MétaCan
Menu
Back to cohort
Record W3210979668 · doi:10.7939/r3-m0d1-8960

Coordination and Optimization of Power Distribution Systems with Stochastic Distributed Energy Resources using Artificial Intelligence

2021· article· en· W3210979668 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueUniversity of Alberta Library · 2021
Typearticle
Languageen
FieldEngineering
TopicAdvanced Research in Systems and Signal Processing
Canadian institutionsnot available
Fundersnot available
KeywordsComputer sciencePower (physics)Distributed generationEnergy (signal processing)Artificial intelligenceMathematical optimizationEngineeringMathematicsRenewable energyElectrical engineeringStatistics

Abstract

fetched live from OpenAlex

High levels of penetration of distributed photovoltaic generators can cause serious overvoltage issues, especially during periods of high power generation and light loads. It is of vital importance to gain more understanding of the system and to prepare mitigation plans before the number of PV installations reaches a critical level. Therefore, properly assessing the PV hosting capacity is necessary. In this thesis, the hosting capacities of several real circuits in Alberta, Canada are evaluated using Monte Carlo simulation-based probabilistic power flow (MCS-based PPF) method. The examined circuits are located in the cities of Fort McMurray, Lloydminster, and Drumheller. These areas represent circuits of different sizes and complexities. The hosting capacities of the three regions were determined to be 10%, 60%, and 70%, respectively. Buses impacted by PV penetration were found in all three distribution networks. Factors influencing the PV hosting capacity are also identified and analyzed. There have been many solutions proposed to mitigate the voltage problems, some of them using battery energy storage systems (BESS) at the PV generation sites. In addition to their ability to absorb extra power during the light load periods, BESS can also supply additional power under high load conditions. However, their capacity may not be sufficient to allow charging every time when power absorption is desired. Therefore, typical PV/BESS may not fully prevent over-voltage problems in power distribution grids. This thesis develops a cooperative state of charge control scheme to alleviate the BESS capacity problem through Monte-Carlo Tree Search based reinforcement learning (MCTS-RL). The proposed intelligent method coordinates the distributed batteries from other regions to provide voltage regulation in a distribution network. Furthermore, the energy optimization process during the day hours and the simultaneous state of charge control are achieved using model predictive control (MPC). The proposed approach is demonstrated on two test cases, the IEEE 33 bus system and a practical medium size distribution system in Alberta Canada. Optimization technology is developing to the point of becoming a cost-effective enabler of increased utilization of power transfer assets. This research presents a smart decomposition technique for the traditional optimal power flow (OPF) algorithm to allow distributed optimal power flow (DOPF) calculations without relying on a centralized controller. Hence, it develops a feasible distributed architectures for the electric power industry. The proposed method is implemented using the same algorithm MCTS-RL. This reduces computational complexity and avoids difficulties associated with stochastic modeling often used to capture the random nature of distributed energy resources (DER) units and loads. The efficiency of the optimization process is improved when the DOPF reflects the fast response capability of the optimal solution. This contribution provides results for a real-time dispatchable resource and demonstrates the flexibility of RL to adapt to changes in system states, ultimately reducing the generation cost while maintaining the system security constraints. This thesis also develops a decomposition methodology for the traditional optimal power flow. It not only avoids the challenges associated with the stochastic nature of DERs and loads, but it also reduces the computational complexity of the conventional linear programming approach in the optimization problem. It does so using machine learning algorithms employed for two crucial tasks. First, MCTS-RL identifies clusters of network nodes to form a distributed architecture suitable for electric power transactions. Second, the network states updated by RL are used to execute conventional linear programming on a reduced set of lines identified during the previous step. The proposed approach is demonstrated through a real-time balancing electricity market constructed over the IEEE 69-bus system and enhanced using price signals based on distribution locational marginal prices. This application clearly shows the ability of the new technique to effectively coordinate multiple distribution system entities while maintaining system security constraints.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.879
Threshold uncertainty score0.257

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.010
GPT teacher head0.188
Teacher spread0.178 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it