting and transparent decision making. Each prosumer data is managed locally within a private DataBox, where raw data remain confined. Incoming requests are processed by an Autonomous Privacy Budget Negotiation Protocol (APBNP), which determines an appropriate privacy budget based on trust, feature sensitivity, declared purpose, historical behavior, and risk-aware pricing. When needed, APBNP generates privacy-preserving counter-offers, such as reduced resolution or duration. An Explainable Agreement Layer (X-Contract) produces human- and machine-readable justifications for each decision. After agreement, requester code executes locally in a sandbox, and only sanitized outputs are shared. Experiments on realistic energy market settings show reduced privacy leakage, higher acceptance rates, and improved interpretability.

Poushali Sengupta, Sabita Maharjan, Frank Eliassen +1

Department of Informatics, University of Oslo, Norway · *University of Electronic Science and Technology of China

Automated Negotiation Differential Privacy Privacy-Utility Tradeoff

Ask PDF

Sep 10, 2026cs.AI

Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models

Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret. Explainable Artificial Intelligence (XAI) techniques address this opacity, but traditional XAI dashboards require substantial technical expertise and provide limited flexibility for dynamic, context-aware inquiry. Conversational XAI systems offer a promising alternative; however, previous approaches, such as TalkToModel, were constrained by rigid custom grammars and achieved only 76.8% intent-parsing accuracy. This paper introduces the Explainability Assistant, an open-source conversational XAI system that leverages the function-calling capabilities of modern Large Language Models (LLMs) to overcome these limitations. The system achieves 94% intent-parsing accuracy, supports flexible natural language interaction, and adapts to different ML problem types without task-specific fine-tuning. We present the system's architecture and report results from a comparative evaluation conducted with energy domain specialists, contrasting the Explainability Assistant with a traditional XAI dashboard. The evaluation suggests improved usability and consistent task accuracy, with all experts unanimously preferring the conversational interface for practical use.

Rodion Krjutškov, Eduard Barbu, Nikos Sakkas +1

Nupp Software Tallinn, Estonia · Institute of Computer Science University of Tartu Tartu, Estonia · Apintech Ltd POLIS-21 Group Cyprus +1

Explainable Artificial Intelligence

Ask PDF

Jun 23, 2026cs.DC

Power-Flexible AI Data Centers: A New Paradigm for Grid-Responsive Compute

The rapid expansion of artificial intelligence (AI) infrastructure is driving unprecedented growth in electricity demand from data centers. Traditional power-system planning treats large computing facilities as inflexible peak loads, leading to costly infrastructure upgrades and long delays in grid interconnection. Recent work has shown that AI clusters can reduce electricity consumption during peak demand through software-based workload orchestration. This article explores how modern GPU-based AI data centers can operate as grid-interactive assets that respond dynamically to power system conditions. We describe an architecture integrating grid signals, workload scheduling, and power telemetry for fine-grained cluster power control. Experimental results from a real-world deployment on a 130 kW GPU cluster demonstrate multiple forms of flexibility, including rapid load reduction, sustained curtailment, and carbon-aware operation while preserving service levels for priority jobs. We further demonstrate performance-aware load shifting across geographically distributed clusters, enabling workloads to migrate toward regions with lower grid stress. Together, these capabilities transform AI infrastructure from static electricity consumers into flexible resources that support grid reliability, accelerate interconnection, and improve computing sustainability.

Chris Williams, Philip Colangelo, Ayse Coskun +15

Emerald AI · Electric Power Research Institute (EPRI) · National Grid +2

Demand Response Power Systems

Ask PDF