Axel Tidemann

Short-Term Load Forecasting With Seasonal Decomposition Using Evolution for Parameter Tuning

This paper studies data-driven short-term load forecasting, where historic data are used to predict the expected load for the next 24 h. Our focus is to simplify and automate the estimation and analysis of various forecasting models. We propose a three-stage approach to load forecasting, consisting of preprocessing, forecasting, and postprocessing, where the forecasting stage uses evolution to automatically set the parameters for each model. In our implementation, the preprocessing stage includes removal of daily and weekly seasonality by a nonparametric method. This seasonal pattern is added in the postprocessing stage. The system allows for easy exploration of several forecasting models, without the need to have in-depth knowledge of how to obtain the best performance for each model. We apply the method to several forecasting algorithms and on three datasets: (1) distribution substation; (2) GEFCom 2012; and (3) a transmission level dataset. We find that the forecasting algorithms considered produce significantly more accurate forecasts when combined with our proposed preprocessing stage compared with applying the same algorithms directly on the raw data. We also find that the parameter values chosen by evolution often provide insights into the interplay between the different datasets and forecast models. Software is available online.

Self-organizing multiple models for imitation: teaching a robot to dance the YMCA

The traditional approach to implement motor behaviour in a robot required a programmer to carefully decide the joint velocities at each timestep. By using the principle of learning by imitation, the robot can instead be taught simply by showing it what to do. This paper investigates the self-organization of a connectionist modular architecture for motor learning and control that is used to imitate human dancing. We have observed that the internal representation of a motion behaviour tends to be captured by more than one module. This supports the hypothesis that a modular architecture for motor learning is capable of self-organizing the decomposition of a movement.

Effects of data cleansing on load prediction algorithms

The rollout of advanced metering infrastructure that is planned in many countries worldwide will lead to a massive inflow of data from moderately reliable sensory equipment. In principle, this will make intelligent and automated planning and operation possible at an increasingly finer scale in the electric grid. However, errors can creep into the meter data, either from faulty sensors or during transmission from the meters to the database. This work studies the role of data cleansing as a preprocessing step for short-term (24-hour) power load prediction. We focus on cleansing and prediction at several levels of granularity, from the transmission level via distribution substations down to single households. We believe that preprocessing filters such as cleansing should lead to more robustness and/or precision in the subsequent processing step. However, load cleansing frameworks tend to make the popular assumption of normally and independently distributed noise in the time series. We show that this is incorrect at the diurnal level, due to the characteristic pattern of power consumption, with two peak loads during daytime and a nighttime trough. Moreover, we present empirical evidence that a preprocessing step based on this assumption fails to contribute positively to the performance of the subsequent prediction step. To rectify this problem, we suggest to subtract the average power load consumption in a given period before cleansing. We present empirical evidence that this improves the robustness and efficiency of load cleansing as a preprocessing step. Data cleansing and load prediction is performed by a system that searches out parameters using an evolutionary approach.

A Drum Machine That Learns to Groove

Music production relies increasingly on advanced hardware and software tools that makes the creative process more flexible and versatile. The advancement of these tools helps reduce both the time and money required to create music. This paper presents research towards enhancing the functionality of a key tool, the drum machine. We add the ability to learn how to groovefrom human drummers, an important human quality when it comes to drumming. We show how the learning drum machine overcomes limitations of traditional drum machines.

A review of case-based reasoning in cognition–action continuum: a step toward bridging symbolic and non-symbolic artificial intelligence

In theories and models of computational intelligence, cognition and action have historically been investigated on separate grounds. We conjecture that the main mechanism of case-based reasoning (CBR) applies to cognitive tasks at various levels and of various granularity, and hence can represent a bridge - or a continuum - between the higher and lower levels of cognition. CBR is an artificial intelligence method that draws upon the idea of solving a new problem reusing similar past experiences. In this paper we re-formulate the notion of CBR to highlight the commonalities between higher level cognitive tasks such as diagnosis, and lower level control such as voluntary movements of an arm. In this view, CBR is envisaged as a generic process independent from the content and the detailed format of cases. Diagnostic cases and internal representations underlying motor control constitute two instantiations of the case representation. In order to claim such a generic mechanism, the account of CBR needs to be revised so that its position in non-symbolic AI becomes clearer. The paper reviews the CBR literature that targets lower levels of cognition to show how CBR may be considered as a step toward bridging the gap between symbolic and nonsymbolic AI.

Learning Dance Movements by Imitation: A Multiple Model Approach

Imitation learning is an intuitive and easy way of programming robots. Instead of specifying motor commands, you simply show the robot what to do. This paper presents a modular connectionist architecture that enables imitation learning in a simulated robot. The robot imitates human dance movements, and the architecture self-organizes the decomposition of movements into submovements, which are controlled by different modules. Modules both dominate and collaborate during control of the robot. Low-level examination of the inverse models (i.e. motor controllers) reveals a recurring pattern of neural activity during repetition of movements, indicating that the modules successfully capture specific parts of the trajectory to be imitated.

Agent-Based Simulation of Stakeholder Behaviour through Evolutionary Game Theory

Aquaculture organizations establish facilities at the coast in Froya, Norway. The facilities block the surrounding area from fishing and cause environmental damage to close natural resources. Fishers who depend on those natural resources get the opportunity to influence the aquaculture expansion through complaints about the municipality’s coastal plan. Statistics show that fishers don’t complain as much as expected. This work aims to investigate why. An agent-based simulation is developed in order to model the fishers as intelligent agents with complex interaction. Fishermen’s decision making is simulated through an artificial neural network which adapts its behavior (i.e. weights) by “learning-by-imitation”, a method in evolutionary game theory, from other stakeholders’ behavior in the environment. The promising results show that with further development the simulation system may be part of a decision support system that promotes policies that are fair for the stakeholders.

Operational support in fish farming through case-based reasoning

Farmed fish is the third biggest export in Norway (around NOK 30 billion/€3.82 billion/US

Using Multiple Models to Imitate Drumming

5.44 billion in 2010), and large fish farms have biomass worth around NOK 150 million/€19.38 million/US

[self.]: Realization / Art Installation / Artificial Intelligence: A Demonstration

26.72 million. Several processes are automated (e.g. the feeding system), and sensory logging systems are becoming ubiquitous. Still, the key to successful management of a site is the operational knowledge possessed by the fish farmers. In most cases, this information is not stored formally. To capture, store and reuse this knowledge in a more systematic way is called for. We present a system that employs case-based reasoning (CBR) for such knowledge management, combined with sensor data and numerical models. The CBR system will ultimately be the core part of a decision support for regional managers surveying fish farming sites. Data is acquired from multiple fish farms, spanning several years. We present recent results in testing how well the CBR system finds similar cases. An important part of this test is the evaluation of three different methods for case retrieval (kNN, linear programming for setting feature weights, Echo State Network).